{"total":275,"rows":[{"id":"2202.03555","title":"data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language","created":"2022-02-07","cited_by_count":727,"area":null},{"id":"2209.03143","title":"AudioLM: a Language Modeling Approach to Audio Generation","created":"2022-09-07","cited_by_count":616,"area":null},{"id":"2205.10643","title":"Self-Supervised Speech Representation Learning: A Review","created":"2022-05-21","cited_by_count":260,"area":null},{"id":"2211.03929","title":"Comparative layer-wise analysis of self-supervised speech models","created":"2022-11-08","cited_by_count":158,"area":null},{"id":"2110.01900","title":"DistilHuBERT: Speech Representation Learning by Layer-wise Distillation of Hidden-unit BERT","created":"2021-10-05","cited_by_count":144,"area":null},{"id":"2406.08619","title":"Self-Supervised Speech Representations are More Phonetic than Semantic","created":"2024-06-12","cited_by_count":71,"area":null},{"id":"2305.18975","title":"Voice Conversion With Just Nearest Neighbors","created":"2023-05-30","cited_by_count":68,"area":null},{"id":"2307.00162","title":"What Do Self-Supervised Speech Models Know About Words?","created":"2023-06-30","cited_by_count":64,"area":null},{"id":"2206.01685","title":"Toward a realistic model of speech processing in the brain with self-supervised learning","created":"2022-06-03","cited_by_count":63,"area":null},{"id":"2210.07185","title":"On the Utility of Self-supervised Models for Prosody-related Tasks","created":"2022-10-13","cited_by_count":42,"area":null},{"id":"2404.09385","title":"A Large-Scale Evaluation of Speech Foundation Models","created":"2024-04-15","cited_by_count":40,"area":null},{"id":"2203.15081","title":"Word Discovery in Visually Grounded, Self-Supervised Speech Models","created":"2022-03-28","cited_by_count":37,"area":null},{"id":"2205.14252","title":"Self-supervised models of audio effectively explain human cortical responses to speech","created":"2022-05-27","cited_by_count":37,"area":null},{"id":"2305.17651","title":"DPHuBERT: Joint Distillation and Pruning of Self-Supervised Speech Models","created":"2023-05-28","cited_by_count":36,"area":null},{"id":"2306.06232","title":"Probing self-supervised speech models for phonetic and phonemic information: a case study in aspiration","created":"2023-06-09","cited_by_count":36,"area":null},{"id":"2210.02595","title":"Exploration of A Self-Supervised Speech Model: A Study on Emotional Corpora","created":"2022-10-05","cited_by_count":31,"area":null},{"id":"2210.11723","title":"Evidence of Vocal Tract Articulation in Self-Supervised Learning of Speech","created":"2022-10-21","cited_by_count":31,"area":null},{"id":"2204.03863","title":"Automatic Pronunciation Assessment using Self-Supervised Speech Representation Learning","created":"2022-04-08","cited_by_count":29,"area":null},{"id":"2210.00705","title":"SpeechCLIP: Integrating Speech with Pre-Trained Vision and Language Model","created":"2022-10-03","cited_by_count":29,"area":null},{"id":"2210.06175","title":"Exploring Efficient-tuning Methods in Self-supervised Speech Models","created":"2022-10-10","cited_by_count":26,"area":null},{"id":"2203.12668","title":"Pseudo Label Is Better Than Human Label","created":"2022-03-22","cited_by_count":25,"area":null},{"id":"2403.16865","title":"Encoding of lexical tone in self-supervised models of spoken language","created":"2024-03-25","cited_by_count":23,"area":null},{"id":"2305.11072","title":"Self-supervised Fine-tuning for Improved Content Representations by Speaker-invariant Clustering","created":"2023-05-18","cited_by_count":22,"area":null},{"id":"2404.09173","title":"TransformerFAM: Feedback attention is working memory","created":"2024-04-14","cited_by_count":22,"area":null},{"id":"2110.15684","title":"Fusing ASR Outputs in Joint Training for Speech Emotion Recognition","created":"2021-10-29","cited_by_count":21,"area":null},{"id":"2210.16043","title":"Analyzing Acoustic Word Embeddings from Pre-trained Self-supervised Speech Models","created":"2022-10-28","cited_by_count":21,"area":null},{"id":"2305.12464","title":"Self-supervised Predictive Coding Models Encode Speaker and Phonetic Information in Orthogonal Subspaces","created":"2023-05-21","cited_by_count":20,"area":null},{"id":"2309.10787","title":"AV-SUPERB: A Multi-Task Evaluation Benchmark for Audio-Visual Representation Models","created":"2023-09-19","cited_by_count":19,"area":null},{"id":"2210.15386","title":"Opening the Black Box of wav2vec Feature Encoder","created":"2022-10-27","cited_by_count":18,"area":null},{"id":"2305.12263","title":"Self-supervised representations in speech-based depression detection","created":"2023-05-20","cited_by_count":18,"area":null},{"id":"2305.18957","title":"Wave to Syntax: Probing spoken language models for syntax","created":"2023-05-30","cited_by_count":18,"area":null},{"id":"2306.06524","title":"What Can an Accent Identifier Learn? Probing Phonetic and Prosodic Information in a Wav2vec2-based Accent Identification Model","created":"2023-06-10","cited_by_count":18,"area":null},{"id":"2309.05472","title":"LeBenchmark 2.0: a Standardized, Replicable and Enhanced Framework for Self-supervised Representations of French Speech","created":"2023-09-11","cited_by_count":18,"area":null},{"id":"2408.13678","title":"A layer-wise analysis of Mandarin and English suprasegmentals in SSL speech models","created":"2024-08-24","cited_by_count":18,"area":null},{"id":"2506.05140","title":"AudioLens: A Closer Look at Auditory Attribute Perception of Large Audio-Language Models","created":"2025-06-05","cited_by_count":18,"area":null},{"id":"2204.00540","title":"End-to-End Integration of Speech Recognition, Speech Enhancement, and Self-Supervised Learning Representation","created":"2022-04-01","cited_by_count":17,"area":null},{"id":"2308.14456","title":"Speech Self-Supervised Representations Benchmarking: a Case for Larger Probing Heads","created":"2023-08-28","cited_by_count":17,"area":null},{"id":"2406.10283","title":"Attentive Merging of Hidden Embeddings from Pre-trained Speech Model for Anti-spoofing Detection","created":"2024-06-12","cited_by_count":17,"area":null},{"id":"2211.09944","title":"MelHuBERT: A simplified HuBERT on Mel spectrograms","created":"2022-11-17","cited_by_count":16,"area":null},{"id":"2310.10788","title":"Self-Supervised Models of Speech Infer Universal Articulatory Kinematics","created":"2023-10-16","cited_by_count":16,"area":null},{"id":"2504.07053","title":"TASTE: Text-Aligned Speech Tokenization and Embedding for Spoken Language Modeling","created":"2025-04-09","cited_by_count":16,"area":null},{"id":"2204.01397","title":"A Study of Gender Impact in Self-supervised Models for Speech-to-Text Systems","created":"2022-04-04","cited_by_count":15,"area":null},{"id":"2207.00952","title":"M-Adapter: Modality Adaptation for End-to-End Speech-to-Text Translation","created":"2022-07-03","cited_by_count":15,"area":null},{"id":"2303.06740","title":"Fine-tuning Strategies for Faster Inference using Speech Self-Supervised Models: A Comparative Study","created":"2023-03-12","cited_by_count":15,"area":null},{"id":"2308.12370","title":"AdVerb: Visually Guided Audio Dereverberation","created":"2023-08-23","cited_by_count":15,"area":null},{"id":"2502.07029","title":"Leveraging Allophony in Self-Supervised Speech Models for Atypical Pronunciation Assessment","created":"2025-02-10","cited_by_count":15,"area":null},{"id":"2406.09200","title":"Orthogonality and isotropy of speaker and phonetic information in self-supervised speech representations","created":"2024-06-13","cited_by_count":14,"area":null},{"id":"2204.00400","title":"Probing Speech Emotion Recognition Transformers for Linguistic Knowledge","created":"2022-04-01","cited_by_count":13,"area":null},{"id":"2210.10041","title":"Hidden State Variability of Pretrained Language Models Can Guide Computation Reduction for Transfer Learning","created":"2022-10-18","cited_by_count":13,"area":null},{"id":"2302.09908","title":"A Sidecar Separator Can Convert a Single-Talker Speech Recognition System to a Multi-Talker One","created":"2023-02-20","cited_by_count":13,"area":null},{"id":"2310.09925","title":"Homophone Disambiguation Reveals Patterns of Context Mixing in Speech Transformers","created":"2023-10-15","cited_by_count":13,"area":null},{"id":"2408.06227","title":"FLEURS-R: A Restored Multilingual Speech Corpus for Generation Tasks","created":"2024-08-12","cited_by_count":13,"area":null},{"id":"2112.07648","title":"On the Use of External Data for Spoken Named Entity Recognition","created":"2021-12-14","cited_by_count":12,"area":null},{"id":"2205.02694","title":"Quantifying Language Variation Acoustically with Few Resources","created":"2022-05-05","cited_by_count":12,"area":null},{"id":"2602.18899","title":"[b] = [d] - [t] + [p]: Self-supervised Speech Models Discover Phonological Vector Arithmetic","created":"2026-02-21","cited_by_count":12,"area":null},{"id":"2203.16965","title":"PADA: Pruning Assisted Domain Adaptation for Self-Supervised Speech Representations","created":"2022-03-31","cited_by_count":11,"area":null},{"id":"2204.02470","title":"Combining Spectral and Self-Supervised Features for Low Resource Speech Recognition and Translation","created":"2022-04-05","cited_by_count":11,"area":null},{"id":"2303.08019","title":"Leveraging Pretrained Representations with Task-related Keywords for Alzheimer's Disease Detection","created":"2023-03-14","cited_by_count":11,"area":null},{"id":"2305.17733","title":"Investigating Pre-trained Audio Encoders in the Low-Resource Condition","created":"2023-05-28","cited_by_count":11,"area":null},{"id":"2306.00561","title":"Masked Autoencoders with Multi-Window Local-Global Attention Are Better Audio Learners","created":"2023-06-01","cited_by_count":11,"area":null},{"id":"2312.10019","title":"Understanding Probe Behaviors through Variational Bounds of Mutual Information","created":"2023-12-15","cited_by_count":11,"area":null},{"id":"2407.09817","title":"Empowering Whisper as a Joint Multi-Talker and Target-Talker Speech Recognition System","created":"2024-07-13","cited_by_count":11,"area":null},{"id":"2606.01802","title":"MOSS-Audio Technical Report","created":"2026-06-01","cited_by_count":11,"area":null},{"id":"2206.09783","title":"Boosting Cross-Domain Speech Recognition with Self-Supervision","created":"2022-06-20","cited_by_count":10,"area":null},{"id":"2306.01015","title":"How to Estimate Model Transferability of Pre-Trained Speech Models?","created":"2023-06-01","cited_by_count":10,"area":null},{"id":"2406.09345","title":"DiscreteSLU: A Large Language Model with Self-Supervised Discrete Speech Units for Spoken Language Understanding","created":"2024-06-13","cited_by_count":10,"area":null},{"id":"2110.03504","title":"Mandarin-English Code-switching Speech Recognition with Self-supervised Speech Representation Models","created":"2021-10-07","cited_by_count":9,"area":null},{"id":"2306.07763","title":"NAVER LABS Europe's Multilingual Speech Translation Systems for the IWSLT 2023 Low-Resource Track","created":"2023-06-13","cited_by_count":9,"area":null},{"id":"2306.08374","title":"SpeechGLUE: How Well Can Self-Supervised Speech Models Capture Linguistic Knowledge?","created":"2023-06-14","cited_by_count":9,"area":null},{"id":"2401.05551","title":"Useful Blunders: Can Automated Speech Recognition Errors Improve Downstream Dementia Classification?","created":"2024-01-10","cited_by_count":9,"area":null},{"id":"2410.24177","title":"DC-Spin: A Speaker-invariant Speech Tokenizer for Spoken Language Models","created":"2024-10-31","cited_by_count":9,"area":null},{"id":"2402.02617","title":"Layer-Wise Analysis of Self-Supervised Acoustic Word Embeddings: A Study on Speech Emotion Recognition","created":"2024-02-04","cited_by_count":8,"area":null},{"id":"2407.18517","title":"SLIM: Style-Linguistics Mismatch Model for Generalized Audio Deepfake Detection","created":"2024-07-26","cited_by_count":8,"area":null},{"id":"2412.02006","title":"Unveiling Interpretability in Self-Supervised Speech Representations for Parkinson's Diagnosis","created":"2024-12-02","cited_by_count":8,"area":null},{"id":"2603.12642","title":"Self-Supervised Speech Models Encode Phonetic Context via Position-dependent Orthogonal Subspaces","created":"2026-03-13","cited_by_count":8,"area":null},{"id":"2110.04484","title":"Wav2vec-S: Semi-Supervised Pre-Training for Low-Resource ASR","created":"2021-10-09","cited_by_count":7,"area":null},{"id":"2205.03759","title":"Silence is Sweeter Than Speech: Self-Supervised Model Using Silence to Store Speaker Information","created":"2022-05-08","cited_by_count":7,"area":null},{"id":"2305.16263","title":"Unified Modeling of Multi-Talker Overlapped Speech Recognition and Diarization with a Sidecar Separator","created":"2023-05-25","cited_by_count":7,"area":null},{"id":"2406.16990","title":"AND: Audio Network Dissection for Interpreting Deep Acoustic Models","created":"2024-06-24","cited_by_count":7,"area":null},{"id":"2502.08866","title":"BrainWavLM: Fine-tuning Speech Representations with Brain Responses to Language","created":"2025-02-13","cited_by_count":7,"area":null},{"id":"2505.19103","title":"WHISTRESS: Enriching Transcriptions with Sentence Stress Detection","created":"2025-05-25","cited_by_count":7,"area":null},{"id":"2505.22765","title":"StressTest: Can YOUR Speech LM Handle the Stress?","created":"2025-05-28","cited_by_count":7,"area":null},{"id":"2506.18843","title":"USAD: Universal Speech and Audio Representation via Distillation","created":"2025-06-23","cited_by_count":7,"area":null},{"id":"2605.27772","title":"Do Audio LLMs Listen or Read? Analyzing and Mitigating Paralinguistic Failures with VoxParadox","created":"2026-05-26","cited_by_count":7,"area":null},{"id":"2205.01987","title":"ON-TRAC Consortium Systems for the IWSLT 2022 Dialect and Low-resource Speech Translation Tasks","created":"2022-05-04","cited_by_count":6,"area":null},{"id":"2211.05103","title":"Accidental Learners: Spoken Language Identification in Multilingual Self-Supervised Models","created":"2022-11-09","cited_by_count":6,"area":null},{"id":"2305.19184","title":"Leveraging Semantic Information for Efficient Self-Supervised Emotion Recognition with Audio-Textual Distilled Models","created":"2023-05-30","cited_by_count":6,"area":null},{"id":"2306.03014","title":"On the Behavior of Intrusive and Non-intrusive Speech Enhancement Metrics in Predictive and Generative Settings","created":"2023-06-05","cited_by_count":6,"area":null},{"id":"2309.02450","title":"Self-Supervised Video Transformers for Isolated Sign Language Recognition","created":"2023-09-02","cited_by_count":6,"area":null},{"id":"2502.05389","title":"The Role of Prosody in Spoken Question Answering","created":"2025-02-08","cited_by_count":6,"area":null},{"id":"2510.12851","title":"Silence is Golden: Mitigating Hallucinations in Large Audio-Language Models via Layer-Weighted Vector Steering","created":"2025-10-14","cited_by_count":6,"area":null},{"id":"2111.14842","title":"Do We Still Need Automatic Speech Recognition for Spoken Language Understanding?","created":"2021-11-29","cited_by_count":5,"area":null},{"id":"2204.01235","title":"An Analysis of Semantically-Aligned Speech-Text Embeddings","created":"2022-04-04","cited_by_count":5,"area":null},{"id":"2207.02262","title":"Ultra-Low-Bitrate Speech Coding with Pretrained Transformers","created":"2022-07-05","cited_by_count":5,"area":null},{"id":"2401.08833","title":"Revisiting Self-supervised Learning of Speech Representation from a Mutual Information Perspective","created":"2024-01-16","cited_by_count":5,"area":null},{"id":"2403.20184","title":"Exploring Pathological Speech Quality Assessment with ASR-Powered Wav2Vec2 in Data-Scarce Context","created":"2024-03-29","cited_by_count":5,"area":null},{"id":"2409.05910","title":"Property Neurons in Self-Supervised Speech Transformers","created":"2024-09-07","cited_by_count":5,"area":null},{"id":"2409.12634","title":"Exploring bat song syllable representations in self-supervised audio encoders","created":"2024-09-19","cited_by_count":5,"area":null},{"id":"2501.05966","title":"Towards Early Prediction of Self-Supervised Speech Model Performance","created":"2025-01-10","cited_by_count":5,"area":null},{"id":"2505.22487","title":"Effective Context in Neural Speech Models","created":"2025-05-28","cited_by_count":5,"area":null}],"next_cursor":"100"}