{"total":101,"rows":[{"id":"2105.01051","title":"SUPERB: Speech processing Universal PERformance Benchmark","created":"2021-05-03","cited_by_count":666,"area":null},{"id":"2102.01192","title":"Generative Spoken Language Modeling from Raw Audio","created":"2021-02-01","cited_by_count":340,"area":null},{"id":"2107.04734","title":"Layer-wise Analysis of a Self-supervised Speech Representation Model","created":"2021-07-10","cited_by_count":298,"area":null},{"id":"2205.10643","title":"Self-Supervised Speech Representation Learning: A Review","created":"2022-05-21","cited_by_count":260,"area":null},{"id":"2402.05755","title":"Spirit LM: Interleaved Spoken and Written Language Model","created":"2024-02-08","cited_by_count":126,"area":"mllm"},{"id":"2305.13009","title":"Textually Pretrained Speech Language Models","created":"2023-05-22","cited_by_count":101,"area":null},{"id":"2309.09510","title":"Dynamic-SUPERB: Towards A Dynamic, Collaborative, and Comprehensive Instruction-Tuning Benchmark for Speech","created":"2023-09-18","cited_by_count":101,"area":null},{"id":"2503.04721","title":"Full-Duplex-Bench: A Benchmark to Evaluate Full-duplex Spoken Dialogue Models on Turn-taking Capabilities","created":"2025-03-06","cited_by_count":100,"area":null},{"id":"2208.07998","title":"What Artificial Neural Networks Can Tell Us About Human Language Acquisition","created":"2022-08-17","cited_by_count":99,"area":null},{"id":"2308.05725","title":"EXPRESSO: A Benchmark and Analysis of Discrete Expressive Speech Resynthesis","created":"2023-08-10","cited_by_count":98,"area":null},{"id":"2410.03751","title":"Recent Advances in Speech Language Models: A Survey","created":"2024-10-01","cited_by_count":87,"area":null},{"id":"2203.06849","title":"SUPERB-SG: Enhanced Speech processing Universal PERformance Benchmark for Semantic and Generative Capabilities","created":"2022-03-14","cited_by_count":77,"area":null},{"id":"2309.07937","title":"Voxtlm: unified decoder-only models for consolidating speech recognition/synthesis and speech/text continuation tasks","created":"2023-09-14","cited_by_count":72,"area":null},{"id":"2409.15594","title":"Beyond Turn-Based Interfaces: Synchronous LLMs as Full-Duplex Dialogue Agents","created":"2024-09-23","cited_by_count":72,"area":"agents"},{"id":"2203.01205","title":"Audio Self-supervised Learning: A Survey","created":"2022-03-02","cited_by_count":65,"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":"2104.14700","title":"The Zero Resource Speech Challenge 2021: Spoken language modelling","created":"2021-04-29","cited_by_count":47,"area":null},{"id":"2502.06490","title":"Recent Advances in Discrete Speech Tokens: A Review","created":"2025-02-10","cited_by_count":43,"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":"2505.15957","title":"Towards Holistic Evaluation of Large Audio-Language Models: A Comprehensive Survey","created":"2025-05-21","cited_by_count":39,"area":null},{"id":"2305.10005","title":"DinoSR: Self-Distillation and Online Clustering for Self-supervised Speech Representation Learning","created":"2023-05-17","cited_by_count":37,"area":"distill"},{"id":"2210.15759","title":"Self-supervised language learning from raw audio: Lessons from the Zero Resource Speech Challenge","created":"2022-10-27","cited_by_count":34,"area":null},{"id":"2404.00685","title":"Scaling Properties of Speech Language Models","created":"2024-03-31","cited_by_count":32,"area":null},{"id":"2306.01506","title":"BabySLM: language-acquisition-friendly benchmark of self-supervised spoken language models","created":"2023-06-02","cited_by_count":29,"area":null},{"id":"2202.07359","title":"textless-lib: a Library for Textless Spoken Language Processing","created":"2022-02-15","cited_by_count":28,"area":null},{"id":"2202.03543","title":"Self-Supervised Representation Learning for Speech Using Visual Grounding and Masked Language Modeling","created":"2022-02-07","cited_by_count":25,"area":null},{"id":"2302.12057","title":"ProsAudit, a prosodic benchmark for self-supervised speech models","created":"2023-02-23","cited_by_count":25,"area":null},{"id":"2202.11929","title":"Word Segmentation on Discovered Phone Units with Dynamic Programming and Self-Supervised Scoring","created":"2022-02-24","cited_by_count":24,"area":null},{"id":"2203.05936","title":"Are discrete units necessary for Spoken Language Modeling?","created":"2022-03-11","cited_by_count":24,"area":null},{"id":"2410.04029","title":"SyllableLM: Learning Coarse Semantic Units for Speech Language Models","created":"2024-10-05","cited_by_count":24,"area":null},{"id":"2109.08186","title":"Fast-Slow Transformer for Visually Grounding Speech","created":"2021-09-16","cited_by_count":23,"area":null},{"id":"2411.01834","title":"Align-SLM: Textless Spoken Language Models with Reinforcement Learning from AI Feedback","created":"2024-11-04","cited_by_count":23,"area":"alignment"},{"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":"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":"2310.05224","title":"Generative Spoken Language Model based on continuous word-sized audio tokens","created":"2023-10-08","cited_by_count":19,"area":null},{"id":"2410.07168","title":"Sylber: Syllabic Embedding Representation of Speech from Raw Audio","created":"2024-10-09","cited_by_count":19,"area":null},{"id":"2412.18603","title":"Long-Form Speech Generation with Spoken Language Models","created":"2024-12-24","cited_by_count":19,"area":null},{"id":"2110.15909","title":"Contrastive prediction strategies for unsupervised segmentation and categorization of phonemes and words","created":"2021-10-29","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":"2209.15483","title":"Augmentation Invariant Discrete Representation for Generative Spoken Language Modeling","created":"2022-09-30","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":"2410.00168","title":"SSR: Alignment-Aware Modality Connector for Speech Language Models","created":"2024-09-30","cited_by_count":16,"area":null},{"id":"2501.04962","title":"VoxEval: Benchmarking the Knowledge Understanding Capabilities of End-to-End Spoken Language Models","created":"2025-01-09","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":"2104.11946","title":"Aligned Contrastive Predictive Coding","created":"2021-04-24","cited_by_count":15,"area":null},{"id":"2111.02674","title":"Voice Conversion Can Improve ASR in Very Low-Resource Settings","created":"2021-11-04","cited_by_count":14,"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":"2206.02211","title":"Variable-rate hierarchical CPC leads to acoustic unit discovery in speech","created":"2022-06-05","cited_by_count":13,"area":null},{"id":"2210.10027","title":"Maestro-U: Leveraging joint speech-text representation learning for zero supervised speech ASR","created":"2022-10-18","cited_by_count":13,"area":null},{"id":"2306.04306","title":"Allophant: Cross-lingual Phoneme Recognition with Articulatory Attributes","created":"2023-06-07","cited_by_count":13,"area":null},{"id":"2206.11332","title":"DP-Parse: Finding Word Boundaries from Raw Speech with an Instance Lexicon","created":"2022-06-22","cited_by_count":12,"area":null},{"id":"2310.03018","title":"Zero Resource Code-switched Speech Benchmark Using Speech Utterance Pairs For Multiple Spoken Languages","created":"2023-10-04","cited_by_count":12,"area":null},{"id":"2210.15775","title":"Evaluating context-invariance in unsupervised speech representations","created":"2022-10-27","cited_by_count":11,"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":"2409.03701","title":"LAST: Language Model Aware Speech Tokenization","created":"2024-09-05","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":"2410.00025","title":"Improving Spoken Language Modeling with Phoneme Classification: A Simple Fine-tuning Approach","created":"2024-09-16","cited_by_count":8,"area":null},{"id":"2412.17048","title":"Why Do Speech Language Models Fail to Generate Semantically Coherent Outputs? A Modality Evolving Perspective","created":"2024-12-22","cited_by_count":8,"area":null},{"id":"2512.20308","title":"SpidR: Learning Fast and Stable Linguistic Units for Spoken Language Models Without Supervision","created":"2025-12-23","cited_by_count":8,"area":null},{"id":"2104.00766","title":"Configurable Privacy-Preserving Automatic Speech Recognition","created":"2021-04-01","cited_by_count":7,"area":null},{"id":"2106.11603","title":"Information Retrieval for ZeroSpeech 2021: The Submission by University of Wroclaw","created":"2021-06-22","cited_by_count":7,"area":null},{"id":"2204.05148","title":"Speech Sequence Embeddings using Nearest Neighbors Contrastive Learning","created":"2022-04-11","cited_by_count":7,"area":null},{"id":"2505.02692","title":"fastabx: A library for efficient computation of ABX discriminability","created":"2025-05-05","cited_by_count":7,"area":null},{"id":"2508.09350","title":"Flow-SLM: Joint Learning of Linguistic and Acoustic Information for Spoken Language Modeling","created":"2025-08-12","cited_by_count":7,"area":null},{"id":"2602.09823","title":"Covo-Audio Technical Report","created":"2026-02-10","cited_by_count":7,"area":null},{"id":"2107.06546","title":"ZR-2021VG: Zero-Resource Speech Challenge, Visually-Grounded Language Modelling track, 2021 edition","created":"2021-07-14","cited_by_count":6,"area":null},{"id":"2401.14289","title":"Speech foundation models on intelligibility prediction for hearing-impaired listeners","created":"2024-01-24","cited_by_count":6,"area":null},{"id":"2504.03036","title":"IPA-CHILDES & G2P+: Feature-Rich Resources for Cross-Lingual Phonology and Phonemic Language Modeling","created":"2025-04-03","cited_by_count":6,"area":null},{"id":"2505.14470","title":"PAST: Phonetic-Acoustic Speech Tokenizer","created":"2025-05-20","cited_by_count":6,"area":null},{"id":"2305.19563","title":"Zero-Shot Automatic Pronunciation Assessment","created":"2023-05-31","cited_by_count":5,"area":null},{"id":"2510.06195","title":"Latent Speech-Text Transformer","created":"2025-10-07","cited_by_count":5,"area":null},{"id":"2402.03988","title":"REBORN: Reinforcement-Learned Boundary Segmentation with Iterative Training for Unsupervised ASR","created":"2024-02-06","cited_by_count":4,"area":null},{"id":"2505.17446","title":"Exploring the Effect of Segmentation and Vocabulary Size on Speech Tokenization for Speech Language Models","created":"2025-05-23","cited_by_count":4,"area":null},{"id":"2601.14046","title":"PRiSM: Benchmarking Phone Realization in Speech Models","created":"2026-01-20","cited_by_count":4,"area":null},{"id":"2602.16687","title":"Scaling Open Discrete Audio Foundation Models with Interleaved Semantic, Acoustic, and Text Tokens","created":"2026-02-18","cited_by_count":4,"area":null},{"id":"2111.11433","title":"Towards Tokenized Human Dynamics Representation","created":"2021-11-22","cited_by_count":3,"area":null},{"id":"2509.14882","title":"Llama-Mimi: Exploring the Limits of Flattened Speech Language Modeling","created":"2025-09-18","cited_by_count":3,"area":null},{"id":"2510.04268","title":"LongTail-Swap: benchmarking language models' abilities on rare words","created":"2025-10-05","cited_by_count":3,"area":null},{"id":"2209.06987","title":"Non-Parallel Voice Conversion for ASR Augmentation","created":"2022-09-15","cited_by_count":2,"area":null},{"id":"2303.08809","title":"Cascading and Direct Approaches to Unsupervised Constituency Parsing on Spoken Sentences","created":"2023-03-15","cited_by_count":2,"area":null},{"id":"2312.01515","title":"Bigger is not Always Better: The Effect of Context Size on Speech Pre-Training","created":"2023-12-03","cited_by_count":2,"area":null},{"id":"2405.08237","title":"A predictive learning model can simulate temporal dynamics and context effects found in neural representations of continuous speech","created":"2024-05-13","cited_by_count":2,"area":null},{"id":"2504.03338","title":"BabyLM's First Words: Word Segmentation as a Phonological Probing Task","created":"2025-04-04","cited_by_count":2,"area":null},{"id":"2601.10272","title":"MoST: Mixing Speech and Text with Modality-Aware Mixture of Experts","created":"2026-01-15","cited_by_count":2,"area":"mllm"},{"id":"2601.18617","title":"Emergence of Phonemic, Syntactic, and Semantic Representations in Artificial Neural Networks","created":"2026-01-26","cited_by_count":2,"area":null},{"id":"2206.11706","title":"A Temporal Extension of Latent Dirichlet Allocation for Unsupervised Acoustic Unit Discovery","created":"2022-06-23","cited_by_count":1,"area":null},{"id":"2312.11142","title":"Efficiency-oriented approaches for self-supervised speech representation learning","created":"2023-12-18","cited_by_count":1,"area":null},{"id":"2402.05819","title":"Integrating Self-supervised Speech Model with Pseudo Word-level Targets from Visually-grounded Speech Model","created":"2024-02-08","cited_by_count":1,"area":null},{"id":"2404.00856","title":"Removing Speaker Information from Speech Representation using Variable-Length Soft Pooling","created":"2024-04-01","cited_by_count":1,"area":null},{"id":"2506.14767","title":"A Variational Framework for Improving Naturalness in Generative Spoken Language Models","created":"2025-06-17","cited_by_count":1,"area":null},{"id":"2508.04814","title":"Pitch Accent Detection improves Pretrained Automatic Speech Recognition","created":"2025-08-06","cited_by_count":1,"area":null},{"id":"2509.05359","title":"An Empirical Analysis of Discrete Unit Representations in Speech Language Modeling Pre-training","created":"2025-09-03","cited_by_count":1,"area":null},{"id":"2509.17523","title":"Leveraging Audio-Visual Data to Reduce the Multilingual Gap in Self-Supervised Speech Models","created":"2025-09-22","cited_by_count":1,"area":null},{"id":"2512.21204","title":"SpidR-Adapt: A Universal Speech Representation Model for Few-Shot Adaptation","created":"2025-12-24","cited_by_count":1,"area":null},{"id":"2402.01298","title":"Learning Semantic Information from Raw Audio Signal Using Both Contextual and Phonetic Representations","created":"2024-02-02","cited_by_count":0,"area":null},{"id":"2508.11598","title":"Representing Speech Through Autoregressive Prediction of Cochlear Tokens","created":"2025-08-15","cited_by_count":0,"area":null},{"id":"2602.04217","title":"Frontend Token Enhancement for Token-Based Speech Recognition","created":"2026-02-04","cited_by_count":0,"area":null},{"id":"2603.18612","title":"DiscoPhon: Benchmarking the Unsupervised Discovery of Phoneme Inventories With Discrete Speech Units","created":"2026-03-19","cited_by_count":0,"area":null},{"id":"2607.04064","title":"Speaker-Disentangled Chunk-Wise Regression for Syllabic Tokenization","created":"2026-07-05","cited_by_count":0,"area":null},{"id":"2609.33345","title":"Language Discrimination Improves Linguistic Learning in Multilingual Speech Models","created":"2026-09-27","cited_by_count":0,"area":null}],"next_cursor":"100"}