README_2023.md

General Information
Repository Size and Activity
Contribution Statistics
Other Metrics
Application
Progress Status
Main

---

INTERSPEECH 2023 Papers: A complete collection of influential and exciting research papers from the INTERSPEECH 2023 conference. Explore the latest advances in speech and language processing. Code included. ⭐ the repository to support the advancement of speech technology!

Main

👉 * This count includes repositories on GitHub, GitLab, Hugging Face, and distributions on PyPI, while excluding Web Page or GitHub Page links.

---

Tip

The PDF version of the INTERSPEECH 2023 Conference Programme, comprises a list of all accepted full papers, their presentation order, as well as the designated presentation times.

---

Other collections of the best AI conferences

Important

Conference table will be up to date all the time.

Conference	Year
	2023	2024
Computer Vision (CV)
CVPR
ICCV
ECCV
WACV	➖
FG	➖
Speech/Signal Processing (SP/SigProc)
ICASSP
INTERSPEECH
ISMIR		➖
Natural Language Processing (NLP)
EMNLP
Machine Learning (ML)
AAAI	➖
ICLR	➖
ICML	➖
NeurIPS	➖

---

Contributors

Note

Contributions to improve the completeness of this list are greatly appreciated. If you come across any overlooked papers, please feel free to create pull requests, open issues or contact me via email. Your participation is crucial to making this repository even better.

---

Papers

Section	Papers
Resources for Spoken Language Processing
Speech Synthesis: Prosody and Emotion
Statistical Machine Translation
Self-Supervised Learning in ASR
Prosody
Speech Production
Dysarthric Speech Assessment
Speech Coding: Transmission
Speech Recognition: Signal Processing, Acoustic Modeling, Robustness, Adaptation
Analysis of Speech and Audio Signals
Speech Recognition: Architecture, Search, and Linguistic Components
Speech Recognition: Technologies and Systems for New Applications
Lexical and Language Modeling for ASR
Language Identification and Diarization
Speech Quality Assessment
Feature Modeling for ASR
Interfacing Speech Technology and Phonetics
Speech Synthesis: Multilinguality
Speech Emotion Recognition
Spoken Dialog Systems and Conversational Analysis
Speech Coding and Enhancement
Paralinguistics
Speech Enhancement and Denoising
Speech Synthesis: Evaluation
End-to-End Spoken Dialog Systems
Biosignal-enabled Spoken Communication
Neural-based Speech and Acoustic Analysis

List of sections

• DiGo - Dialog for Good: Speech and Language Technology for Social Good
• Spoken Language Processing: Translation, Information Retrieval, Summarization, Resources, and Evaluation
• Speech, Voice, and Hearing Disorders
• Spoken Term Detection and Voice Search
• Models for Streaming ASR
• Source Separation
• Speech Perception
• Phonetics and Phonology: Languages and Varieties
• Speaker and Language Identification
• Speech Synthesis and Voice Conversion
• Speech and Language in Health: from Remote Monitoring to Medical Conversations
• Novel Transformer Models for ASR
• Speaker Recognition
• Cross-lingual and Multilingual ASR
• Voice Conversion
• Pathological Speech Analysis
• Multimodal Speech Emotion Recognition
• Phonetics, Phonology, and Prosody
• Speech Coding: Privacy
• Analysis of Neural Speech Representations
• End-to-end ASR
• Spoken Language Understanding, Summarization, and Information Retrieval
• Invariant and Robust Pre-trained Acoustic Models
• Speech Synthesis: Representation Learning
• Speech Perception, Production, and Acquisition
• Acoustic Model Adaptation for ASR
• Speech Synthesis: Expressivity
• Multi-modal Systems
• Question Answering from Speech
• Multi-talker Methods in Speech Processing
• Sociophonetics
• Speaker and Language Diarization
• Anti-Spoofing for Speaker Verification
• Speech Coding: Intelligibility
• New Computational Strategies for ASR Training and Inference
• MERLIon CCS Challenge: Multilingual Everyday Recordings - Language Identification On Code-Switched Child-Directed Speech
• Health-Related Speech Analysis
• Automatic Audio Classification and Audio Captioning
• Speech Synthesis
• Speech Synthesis: Controllability and Adaptation
• Search Methods and Decoding Algorithms for ASR
• Speech Signal Analysis
• Connecting Speech-science and Speech-technology for Children's Speech
• Dialog Management
• Speech Activity Detection and Modeling
• Multilingual Models for ASR
• Speech Enhancement and Bandwidth Expansion
• Articulation
• Neural Processing of Speech and Language: Encoding and Decoding the Diverse Auditory Brain
• Perception of Paralinguistics
• Technologies for Child Speech Processing
• Speech Synthesis: Multilinguality; Evaluation
• Show and Tell: Health Applications and Emotion Recognition
• Show and Tell: Speech Tools, Speech Enhancement, Speech Synthesis
• Show and Tell: Language Learning and Educational Resources
• Show and Tell: Media and Commercial Applications

DiGo - Dialog for Good: Speech and Language Technology for Social Good

🆔	Title	Repo	Paper
2194	A Multimodal Investigation of Speech, Text, Cognitive and Facial Video Features for Characterizing Depression with and without Medication	➖
307	Understanding Disrupted Sentences using Underspecified Abstract Meaning Representation
2109	Developing Speech Processing Pipelines for Police Accountability	➖
2086	Prosody-Controllable Gender-Ambiguous Speech Synthesis: A Tool for Investigating Implicit Bias in Speech Perception
848	Affective Attributes of French Caregivers' Professional Speech	➖

Spoken Language Processing: Translation, Information Retrieval, Summarization, Resources, and Evaluation

🆔	Title	Repo	Paper
180	Pragmatic Pertinence: A Learnable Confidence Metric to Assess the Subjective Quality of LM-Generated Text	➖
2078	ASR and Emotional Speech: A Word-Level Investigation of the Mutual Impact of Speech and Emotion Recognition	➖
916	BASS: Block-wise Adaptation for Speech Summarization
1258	Speaker Tracking using Graph Attention Networks with Varying Duration Utterances in Multi-Channel Naturalistic Data: Fearless Steps Apollo 11 Audio Corpus	➖
36	Combining Language Corpora in a Japanese Electromagnetic Articulography Database for Acoustic-to-Articulatory Inversion	➖
523	A Dual Attention-based Modality-Collaborative Fusion Network for Emotion Recognition
2174	Large Dataset Generation of Synchronized Music Audio and Lyrics at Scale using Teacher-Student Paradigm	➖
483	Enc-Dec RNN Acoustic Word Embeddings Learned via Pairwise Prediction
864	Query based Acoustic Summarization for Podcasts	➖
1242	Spot Keywords from Very Noisy and Mixed Speech	➖
891	Knowledge Distillation on Joint Task End-to-End Speech Translation	➖
343	Investigating Pre-trained Audio Encoders in the Low-Resource Condition
1718	Improving Textless Spoken Language Understanding with Discrete Units as Intermediate Target	➖
823	MAVD: The First Open Large-Scale Mandarin Audio-Visual Dataset with Depth Information
1674	CN-Celeb-AV: A Multi-Genre Audio-Visual Dataset for Person Recognition
1762	Improving Zero-Shot Cross-Domain Slot Filling via Transformer-based Slot Semantics Fusion	➖
619	Rethinking Transfer and Auxiliary Learning for Improving Audio Captioning Transformer	➖
1468	Boosting Punctuation Restoration with Data Generation and Reinforcement Learning	➖
695	J-ToneNet: A Transformer-based Encoding Network for Improving Tone Classification in Continuous Speech via F0 Sequences	➖
1152	Towards Cross-Language Prosody Transfer for Dialog
2506	Strategies for Improving Low Resource Speech to Text Translation Relying on Pre-trained ASR Models	➖
1980	ITALIC: An Italian Intent Classification Dataset
1778	Perceptual and Task-Oriented Assessment of a Semantic Metric for ASR Evaluation	➖
1466	How ChatGPT is Robust for Spoken Language Understanding?	➖
1233	GigaST: A 10,000-hour Pseudo Speech Translation Corpus
1570	Boosting Chinese ASR Error Correction with Dynamic Error Scaling Mechanism	➖
2473	Crowdsource-based Validation of the Audio Cocktail as a Sound Browsing Tool	➖
1675	PunCantonese: A Benchmark Corpus for Low-Resource Cantonese Punctuation Restoration from Speech Transcripts
1358	Speech-to-Face Conversion using Denoising Diffusion Probabilistic Models	➖
2255	Inter-Connection: Effective Connection between Pre-trained Encoder and Decoder for Speech Translation	➖
1068	How Does Pretraining Improve Discourse-aware Translation?	➖
1135	PATCorrect: Non-Autoregressive Phoneme-Augmented Transformer for ASR Error Correction	➖
161	Model-assisted Lexical Tone Evaluation of Three-Year-Old Chinese-Speaking Children by also Considering Segment Production	➖
1392	Sentence Embedder Guided Utterance Encoder (SEGUE) for Spoken Language Understanding
1582	Joint Time and Frequency Transformer for Chinese Opera Classification	➖
116	AdaMS: Deep Metric Learning with Adaptive Margin and Adaptive Scale for Acoustic Word Discrimination	➖
2252	Investigating Reproducibility at Interspeech Conferences: A Longitudinal and Comparative Perspective	➖
2250	Combining Heterogeneous Structures for Event Causality Identification	➖
1208	An Efficient Approach for the Automated Segmentation and Transcription of the People's Speech Corpus	➖
1425	Diverse Feature Mapping and Fusion via Multitask Learning for Multilingual Speech Emotion Recognition	➖
903	Take the Hint: Improving Arabic Diacritization with Partially-Diacritized Text
466	Low-Resource Cross-Lingual Adaptive Training for Nigerian Pidgin
1878	Efficient Adaptation of Spoken Language Understanding based on End-to-End Automatic Speech Recognition	➖
597	PhonMatchNet: Phoneme-Guided Zero-Shot Keyword Spotting for User-Defined Keywords
69	Mix before Align: Towards Zero-Shot Cross-Lingual Sentiment Analysis via Soft-Mix and Multi-View Learning	➖
170	AlignAtt: using Attention-based Audio-Translation Alignments as a Guide for Simultaneous Speech Translation	➖
2225	Incremental Blockwise Beam Search for Simultaneous Speech Translation with Controllable Quality-Latency Tradeoff	➖
1979	Zambezi Voice: A Multilingual Speech Corpus for Zambian Languages

Speech, Voice, and Hearing Disorders

🆔	Title	Repo	Paper
2421	Debiased Automatic Speech Recognition for Dysarthric Speech via Sample Reweighting with Sample Affinity Test	➖
2198	Multimodal Locally Enhanced Transformer for Continuous Sign Language Recognition	➖
1759	Towards Supporting an Early Diagnosis of Multiple Sclerosis using Vocal Features	➖
1891	Whisper Features for Dysarthric Severity-Level Classification	➖
2191	A New Benchmark of Aphasia Speech Recognition and Detection based on E-Branchformer and Multi-task Learning
222	Dysarthric Speech Recognition, Detection and Classification using Raw Phase and Magnitude Spectra	➖
2026	A Stutter Seldom Comes Alone - Cross-Corpus Stuttering Detection as a Multi-label Problem	➖
1542	Transfer Learning to Aid Dysarthria Severity Classification for Patients with Amyotrophic Lateral Sclerosis	➖
2203	DuTa-VC: A Duration-aware Typical-to-Atypical Voice Conversion Approach with Diffusion Probabilistic Model
201	CNVVE: Dataset and Benchmark for Classifying Non-verbal Voice
1541	Arabic Dysarthric Speech Recognition using Adversarial and Signal-based Augmentation
1887	Weakly-Supervised Forced Alignment of Disfluent Speech using Phoneme-level Modeling
1998	Glottal Source Analysis of Voice Deficits in Basal Ganglia Dysfunction: Evidence from de novo Parkinson's Disease and Huntington's Disease	➖
2478	An Analysis of Glottal Features of Chronic Kidney Disease Speech and its Application to CKD Detection	➖
983	Weakly Supervised Glottis Segmentation in High-Speed Video Endoscopy using Bounding Box Labels	➖
1669	Investigating the Dynamics of Hand and Lips in French Cued Speech using Attention Mechanisms and CTC-based Decoding	➖
670	Hearing Loss Affects Emotion Perception in Older Adults: Evidence from a Prosody-Semantics Stroop Task	➖
554	Cochlear-Implant Listeners Listening to Cochlear-Implant Simulated Speech	➖
2168	Validation of a Task-Independent Cepstral Peak Prominence Measure with Voice Activity Detection	➖
1679	Score-balanced Loss for Multi-aspect Pronunciation Assessment
2108	Federated Learning for Secure Development of AI Models for Parkinson's Disease Detection using Speech from Different Languages	➖
652	F0inTFS: A Lightweight Periodicity Enhancement Strategy for Cochlear Implants	➖
1678	Differentiating Acoustic and Physiological Features in Speech for Hypoxia Detection	➖
786	Mandarin Electrolaryngeal Speech Voice Conversion using Cross-Domain Features	➖
866	Audio-Visual Mandarin Electrolaryngeal Speech Voice Conversion	➖
1744	Which Aspects of Motor Speech Disorder are Captured by Mel Frequency Cepstral Coefficients? Evidence from the Change in STN-DBS Conditions in Parkinson's Disease	➖
1096	Detecting Manifest Huntington's Disease using Vocal Data	➖
1623	Exploring Multi-Task Learning and Data Augmentation in Dementia Detection with Self-Supervised Pre-trained Models	➖

Spoken Term Detection and Voice Search

🆔	Title	Repo	Paper
478	Matching Latent Encoding for Audio-Text based Keyword Spotting	➖
1215	Self-Paced Pattern Augmentation for Spoken Term Detection in Zero-Resource	➖
2362	On-Device Constrained Self-Supervised Speech Representation Learning for Keyword Spotting via Knowledge Distillation	➖
90	Online Continual Learning in Keyword Spotting for Low-Resource Devices via Pooling High-Order Temporal Statistics	➖
689	Improving Small Footprint Few-Shot Keyword Spotting with Supervision on Auxiliary Data	➖
2222	Robust Keyword Spotting for Noisy Environments by Leveraging Speech Enhancement and Speech Presence Probability	➖

Models for Streaming ASR

🆔	Title	Repo	Paper
831	Enhancing the Unified Streaming and Non-Streaming Model with Contrastive Learning	➖
1497	ZeroPrompt: Streaming Acoustic Encoders are Zero-Shot Masked LMs	➖
361	Improved Training for End-to-End Streaming Automatic Speech Recognition Model with Punctuation	➖
1129	DCTX-Conformer: Dynamic Context Carry-over for Low Latency Unified Streaming and Non-Streaming Conformer	➖
1121	Knowledge Distillation from Non-Streaming to Streaming ASR Encoder using Auxiliary Non-Streaming Layer	➖
884	Adaptive Contextual Biasing for Transducer based Streaming Speech Recognition	➖

Source Separation

🆔	Title	Repo	Paper
1753	Audio-Visual Speech Separation in Noisy Environments with a Lightweight Iterative Model
1389	Remixing-based Unsupervised Source Separation from Scratch	➖
577	CAPTDURE: Captioned Sound Dataset of Single Sources	➖
488	Recursive Sound Source Separation with Deep Learning-based Beamforming for Unknown Number of Sources	➖
2537	Multi-Channel Speech Separation with Cross-Attention and Beamforming	➖
185	Background-Sound Controllable Voice Source Separation	➖

Speech Perception

🆔	Title	Repo	Paper
1922	A Neural Architecture for Selective Attention to Speech Features	➖
1122	Quantifying Informational Masking due to Masker Intelligibility in Same-Talker Speech-in-Speech Perception	➖
1476	On the Benefits of Self-Supervised Learned Speech Representations for Predicting Human Phonetic Misperceptions	➖
2154	Predicting Perceptual Centers Located at Vowel Onset in German Speech using Long Short-Term Memory Networks	➖
63	Exploring the Mutual Intelligibility Breakdown Caused by Sculpting Speech from a Competing Speech Signal	➖
2103	Perception of Incomplete Voicing Neutralization of Obstruents in Tohoku Japanese	➖

Phonetics and Phonology: Languages and Varieties

🆔	Title	Repo	Paper
1879	The Emergence of Obstruent-Intrinsic f0 and VOT as Cues to the Fortis/Lenis Contrast in West Central Bavarian	➖
431	〈'〉 in Tsimane': A Preliminary Investigation
2200	Segmental Features of Brazilian (Santa Catarina) Hunsrik	➖
2337	Opening or Closing? An Electroglottographic Analysis of Voiceless Coda Consonants in Australian English	➖
295	Increasing Aspiration of Word-Medial Fortis Plosives in Swiss Standard German	➖
1456	Lexical Stress and Velar Palatalization in Italian: A Spatio-Temporal Interaction	➖

Speaker and Language Identification

🆔	Title	Repo	Paper
1989	Vietnam-Celeb: A Large-Scale Dataset for Vietnamese Speaker Recognition
2254	What Can an Accent Identifier Learn? Probing Phonetic and Prosodic Information in a Wav2vec2-based Accent Identification Model
241	The 2022 NIST Language Recognition Evaluation	➖
155	Description and Analysis of the KPT system for NIST Language Recognition Evaluation 2022	➖
1725	ACA-Net: Towards Lightweight Speaker Verification using Asymmetric Cross Attention
402	Branch-ECAPA-TDNN: A Parallel Branch Architecture to Capture Local and Global Features for Speaker Verification	➖
2052	Speaker Verification Across Ages: Investigating Deep Speaker Embedding Sensitivity to Age Mismatch in Enrollment and Test Speech	➖
2569	Wavelet Scattering Transform for Improving Generalization in Low-Resourced Spoken Language Identification	➖
1407	A Parameter-Efficient Learning Approach to Arabic Dialect Identification with Pre-trained General Purpose Speech Model
2272	HABLA: A Dataset of Latin American Spanish Accents for Voice Anti-Spoofing
1702	Self-Supervised Learning Representation based Accent Recognition with Persistent Accent Memory	➖
800	Extremely Low Bit Quantization for Mobile Speaker Verification Systems Under 1MB Memory	➖
1974	Unsupervised Out-of-Distribution Dialect Detection with Mahalanobis Distance	➖
105	Pyannote.Audio 2.1 Speaker Diarization Pipeline: Principle, Benchmark and Recipe
1524	Model Compression for DNN-based Speaker Verification using Weight Quantization	➖
1354	Multi-Resolution Approach to Identification of Spoken Languages and to Improve Overall Language Diarization System using Whisper Model	➖
125	Improving Generalization Ability of Countermeasures for New Mismatch Scenario by Combining Multiple Advanced Regularization Terms	➖
849	Dynamic Fully-Connected Layer for Large-Scale Speaker Verification	➖
844	Reversible Neural Networks for Memory-Efficient Speaker Verification	➖
777	ECAPA++: Fine-grained Deep Embedding Learning for TDNN based Speaker Verification	➖
1206	TO-Rawnet: Improving RawNet with TCN and Orthogonal Regularization for Fake Audio Detection	➖
100	Fooling Speaker Identification Systems with Adversarial Background Music	➖
1314	Mutual Information-based Embedding Decoupling for Generalizable Speaker Verification	➖
574	Target Active Speaker Detection with Audio-Visual Cues
2401	Improving End-to-End Neural Diarization using Conversational Summary Representations	➖
2039	Phase Perturbation Improves Channel Robustness for Speech Spoofing Countermeasures
210	Improving Training Datasets for Resource-constrained Speaker Recognition Neural Networks	➖
1498	Instance-based Temporal Normalization for Speaker Verification	➖
881	On the Robustness of Wav2Vec 2.0 based Speaker Recognition Systems	➖
697	P-Vectors: A Parallel-coupled TDNN/Transformer Network for Speaker Verification
1249	Group GMM-ResNet for Detection of Synthetic Speech Attacks	➖
452	Robust Training for Speaker Verification against Noisy Labels
1404	Self-Distillation into Self-Attention Heads for Improving Transformer-based End-to-End Neural Speaker Diarization	➖
1217	Build a SRE Challenge System: Lessons from VoxSRC 2022 and CNSRC 2022
1648	Describing the Phonetics in the Underlying Speech Attributes for Deep and Interpretable Speaker Recognition
1214	Range-based Equal Error Rate for Spoof Localization	➖
1888	Exploring the English Accent-Independent Features for Speech Emotion Recognition using Filter and Wrapper-based Methods for Feature Selection	➖
205	Powerset Multi-Class Cross Entropy Loss for Neural Speaker Diarization
394	A Method of Audio-Visual Person Verification by Mining Connections between Time Series	➖
605	One-Step Knowledge Distillation and Fine-Tuning in using Large Pre-trained Self-Supervised Learning Models for Speaker Verification
409	Defense Against Adversarial Attacks on Audio DeepFake Detection
1820	A Conformer-based Classifier for Variable-Length Utterance Processing in Anti-Spoofing
1557	Conformer-based Language Embedding with Self-Knowledge Distillation for Spoken Language Identification	➖
2419	CommonAccent: Exploring Large Acoustic Pre-trained Models for Accent Classification based on Common Voice	➖
266	From Adaptive Score Normalization to Adaptive Data Normalization for Speaker Verification Systems	➖
1513	CAM++: A Fast and Efficient Network for Speaker Verification using Context-aware Masking
1928	North Sámi Dialect Identification with Self-Supervised Speech Models
2289	Encoder-Decoder Multimodal Speaker Change Detection	➖
1603	Disentangled Representation Learning for Multilingual Speaker Recognition
2310	A Compact End-to-End Model with Local and Global Context for Spoken Language Identification
1005	On the Robustness of Arabic Speech Dialect Identification	➖
927	Adaptive Neural Network Quantization for Lightweight Speaker Verification	➖
1205	Adversarial Diffusion Probability Model For Cross-Domain Speaker Verification Integrating Contrastive Loss	➖
1554	Chinese Dialect Recognition based on Transfer Learning	➖
270	Spoofing Attacker also Benefits from Self-Supervised Pretrained Model	➖
854	Label aware Speech Representation Learning for Language Identification	➖
1761	Exploring the Impact of Back-end Network on Wav2vec 2.0 for Dialect Identification	➖
453	Improving Speaker Verification with Self-pretrained Transformer Models
372	Handling the Alignment for Wake Word Detection: A Comparison Between Alignment-based, Alignment-Free and Hybrid Approaches	➖

Speech Synthesis and Voice Conversion

🆔	Title	Repo	Paper
2336	Mitigating the Exposure Bias in Sentence-Level Grapheme-to-Phoneme (G2P) Transduction	➖
160	Streaming Parrotron for On-Device Speech-to-Speech Conversion	➖
2407	Exploiting Emotion Information in Speaker Embeddings for Expressive Text-to-Speech
2518	E2E-S2S-VC: End-to-End Sequence-to-Sequence Voice Conversion
2403	DC CoMix TTS: An End-to-End Expressive TTS with Discrete Code Collaborated with Mixer
419	Voice Conversion with Just Nearest Neighbors
1193	CFVC: Conditional Filtering for Controllable Voice Conversion
1157	DualVC: Dual-mode Voice Conversion using Intra-Model Knowledge Distillation and Hybrid Predictive Coding
39	Attention-based Interactive Disentangling Network for Instance-Level Emotional Voice Conversion
836	ALO-VC: Any-to-Any Low-Latency One-Shot Voice Conversion
1978	Evaluating and Reducing the Distance between Synthetic and Real Speech Distributions	➖
2202	Decoupling Segmental and Prosodic cues of Non-Native Speech through Vector Quantization
2383	VC-T: Streaming Voice Conversion based on Neural Transducer
191	Emo-StarGAN: A Semi-Supervised Any-to-Many Non-Parallel Emotion Preserving Voice Conversion
1788	ControlVC: Zero-Shot Voice Conversion with Time-Varying Controls on Pitch and Speed
1356	Reverberation-Controllable Voice Conversion using Reverberation Time Estimator	➖
2558	Cross-Utterance Conditioned Coherent Speech Editing

Speech and Language in Health: from Remote Monitoring to Medical Conversations

🆔	Title	Repo	Paper
2287	An Automatic Multimodal Approach to Analyze Linguistic and Acoustic Cues on Parkinson's Disease Patients	➖
1332	Personalization for Robust Voice Pathology Detection in Sound Waves
2249	Integrated and Enhanced Pipeline System to Support Spoken Language Analytics for Screening Neurocognitive Disorders	➖
1990	Capturing Mismatch between Textual and Acoustic Emotion Expressions for Mood Identification in Bipolar Disorder	➖
296	FTA-Net: A Frequency and Time Attention Network for Speech Depression Detection	➖
1709	Bayesian Networks for the Robust and Unbiased Prediction of Depression and its Symptoms Utilizing Speech and Multimodal Data	➖
1263	Hyper-Parameter Adaptation of Conformer ASR Systems for Elderly and Dysarthric Speech Recognition	➖
1721	Classifying Depression Symptom Severity: Assessment of Speech Representations in Personalized and Generalized Machine Learning Models	➖
1946	Active Learning for Abnormal Lung Sound Data Curation and Detection in Asthma	➖
2079	Automatic Assessment of Alzheimer's across Three Languages using Speech and Language Features	➖
301	On-the-Fly Feature based Rapid Speaker Adaptation for Dysarthric and Elderly Speech Recognition
1722	Relationship between LTAS-based Spectral Moments and Acoustic Parameters of Hypokinetic Dysarthria in Parkinson's Disease	➖
963	Respiratory Distress Estimation in Human-Robot Interaction Scenario	➖
1771	Prediction of the Gender-based Violence Victim Condition using Speech: What do Machine Learning Models rely on?	➖
1916	Whisper Encoder features for Infant Cry Classification	➖
1997	Classifying Dementia in the Presence of Depression: A Cross-Corpus Study	➖
297	Exploiting Cross-Domain and Cross-Lingual Ultrasound Tongue Imaging Features for Elderly and Dysarthric Speech Recognition	➖
464	Multi-Class Detection of Pathological Speech with Latent Features: How does It Perform on Unseen Data?	➖
2002	Responsiveness, Sensitivity and Clinical Utility of Timing-Related Speech Biomarkers for Remote Monitoring of ALS Disease Progression	➖
322	Use of Speech Impairment Severity for Dysarthric Speech Recognition	➖
721	MMLung: Moving Closer to Practical Lung Health Estimation using Smartphones
913	Investigating the Utility of Synthetic Data for Doctor-Patient Conversation Summarization	➖
2101	Non-Uniform Speaker Disentanglement for Depression Detection from Raw Speech Signals
753	PoCaPNet: A Novel Approach for Surgical Phase Recognition using Speech and X-Ray Images
2100	Combining Multiple Multimodal Speech Features into an Interpretable Index Score for Capturing Disease Progression in Amyotrophic Lateral Sclerosis	➖
1438	The MASCFLICHT Corpus: Face Mask Type and Coverage Area Recognition from Speech
1435	Towards Reference Speech Characterization for Health Applications
2146	Automatic Classification of Hypokinetic and Hyperkinetic Dysarthria based on GMM-Supervectors	➖
947	Towards Robust Paralinguistic Assessment for Real-World Mobile Health (mHealth) Monitoring: an Initial Study of Reverberation Effects on Speech	➖

Novel Transformer Models for ASR

🆔	Title	Repo	Paper
2228	Conmer: Streaming Conformer without Self-Attention for Interactive Voice Assistants	➖
1255	Intra-Ensemble: A New Method for Combining Intermediate Outputs in Transformer-based Automatic Speech Recognition	➖
1194	A Comparative Study on E-Branchformer vs Conformer in Speech Recognition, Translation, and Understanding Tasks
1611	HyperConformer: Multi-head HyperMixer for Efficient Speech Recognition	➖
893	Memory-Augmented Conformer for Improved End-To-End Long-form ASR
552	Towards Effective and Compact Contextual Representation for Conformer Transducer Speech Recognition Systems	➖

Speaker Recognition

🆔	Title	Repo	Paper
1294	An Enhanced Res2Net with Local and Global Feature Fusion for Speaker Verification
1286	A Study on Visualization of Voiceprint Feature	➖
1083	VoxTube: A Multilingual Speaker Recognition Dataset
1298	Visualizing Data Augmentation in Deep Speaker Recognition	➖
1565	Ordered and Binary Speaker Embedding	➖
2031	Self-FiLM: Conditioning GANs with Self-Supervised Representations for Bandwidth Extension based Speaker Recognition	➖
1202	Curriculum Learning for Self-Supervised Speaker Verification	➖
1558	Introducing Self-Supervised Phonetic Information for Text-Independent Speaker Verification	➖
1379	A Teacher-Student Approach for Extracting Informative Speaker Embeddings from Speech Mixtures	➖
1479	Experimenting with Additive Margins for Contrastive Self-Supervised Speaker Verification	➖

Cross-lingual and Multilingual ASR

🆔	Title	Repo	Paper
1630	Fast and Efficient Multilingual Self-Supervised Pre-training for Low-Resource Speech Recognition	➖
1338	UniSplice: Universal Cross-Lingual Data Splicing for Low-Resource ASR	➖
772	Allophant: Cross-Lingual Phoneme Recognition with Articulatory Attributes
97	Phonetic-assisted Multi-Target Units Modeling for Improving Conformer-Transducer ASR System	➖
1061	Comparison of Multilingual Self-Supervised and Weakly-Supervised Speech Pre-training for Adaptation to Unseen Languages	➖
1444	DistilXLSR: A Light Weight Cross-Lingual Speech Representation Model

Voice Conversion

🆔	Title	Repo	Paper
251	Emotional Voice Conversion with Semi-Supervised Generative Modeling
817	Diff-HierVC: Diffusion-based Hierarchical Voice Conversion with Robust Pitch Generation and Masked Prior for Zero-Shot Speaker Adaptation
215	S2CD-VC: Self-Heuristic Speaker Content Disentanglement for Any-to-Any Voice Conversion
1508	Flow-VAE VC: End-to-End Flow Framework with Contrastive Loss for Zero-Shot Voice Conversion
1602	Automatic Speech Disentanglement for Voice Conversion using Rank Module and Speech Augmentation
2298	End-to-End Zero-Shot Voice Conversion with Location-Variable Convolutions

Pathological Speech Analysis

🆔	Title	Repo	Paper
2093	Multimodal Assessment of Bulbar Amyotrophic Lateral Sclerosis (ALS) using a Novel Remote Speech Assessment App	➖
2181	On the use of High Frequency Information for Voice Pathology Classification	➖
1784	Do Phonatory Features Display Robustness to Characterize Parkinsonian Speech Across Corpora?	➖
2531	Severity Classification of Parkinson's Disease from Speech using Single Frequency Filtering-based Features	➖
1915	Comparison of Acoustic Measures of Dysphonia in Parkinson's Disease and Huntington's Disease: Effect of Sex and Speaking Task	➖
1734	Alzheimer Disease Classification through ASR-based Transcriptions: Exploring the Impact of Punctuation and Pauses
1574	A Pipeline to Evaluate the Effects of Noise on Machine Learning Detection of Laryngeal Cancer
2474	ReCLR: Reference-Enhanced Contrastive Learning of Audio Representation for Depression Detection	➖
234	Automated Multiple Sclerosis Screening based on Encoded Speech Representations	➖
1934	Cross-Lingual Features for Alzheimer's Dementia Detection from Speech	➖
1653	Careful Whisper - Leveraging Advances in Automatic Speech Recognition for Robust and Interpretable Aphasia Subtype Classification	➖
1868	Behavioral Analysis of Pathological Speaker Embeddings of Patients During Oncological Treatment of Oral Cancer	➖

Multimodal Speech Emotion Recognition

🆔	Title	Repo	Paper
1832	LanSER: Language-Model Supported Speech Emotion Recognition	➖
463	Fine-tuned RoBERTa Model with a CNN-LSTM Network for Conversational Emotion Recognition	➖
1591	Emotion Label Encoding using Word Embeddings for Speech Emotion Recognition	➖
2444	Discrimination of the Different Intents Carried by the Same Text through Integrating Multimodal Information	➖
510	Meta-Domain Adversarial Contrastive Learning for Alleviating Individual Bias in Self-Sentiment Predictions	➖
413	SWRR: Feature Map Classifier based on Sliding Window Attention and High-Response Feature Reuse for Multimodal Emotion Recognition	➖

Phonetics, Phonology, and Prosody

🆔	Title	Repo	Paper
1443	Effects of Meter, Genre and Experience on Pausing, Lengthening and Prosodic Phrasing in German Poetry Reading	➖
1142	Comparing First Spectral Moment of Australian English /s/ between Straight and Gay Voices using Three Analysis Window Sizes	➖
2584	Universal Automatic Phonetic Transcription into the International Phonetic Alphabet
2134	Voice Twins: Discovering Extremely Similar-Sounding, Unrelated Speakers	➖
1042	Filling the Population Statistics Gap: Swiss German Reference Data on F0 and Speech Tempo for Forensic Contexts	➖
1619	Investigating the Syntax-Discourse Interface in the Phonetic Implementation of Discourse Markers	➖
2214	Evaluation of a Forensic Automatic Speaker Recognition System with Emotional Speech Recordings	➖
1052	An Outlier Analysis of Vowel Formants from a Corpus Phonetics Pipeline
340	The Hidden Dance of Phonemes and Visage: Unveiling the Enigmatic Link between Phonemes and Facial Features
1880	Beatboxing Kick Drum Kinematics	➖
536	Effects of Hearing Loss and Amplification on Mandarin Consonant Perception	➖
2020	An Acoustic Analysis of Fricative Variation in Three Accents of English	➖
109	Acoustic Cues to Stress Perception in Spanish – a Mismatch Negativity Study	➖
976	Bulgarian Unstressed Vowel Reduction: Received Views vs Corpus Findings	➖
1764	An Investigation of Indian Native Language Phonemic Influences on L2 English Pronunciations	➖
498	Identifying Stable Sections for Formant Frequency Extraction of French Nasal Vowels based on Difference Thresholds	➖
1903	Evaluation of Delexicalization Methods for Research on Emotional Speech	➖
1772	Nonbinary American English Speakers Encode Gender in Vowel Acoustics	➖
44	Coarticulation of Sibe Vowels and Dorsal Fricatives in Spontaneous Speech: An Acoustic Study	➖
1013	Using Speech Synthesis to Explain Automatic Speaker Recognition: A New Application of Synthetic Speech	➖
2534	Same F0, Different Tones: A Multidimensional Investigation of Zhangzhou Tones	➖
1985	Discovering Phonetic Feature Event Patterns in Transformer Embeddings	➖
2204	A System for Generating Voice Source Signals that Implements the Transformed LF-Model Parameter Control	➖
2352	Speaker-Independent Speech Inversion for Estimation of Nasalance	➖
1359	Effects of Tonal Coarticulation and Prosodic Positions on Tonal Contours of Low Rising Tones: In the Case of Xiamen Dialect	➖
2187	Durational and Non-Durational Correlates of Lexical and Derived Geminates in Arabic	➖
68	Mapping Phonemes to Acoustic Symbols and Codes using Synchrony in Speech Modulation Vectors Estimated by the Travellingwave Filter Bank	➖
1480	Rhythmic Characteristics of L2 German Speech by Advanced Chinese Learners	➖
1538	(Dis)agreement and Preference Structure are Reflected in Matching Along Distinct Acoustic-Prosodic Features	➖
995	Vowel Reduction by Greek-Speaking Children: The Effect of Stress and Word Length	➖
1822	Pitch Distributions in a Very Large Corpus of Spontaneous Finnish Speech	➖
828	Speech Enhancement Patterns in Human-Robot Interaction: A Cross-Linguistic Perspective

Speech Coding: Privacy

🆔	Title	Repo	Paper
1026	Masking Kernel for Learning Energy-Efficient Representations for Speaker Recognition and Mobile Health
727	eSTImate: A Real-Time Speech Transmission Index Estimator with Speech Enhancement Auxiliary Task using Self-Attention Feature Pyramid Network	➖
815	Efficient Encoder-Decoder and Dual-Path Conformer for Comprehensive Feature Learning in Speech Enhancement	➖
2138	Privacy-Preserving Representation Learning for Speech Understanding	➖
448	Vocoder Drift in X-Vector–based Speaker Anonymization
703	Malafide: A Novel Adversarial Convolutive Noise Attack Against Deepfake and Spoofing Detection Systems	➖

Analysis of Neural Speech Representations

🆔	Title	Repo	Paper
1087	Speech Self-Supervised Representation Benchmarking: Are We Doing it Right?
383	An Extension of Disentanglement Metrics and its Application to Voice	➖
2131	An Information-Theoretic Analysis of Self-Supervised Discrete Representations of Speech
1823	SpeechGLUE: How Well Can Self-Supervised Speech Models Capture Linguistic Knowledge?
1418	Comparison of GIF- and SSL-based Features in Pathological Voice Detection	➖
1617	What is Learnt by the LEArnable Front-end (LEAF)? Adapting Per-Channel Energy Normalisation (PCEN) to Noisy Conditions

End-to-end ASR

🆔	Title	Repo	Paper
1640	End-to-End Joint Target and Non-Target Speakers ASR	➖
144	Improving Frame-Level Classifier for Word Timings with Non-peaky CTC in End-to-End Automatic Speech Recognition	➖
564	Joint Autoregressive Modeling of End-to-End Multi-Talker Overlapped Speech Recognition and Utterance-Level Timestamp Prediction	➖
101	Dual-Path Style Learning for End-to-End Noise-Robust Speech Recognition
142	Multi-Pass Training and Cross-Information Fusion for Low-Resource End-to-End Accented Speech Recognition	➖
906	Text-Only Domain Adaptation for End-to-End ASR using Integrated Text-to-Mel-Spectrogram Generator	➖

Spoken Language Understanding, Summarization, and Information Retrieval

🆔	Title	Repo	Paper
461	Leveraging Pretrained ASR Encoders for Effective and Efficient End-to-End Speech Intent Classification and Slot Filling
277	Relation-based Counterfactual Data Augmentation and Contrastive Learning for Robustifying Natural Language Inference Models
1307	Transfer Learning from Pre-trained Language Models Improves End-to-End Speech Summarization	➖
1136	Audio Retrieval with WavText5K and CLAP Training
242	Sequence-Level Knowledge Distillation for Class-Incremental End-to-End Spoken Language Understanding
1652	Contrastive Disentangled Learning for Memory-Augmented Transformer	➖

Invariant and Robust Pre-trained Acoustic Models

🆔	Title	Repo	Paper
438	ProsAudit, a Prosodic Benchmark for Self-Supervised Speech Models	➖
871	Self-Supervised Predictive Coding Models Encode Speaker and Phonetic Information in Orthogonal Subspaces	➖
1862	Evaluating Context-Invariance in Unsupervised Speech Representations
1390	CoBERT: Self-Supervised Speech Representation Learning through Code Representation Learning
847	Self-Supervised Fine-tuning for Improved Content Representations by Speaker-Invariant Clustering
359	Self-Supervised Acoustic Word Embedding Learning via Correspondence Transformer Encoder	➖

Speech Synthesis: Representation Learning

🆔	Title	Repo	Paper
1571	Adversarial Learning of Intermediate Acoustic Feature for End-to-End Lightweight Text-to-Speech
2313	Adapter-based Extension of Multi-Speaker Text-To-Speech Model for New Speakers
2574	SALTTS: Leveraging Self-Supervised Speech Representations for improved Text-to-Speech Synthesis	➖
2326	UnitSpeech: Speaker-Adaptive Speech Synthesis with Untranscribed Data
677	LightVoc: an Upsampling-Free GAN Vocoder based on Conformer and Inverse Short-time Fourier Transform
1095	ChatGPT-EDSS: Empathetic Dialogue Speech Synthesis Trained from ChatGPT-derived Context Word Embeddings

Speech Perception, Production, and Acquisition

🆔	Title	Repo	Paper
1330	Human Transcription Quality Improvement
1604	The Effect of Masking Noise on Listeners' Spectral Tilt Preferences	➖
1967	The Effect of Whistled Vowels on Whistled Word Categorization for Naive Listeners	➖
1481	Automatic Deep Neural Network-based Segmental Pronunciation Error Detection of L2 English Speech (L1 Bengali)	➖
1662	The Effect of Stress on Mandarin Tonal Perception in Continuous Speech for Spanish-Speaking Learners	➖
1918	Combining Acoustic and Aerodynamic Data Collection: A Perceptual Evaluation of Acoustic Distortions	➖
953	Estimating Virtual Targets for Lingual Stop Consonants using General Tau Theory	➖
1931	Using Random Forests to Classify Language as a Function of Syllable Timing in Two Groups: Children with Cochlear Implants and with Normal Hearing	➖
2256	An Improved End-to-End Audio-Visual Speech Recognition Model	➖
1954	What Influences the Foreign Accent Strength? Phonological and Grammatical Errors in the Perception of Accentedness
2077	Investigating the Perception Production Link through Perceptual Adaptation and Phonetic Convergence	➖
1385	Emotion Prompting for Speech Emotion Recognition	➖
1196	Speech-in-Speech Recognition is Modulated by Familiarity to Dialect	➖
673	BASEN: Time-Domain Brain-Assisted Speech Enhancement Network with Convolutional Cross Attention in Multi-Talker Conditions
2046	Are Retroflex-to-Dental Sibilant Substitutions in Polish Children's Speech an Example of a Covert Contrast? A Preliminary Acoustic Study	➖
1123	First Language Effects on Second Language Perception: Evidence from English Low-Vowel Nasal Sequences Perceived by L1 Mandarin Chinese Listeners	➖
2247	Motor Control Similarity between Speakers Saying "a Souk" using Inverse Atlas Tongue Modeling	➖
910	Assessing Phrase Break of ESL Speech with Pre-trained Language Models and Large Language Models	➖
317	A Relationship between Vocal Fold Vibration and Droplet Production	➖
803	Audio, Visual and Audiovisual Intelligibility of Vowels Produced in Noise	➖
172	Optimal Control of Speech with Context-Dependent Articulatory Targets	➖
593	Computational Modeling of Auditory Brainstem Responses Derived from Modified Speech	➖
1732	Leveraging Label Information for Multimodal Emotion Recognition
1465	Improving End-to-End Modeling for Mandarin-English Code-Switching using Lightweight Switch-Routing Mixture-of-Experts	➖
1803	Frequency Patterns of Individual Speaker Characteristics at Higher and Lower Spectral Ranges	➖
1818	Adaptation to Predictive Prosodic cues in Non-Native Standard Dialect	➖
1007	Head Movements in Two- and Four-Person Inter-Active Conversational Tasks in Noisy and Moderately Reverberant Conditions	➖
334	Second Language Identification of Vietnamese Tones by Native Mandarin Learners	➖
203	Nasal Vowel Production and Grammatical Processing in French-Speaking Children with Cochlear Implants and Normal-Hearing Peers	➖
412	Emotion Classification with EEG Responses Evoked by Emotional Prosody of Speech	➖
145	L2-Mandarin Regional Accent Variability During Mandarin Tone-Word Training Facilitates English listeners' Subsequent tone Categorizations	➖
1680	HumanDiffusion: Diffusion Model using Perceptual Gradients	➖
2087	Queer Events, Relationships, and Sports: Does Topic Influence Speakers' Acoustic Expression of Sexual Orientation?	➖

Acoustic Model Adaptation for ASR

🆔	Title	Repo	Paper
583	Factorised Speaker-Environment Adaptive Training of Conformer Speech Recognition Systems	➖
1349	Text Only Domain Adaptation with Phoneme Guided Data Splicing for End-to-End Speech Recognition
327	Cross-Lingual Cross-Age Adaptation for Low-Resource Elderly Speech Emotion Recognition
2215	Modular Domain Adaptation for Conformer-based Streaming ASR	➖
2192	Don't Stop Self-Supervision: Accent Adaptation of Speech Representations via Residual Adapters	➖
1282	SGEM: Test-Time Adaptation for Automatic Speech Recognition via Sequential-Level Generalized Entropy Minimization

Speech Synthesis: Expressivity

🆔	Title	Repo	Paper
858	Controllable Generation of Artificial Speaker Embeddings through Discovery of Principal Directions
2242	Dual Audio Encoders based Mandarin Prosodic Boundary Prediction by using Multi-Granularity Prosodic Representations	➖
645	NoreSpeech: Knowledge Distillation based Conditional Diffusion Model for Noise-robust Expressive TTS
782	MaskedSpeech: Context-aware Speech Synthesis with Masking Strategy
2469	Narrator or Character: Voice Modulation in an Expressive Multi-Speaker TTS
843	CASEIN: Cascading Explicit and Implicit Control for Fine-grained Emotion Intensity Regulation	➖
1405	Semi-Supervised Learning for Continuous Emotional Intensity Controllable Speech Synthesis with Disentangled Representations
1905	Expresso: A Benchmark and Analysis of Discrete Expressive Speech Resynthesis
1460	ComedicSpeech: Adaptive Text to Speech For Stand-up Comedy in Low-Resource Scenario
1552	Neural Speech Synthesis with Enriched Phrase Boundaries
437	Cross-Lingual Prosody Transfer for Expressive Machine Dubbing	➖
2178	Synthesis after a couple PINTs: Investigating the Role of Pause-Internal Phonetic Particles in Speech Synthesis and Perception
433	Accentor: An Explicit Lexical Stress Model for TTS Systems	➖
1032	A Neural TTS System with Parallel Prosody Transfer from Unseen Speakers
715	Diverse and Expressive Speech Prosody Prediction with Denoising Diffusion Probabilistic Model
289	Prosody Modeling with 3D Visual Information for Expressive Video Dubbing	➖
1528	LightClone: Speaker-Guided Parallel Subnet Selection for Few-Shot Voice Cloning
1671	EE-TTS: Emphatic Expressive TTS with Linguistic Information
1673	Stochastic Pitch Prediction Improves the Diversity and Naturalness of Speech in Glow-TTS	➖
122	ContextSpeech: Expressive and Efficient Text-to-Speech for Paragraph Reading
1779	PromptStyle: Controllable Style Transfer for Text-to-Speech with Natural Language Descriptions
1639	Creating Personalized Synthetic Voices from Post-Glossectomy Speech with Guided Diffusion Models
2453	A Generative Framework for Conversational Laughter: Its "Language Model" and Laughter Sound Synthesis	➖
1754	Towards Spontaneous Style Modeling with Semi-Supervised Pre-training for Conversational Text-to-Speech Synthesis
2072	Beyond Style: Synthesizing Speech with Pragmatic Functions
965	eCat: An End-to-End Model for Multi-Speaker TTS & Many-to-Many Fine-Grained Prosody Transfer	➖

Multi-modal Systems

🆔	Title	Repo	Paper
1146	BeAts: Bengali Speech Acts Recognition using Multimodal Attention Fusion
370	Improving the Gap in Visual Speech Recognition Between Normal and Silent Speech based on Metric Learning	➖
989	Whistle-to-Text: Automatic Recognition of the Silbo Gomero Whistled Language	➖
663	A Novel Interpretable and Generalizable Re-Synchronization Model for Cued Speech based on a Multi-Cuer Corpus
668	Visually Grounded Few-Shot Word Acquisition with Fewer Shots	➖
183	JAMFN: Joint Attention Multi-Scale Fusion Network for Depression Detection	➖

Question Answering from Speech

🆔	Title	Repo	Paper
1485	Prompt Guided Copy Mechanism for Conversational Question Answering	➖
1240	Composing Spoken Hints for Follow-on Question Suggestion in Voice Assistants	➖
1391	On Monotonic Aggregation for Open-Domain QA
2240	Question-Context Alignment and Answer-Context Dependencies for Effective Answer Sentence Selection	➖
1606	Multi-Scale Attention for Audio Question Answering
539	Enhancing Visual Question Answering via Deconstructing Questions and Explicating Answers	➖

Multi-talker Methods in Speech Processing

🆔	Title	Repo	Paper
1749	SEF-Net: Speaker Embedding Free Target Spekaer Extraction Network	➖
1530	Overlap aware Continuous Speech Separation without Permutation Invariant Training Linfeng	➖
1952	Cascaded Encoders for Fine-Tuning ASR Models on Overlapped Speech	➖
2069	TokenSplit: using Discrete Speech Representations for Direct, Refined, and Transcript-Conditioned Speech Separation and Recognition	➖
1422	Unified Modeling of Multi-Talker Overlapped Speech Recognition and Diarization with a Sidecar Separator	➖
2098	Time-Domain Transformer-based Audiovisual Speaker Separation	➖
628	Multi-Stream Extension of Variational Bayesian HMM Clustering (MS-VBx) for Combined End-to-End and Vector Clustering-based Diarization	➖
1502	Unsupervised Adaptation with Quality-aware Masking to Improve Target-Speaker Voice Activity Detection for Speaker Diarization	➖
1521	BA-SOT: Boundary-aware Serialized Output Training for Multi-Talker ASR	➖
1172	Improving Label Assignments Learning by Dynamic Sample Dropout Combined with Layer-wise Optimization in Speech Separation	➖
975	Joint Compensation of Multi-Talker Noise and Reverberation for Speech Enhancement with Cochlear Implants using One or More Microphones	➖
494	Speaker Diarization for ASR Output with T-vectors: A Sequence Classification Approach	➖
42	GPU-accelerated Guided Source Separation for Meeting Transcription
1280	Weakly-Supervised Speech Pre-training: A Case Study on Target Speech Recognition
2076	Directional Speech Recognition for Speaker Disambiguation and Cross-talk Suppression	➖
1815	Mixture Encoder for Joint Speech Separation and Recognition	➖

Sociophonetics

🆔	Title	Repo	Paper
206	Aberystwyth English Pre-Aspiration in Apparent Time	➖
1154	Speech Entrainment in Chinese Story-Style Talk Shows: The Interaction Between Gender and Role	➖
1414	Sociodemographic and Attitudinal Effects on Dialect Speakers' Articulation of the Standard Language: Evidence from German-Speaking Switzerland	➖
1704	Vowel Normalisation in Latent Space for Sociolinguistics	➖

Speaker and Language Diarization

🆔	Title	Repo	Paper
1228	Attention-based Encoder-Decoder Network for End-to-End Neural Speaker Diarization with Target Speaker Attractor	➖
1447	Robust Self Supervised Speech Embeddings for Child-Adult Classification in Interactions involving Children with Autism	➖
2367	The DISPLACE Challenge 2023 - DIarization of SPeaker and LAnguage in Conversational Environments
1982	Lexical Speaker Error Correction: Leveraging Language Models for Speaker Diarization Error Correction	➖
1839	The SpeeD-ZevoTech Submission at DISPLACE 2023	➖
656	End-to-End Neural Speaker Diarization with Absolute Speaker Loss	➖

Anti-Spoofing for Speaker Verification

🆔	Title	Repo	Paper
1402	Towards Single Integrated Spoofing-aware Speaker Verification Embeddings
1352	Pseudo-Siamese Network based Timbre-Reserved Black-Box Adversarial Attack in Speaker Identification	➖
2335	Betray Oneself: A Novel Audio DeepFake Detection Model via Mono-to-Stereo Conversion
1166	Robust Audio Anti-Spoofing Countermeasure with Joint Training of Front-end and Back-end and Models	➖
1537	Improved DeepFake Detection using Whisper Features
371	DoubleDeceiver: Deceiving the Speaker Verification System Protected by Spoofing Countermeasures	➖

Speech Coding: Intelligibility

🆔	Title	Repo	Paper
2209	On Training a Neural Residual Acoustic echo Suppressor for Improved ASR	➖
1429	Extending DNN-based Multiplicative Masking to Deep Subband Filtering for Improved Dereverberation
378	UnSE: Unsupervised Speech Enhancement using Optimal Transport
1130	MC-SpEx: Towards Effective Speaker Extraction with Multi-Scale Interfusion and Conditional Speaker Modulation
2177	Causal Signal-based DCCRN with Overlapped-Frame Prediction for Online Speech Enhancement	➖
1511	Gesper: A Restoration-Enhancement Framework for General Speech Reconstruction	➖

New Computational Strategies for ASR Training and Inference

🆔	Title	Repo	Paper
2183	A Metric-Driven Approach to Conformer Layer Pruning for Efficient ASR Inference	➖
1981	Distillation Strategies for Discriminative Speech Recognition Rescoring	➖
969	Another Point of View on Visual Speech Recognition	➖
1062	RASR2: The RWTH ASR Toolkit for Generic Sequence-to-Sequence Speech Recognition
486	Streaming Speech-to-Confusion Network Speech Recognition	➖
809	Accurate and Structured Pruning for Efficient Automatic Speech Recognition	➖

MERLIon CCS Challenge: Multilingual Everyday Recordings - Language Identification On Code-Switched Child-Directed Speech

🆔	Title	Repo	Paper
1446	MERLIon CCS Challenge: A English-Mandarin Code-Switching Child-directed Speech Corpus for Language Identification and Diarization
1335	Spoken Language Identification System for English-Mandarin Code-Switching Child-Directed Speech
1707	Investigating Model Performance in Language Identification: beyond Simple Error Statistics	➖
2533	Improving Wav2vec2-based Spoken Language Identification by Learning Phonological Features	➖
2047	Language Identification Networks for Multilingual Everyday Recordings	➖

Health-Related Speech Analysis

🆔	Title	Repo	Paper
2038	Classification of Vocal Intensity Category from Speech using the Wav2vec2 and Whisper Embeddings	➖
1668	The Effect of Clinical Intervention on the Speech of Individuals with PTSD: Features and Recognition Performances	➖
470	Analysis and Automatic Prediction of Exertion from Speech: Contrasting Objective and Subjective Measures Collected while Running	➖
894	The Androids Corpus: A New Publicly Available Benchmark for Speech based Depression Detection
658	Comparing Hand-Crafted Features to Spectrograms for Autism Severity Estimation	➖
839	Acoustic Characteristics of Depression in Older Adults' Speech: the Role of Covariates	➖

Automatic Audio Classification and Audio Captioning

🆔	Title	Repo	Paper
943	Dual Transformer Decoder based Features Fusion Network for Automated Audio Captioning	➖
1564	Adapting a ConvNeXt Model to Audio Classification on AudioSet
1610	Few-Shot Class-Incremental Audio Classification using Stochastic Classifier
1614	Enhance Temporal Relations in Audio Captioning with Sound Event Detection	➖

Speech Synthesis

🆔	Title	Repo	Paper
407	Epoch-based Spectrum Estimation for Speech
1996	OverFlow: Putting Flows on Top of Neural Transducers for Better TTS
1568	AdapterMix: Exploring the Efficacy of Mixture of Adapters for Low-Resource TTS Adaptation
506	Prior-Free Guided TTS: An Improved and Efficient Diffusion-based Text-Guided Speech Synthesis	➖
367	UnDiff: Unsupervised Voice Restoration with Unconditional Diffusion Model	➖
1301	Pruning Self-Attention for Zero-Shot Multi-Speaker Text-to-Speech
1151	Interpretable Style Transfer for Text-to-Speech with ControlVAE and Diffusion Bridge
879	Towards Robust FastSpeech 2 by Modelling Residual Multimodality
1137	Real Time Spectrogram Inversion on Mobile Phone
58	Automatic Tuning of Loss Trade-offs without Hyper-Parameter Search in End-to-End Zero-Shot Speech Synthesis
2056	A Low-Resource Pipeline for Text-to-Speech from Found Data With Application to Scottish Gaelic
2173	Self-Supervised Solution to the Control Problem of Articulatory Synthesis
1128	Hierarchical Timbre-Cadence Speaker Encoder for Zero-Shot Speech Synthesis
754	ZET-Speech: Zero-Shot adaptive Emotion-Controllable Text-to-Speech Synthesis with Diffusion and Style-based Models
690	Improving WaveRNN with Heuristic Dynamic Blending for Fast and High-Quality GPU Vocoding
194	Intelligible Lip-to-Speech Synthesis with Speech Units
1212	Parameter-Efficient Learning for Text-to-Speech Accent Adaptation
820	Controlling Formant Frequencies with Neural Text-to-Speech for the Manipulation of Perceived Speaker Age
2379	FastFit: Towards Real-Time Iterative Neural Vocoder by Replacing U-Net Encoder with Multiple STFTs
1726	iSTFTNet2: Faster and more Lightweight iSTFT-based Neural Vocoder using 1D-2D CNN
534	VITS2: Improving Quality and Efficiency of Single Stage Text to Speech with Adversarial Learning and Architecture Design
1175	Controlling Multi-Class Human Vocalization Generation via a Simple Segment-based Labeling Scheme	➖

Speech Synthesis: Controllability and Adaptation

🆔	Title	Repo	Paper
1608	HierVST: Hierarchical Adaptive Zero-Shot Voice Style Transfer
391	VISinger2: High-Fidelity End-to-End Singing Voice Synthesis Enhanced by Digital Signal Processing Synthesizer
700	EdenTTS: A Simple and Efficient Parallel Text-to-Speech Architecture with Collaborative Duration-Alignment Learning
368	Generalizable Zero-Shot Speaker Adaptive Speech Synthesis with Disentangled Representations
1020	Speech Inpainting: Context-based Speech Synthesis Guided by Video
2243	STEN-TTS: Improving Zero-Shot Cross-Lingual Transfer for Multi-Lingual TTS with Style-Enhanced Normalization Diffusion Framework	➖

Search Methods and Decoding Algorithms for ASR

🆔	Title	Repo	Paper
933	Average Token Delay: A Latency Metric for Simultaneous Translation	➖
1450	Automatic Speech Recognition Transformer with Global Contextual Information Decoder	➖
1333	Time-Synchronous One-Pass Beam Search for Parallel Online and Offline Transducers with Dynamic Block Training	➖
2065	Prefix Search Decoding for RNN Transducers	➖
78	WhisperX: Time-Accurate Speech Transcription of Long-Form Audio
2449	Implementing Contextual Biasing in GPU Decoder for Online ASR

Speech Signal Analysis

🆔	Title	Repo	Paper
2487	MF-PAM: Accurate Pitch Estimation through Periodicity Analysis and Multi-Level Feature Fusion
2211	Enhancing Speech Articulation Analysis using A Geometric Transformation of the X-ray Microbeam Dataset	➖
1729	Matching Acoustic and Perceptual Measures of Phonation Assessment in Disordered Speech - A Case Study	➖
283	Improved Contextualized Speech Representations for Tonal Analysis	➖
1738	A Study on the Importance of Formant Transitions for Stop-Consonant Classification in VCV Sequence	➖
2229	FusedF0: Improving DNN-based F0 Estimation by Fusion of Summary-Correlograms and Raw Waveform Representations of Speech Signals	➖

Connecting Speech-science and Speech-technology for Children's Speech

🆔	Title	Repo	Paper
928	Using Commercial ASR Solutions to Assess Reading Skills in Children: A Case Report	➖
907	Uncertainty Estimation for Connectionist Temporal Classification based Automatic Speech Recognition	➖
2185	Speech Breathing Behavior During Pauses in Children	➖
926	Exploiting Diversity of Automatic Transcripts from Distinct Speech Recognition Techniques for Children's Speech	➖
1924	Acoustic-to-Articulatory Speech Inversion Features for Mispronunciation Detection of /r/ in Child Speech Sound Disorders	➖
978	BabySLM: Language-Acquisition-Friendly Benchmark of Self-Supervised Spoken Language Models
702	Data Augmentation for Children ASR and Child-adult Speaker Classification using Voice Conversion Methods
2236	Developmental Articulatory and Acoustic Features for Six to Ten Year Old Children	➖
2251	Automatically Predicting Perceived Conversation Quality in a Pediatric Sample Enriched for Autism	➖
1257	An Equitable Framework for Automatically Assessing Children's Oral Narrative Language Abilities	➖
743	An Analysis of Goodness of Pronunciation for Child Speech
1569	Measuring Language Development from Child-centered Recordings
2057	Speaking Clearly, Understanding Better: Predicting the L2 Narrative Comprehension of Chinese Bilingual Kindergarten Children based on Speech Intelligibility using a Machine Learning Approach	➖
312	Classifying Rhoticity of /r/ in Speech Sound Disorder using Age-and-Sex Normalized Formants	➖
1273	Understanding Spoken Language Development of Children with ASD using Pre-trained Speech Embeddings	➖
2099	Measuring Phonological Precision in Children with Cleft Lip and Palate
937	A Study on Using Duration and Formant Features in Automatic Detection of Speech Sound Disorder in Children	➖
1873	Influence of Utterance and Speaker Characteristics on the Classification of Children with Cleft Lip and Palate
1882	Prospective Validation of Motor-based Intervention with Automated Mispronunciation Detection of Rhotics in Residual Speech Sound Disorders	➖

Dialog Management

🆔	Title	Repo	Paper
2238	Parameter-Efficient Low-Resource Dialogue State Tracking by Prompt Tuning	➖
2525	An Autoregressive Conversational Dynamics Model for Dialogue Systems	➖
1983	Style-Transfer based Speech and Audio-Visual Scene Understanding for Robot Action Sequence Acquisition from Videos	➖
1037	Speech aware Dialog System Technology Challenge (DSTC11)
1397	Knowledge-Retrieval Task-Oriented Dialog Systems with Semi-Supervision
2513	Tracking Must Go On: Dialogue State Tracking with Verified Self-Training	➖

Speech Activity Detection and Modeling

🆔	Title	Repo	Paper
558	GL-SSD: Global and Local Speech Style Disentanglement by Vector Quantization for Robust Sentence Boundary Detection in Speech Stream	➖
598	Semantic VAD: Low-Latency Voice Activity Detection for Speech Interaction	➖
2466	Dynamic Encoder RNN for Online Voice Activity Detection in Adverse Noise Conditions	➖
996	Point to the Hidden: Exposing Speech Audio Splicing via Signal Pointer Nets	➖
716	Real-Time Causal Spectro-Temporal Voice Activity Detection based on Convolutional Encoding and Residual Decoding	➖
2413	SVVAD: Personal Voice Activity Detection for Speaker Verification	➖

Multilingual Models for ASR

🆔	Title	Repo	Paper
1613	Learning Cross-Lingual Mappings for Data Augmentation to Improve Low-Resource Speech Recognition	➖
2122	AfriNames: Most ASR models "butcher" African Names
2528	Towards Dialect-Inclusive Recognition in a Low-Resource Language: are Balanced Corpora the Answer?	➖
2588	Svarah: Evaluating English ASR Systems on Indian Accents
1044	N-Shot Benchmarking of Whisper on Diverse Arabic Speech Recognition	➖
1014	The MALACH Corpus: Results with End-to-End Architectures and Pretraining	➖

Speech Enhancement and Bandwidth Expansion

🆔	Title	Repo	Paper
232	Unsupervised Speech Enhancement with Deep Dynamical Generative Speech and Noise Models	➖
857	Noise-Robust Bandwidth Expansion for 8K Speech Recordings	➖
113	mdctGAN: Taming Transformer-based GAN for Speech Super-Resolution with Modified DCT Spectra
625	Zoneformer: On-Device Neural Beamformer for In-Car Multi-Zone Speech Separation, Enhancement and echo Cancellation
634	Low-Complexity Broadband Beampattern Synthesis using Array Response Control	➖
904	A GAN Speech Inpainting Model for Audio Editing Software

Articulation

🆔	Title	Repo	Paper
2316	Deep Speech Synthesis from MRI-based Articulatory Representations
562	Learning to Compute the Articulatory Representations of Speech with the MIRRORNET
804	Generating High-Resolution 3D Real-Time MRI of the Vocal Tract
1593	Exploring a Classification Approach using Quantised Articulatory Movements for Acoustic to Articulatory Inversion	➖

Neural Processing of Speech and Language: Encoding and Decoding the Diverse Auditory Brain

🆔	Title	Repo	Paper
633	Coherence Estimation Tracks Auditory Attention in Listeners with Hearing Impairment	➖
2378	Enhancing the EEG Speech Match Mismatch Tasks with Word Boundaries
1347	Similar Hierarchical Representation of Speech and Other Complex Sounds in the Brain and Deep Residual Networks: an MEG Study	➖
121	Speech Taskonomy: Which Speech Tasks are the most Predictive of fMRI Brain Activity?	➖
282	MEG Encoding using Word Context Semantics in Listening Stories	➖
1949	Investigating the Cortical Tracking of Speech and Music with Sung Speech	➖
414	Exploring Auditory Attention Decoding using Speaker Features	➖
1776	Effects of Spectral Degradation on the Cortical Tracking of the Speech Envelope	➖
964	Effects of Spectral and Temporal Modulation Degradation on Intelligibility and Cortical Tracking of Speech Signals	➖

Perception of Paralinguistics

🆔	Title	Repo	Paper
2061	Transfer Learning for Personality Perception via Speech Emotion Recognition	➖
1131	A Stimulus-Organism-Response Model of Willingness to Buy from Advertising Speech using Voice Quality
1835	Voice Passing: A Non-Binary Voice Gender Prediction System for evaluating Transgender	➖
1139	Influence of Personal Traits on Impressions of One's Own Voice	➖
887	Pardon my Disfluency: The Impact of Disfluency Effects on the Perception of Speaker Competence and Confidence	➖
711	Cross-Linguistic Emotion Perception in Human and TTS Voices

Technologies for Child Speech Processing

🆔	Title	Repo	Paper
1302	Joint Learning Feature and Model Adaptation for Unsupervised Acoustic Modelling of Child Speech	➖
1681	Automatic Assessment of Oral Reading Accuracy for Reading Diagnostics
2084	An ASR-enabled Reading Tutor: Investigating Feedback to Optimize Interaction for Learning to Read	➖
935	Adaptation of Whisper Models to Child Speech Recognition

Speech Synthesis: Multilinguality; Evaluation

🆔	Title	Repo	Paper
2064	Automatic Evaluation of Turn-Taking Cues in Conversational Speech Synthesis
441	Expressive Machine Dubbing through Phrase-Level Cross-Lingual Prosody Transfer	➖
1691	Robust Feature Decoupling in Voice Conversion by using Locality-based Instance Normalization
612	Zero-Shot Accent Conversion using Pseudo Siamese Disentanglement Network	➖
2148	The Effects of Input Type and Pronunciation Dictionary Usage in Transfer Learning for Low-Resource Text-to-Speech
1727	GenerTTS: Pronunciation Disentanglement for Timbre and Style Generalization in Cross-Lingual Text-to-Speech
1285	Analysis of Mean Opinion Scores in Subjective Evaluation of Synthetic Speech based on Tail Probabilities
1584	LibriTTS-R: A Restored Multi-Speaker Text-to-Speech Corpus
1067	UniFLG: Unified Facial Landmark Generator from Text or Speech
444	XPhoneBERT: A Pre-trained Multilingual Model for Phoneme Representations for Text-to-Speech
2224	ClArTTS: An Open-Source Classical Arabic Text-to-Speech Corpus
154	Diffusion-based Accent Modelling in Speech Synthesis	➖
249	Multilingual Text-to-Speech Synthesis for Turkic Languages using Transliteration
553	CVTE-Poly: A New Benchmark for Chinese Polyphone Disambiguation
709	Improve Bilingual TTS using Language and Phonology Embedding with Embedding Strength Modulator
2179	High-Quality Automatic Voice Over with Accurate Alignment: Supervision through Self-Supervised Discrete Speech Units
1097	PronScribe: Highly Accurate Multimodal Phonemic Transcription From Speech and Text	➖
2158	Resource-Efficient Fine-Tuning Strategies for Automatic MOS Prediction in Text-to-Speech for Low-Resource Languages
416	Why We Should Report the Details in Subjective Evaluation of TTS More Rigorously
1622	Speaker-Independent Neural Formant Synthesis
1098	CALLS: Japanese Empathetic Dialogue Speech Corpus of Complaint Handling and Attentive Listening in Customer Center
430	SASPEECH: A Hebrew Single Speaker Dataset for Text to Speech and Voice Conversion

Show and Tell: Health Applications and Emotion Recognition

🆔	Title	Repo	Paper
2618	A Personalised Speech Communication Application for Dysarthric Speakers	➖
2624	Video Multimodal Emotion Recognition System for Real World Applications	➖
2626	Promoting Mental Self-Disclosure in a Spoken Dialogue System	➖
2632	"Select Language, Modality or Put on a Mask!" Experiments with Multimodal Emotion Recognition	➖
2635	My Vowels Matter: Formant Automation Tools for Diverse Child Speech	➖
2636	NEMA: An Ecologically Valid Tool for Assessing Hearing Devices, Advanced Algorithms, and Communication in Diverse Listening Environments	➖
2644	When Words Speak Just as Loudly as Actions: Virtual Agent based Remote Health Assessment Integrating What Patients Say with What They Do	➖
2648	Stuttering Detection Application	➖
2649	Providing Interpretable Insights for Neurological Speech and Cognitive Disorders from Interactive Serious Games	➖
2651	Automated Neural Nursing Assistant (ANNA): An Over-the-Phone System for Cognitive Monitoring	➖
2656	5G-IoT Cloud based Demonstration of Real-Time Audio-Visual Speech Enhancement for Multimodal Hearing-aids
2671	Towards Two-Point Neuron-Inspired Energy-Efficient Multimodal Open Master Hearing aid	➖

Show and Tell: Speech Tools, Speech Enhancement, Speech Synthesis

🆔	Title	Repo	Paper
2614	DeepFilterNet: Perceptually Motivated Real-Time Speech Enhancement
2615	Nkululeko: Machine Learning Experiments on Speaker Characteristics without Programming
2625	Sp1NY: A Quick and Flexible Python Speech Visualization Tool	➖
2629	Intonation Control for Neural Text-to-Speech Synthesis with Polynomial Models of F0	➖
2634	So-to-Speak: an Exploratory Platform for Investigating the Interplay between Style and Prosody in TTS
2638	Comparing /b/ and /d/ with a Single Physical Model of the Human Vocal Tract to Visualize Droplets Produced while Speaking	➖
2640	Show & Tell: Voice Activity Projection and Turn-taking
2652	Real-Time Detection of Soft Voice for Speech Enhancement	➖
2655	Data Augmentation for Diverse Voice Conversion in Noisy Environments	➖
2667	Application for Real-Time Audio-Visual Speech Enhancement	➖

Show and Tell: Language Learning and Educational Resources

🆔	Title	Repo	Paper
2623	A Unified Framework to Improve Learners' Skills of Perception and Production based on Speech Shadowing and Overlapping	➖
2633	Speak & Improve: L2 English Speaking Practice Tool	➖
2641	Measuring Prosody in Child Speech using SoapBox Fluency API	➖
2650	Teaching Non-native Sound Contrasts using Visual Biofeedback	➖
2654	Large-Scale Automatic Audiobook Creation	➖
2658	QVoice: Arabic Speech Pronunciation Learning Application	➖
2659	Asking Questions: an Innovative Way to Interact with Oral History Archives	➖
2660	DisfluencyFixer: A Tool to Enhance Language Learning through Speech to Speech Disfluency Correction
2661	Technology Pipeline for Large Scale Cross-Lingual Dubbing of Lecture Videos into Multiple Indian Languages	➖
2668	MyVoice: Arabic Speech Resource Collaboration Platform	➖
2669	Personal Primer Prototype 1: Invitation to Make Your Own Embooked Speech-based Educational Artifact

Show and Tell: Media and Commercial Applications

🆔	Title	Repo	Paper
2621	Let's Give a Voice to Conversational Agents in Virtual Reality
2622	FOOCTTS: Generating Arabic Speech with Acoustic Environment for Football Commentator	➖
2637	Video Summarization Leveraging Multimodal Information for Presentations	➖
2645	What Questions are My Customers Asking?: Towards Actionable Insights from Customer Questions in Contact Center Calls	➖
2646	COnVoy: A Contact Center Operated Pipeline for Voice of Customer Discovery	➖
2653	NeMo Forced Aligner and its Application to Word Alignment for Subtitle Generation	➖
2662	CauSE: Causal Search Engine for Understanding Contact-Center Conversations	➖
2663	Tailored Real-Time Call Summarization System for Contact Centers	➖
2647	Federated Learning Toolkit with Voice-based User Verification Demo	➖
2657	Learning when to Speak: Latency and Quality Trade-offs for Simultaneous Speech-to-Speech Translation with Offline Models
2628	Fast Enrollable Streaming Keyword Spotting System: Training and Inference using a Web Browser	➖
2665	Cross-Lingual/Cross-Channel Intent Detection in Contact-Center Conversations	➖

---

Key Terms

---

Star History