{"total":144,"rows":[{"id":"2212.09058","title":"BEATs: Audio Pre-Training with Acoustic Tokenizers","created":"2022-12-18","cited_by_count":388,"area":null},{"id":"2306.12925","title":"AudioPaLM: A Large Language Model That Can Speak and Listen","created":"2023-06-22","cited_by_count":343,"area":null},{"id":"2205.10643","title":"Self-Supervised Speech Representation Learning: A Review","created":"2022-05-21","cited_by_count":260,"area":null},{"id":"2303.01037","title":"Google USM: Scaling Automatic Speech Recognition Beyond 100 Languages","created":"2023-03-02","cited_by_count":231,"area":null},{"id":"2307.11795","title":"Prompting Large Language Models with Speech Recognition Abilities","created":"2023-07-21","cited_by_count":140,"area":null},{"id":"2305.09636","title":"SoundStorm: Efficient Parallel Audio Generation","created":"2023-05-16","cited_by_count":114,"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":"2304.04947","title":"Conditional Adapters: Parameter-efficient Transfer Learning with Fast Inference","created":"2023-04-11","cited_by_count":69,"area":null},{"id":"2501.01108","title":"MuQ: Self-Supervised Music Representation Learning with Mel Residual Vector Quantization","created":"2025-01-02","cited_by_count":68,"area":null},{"id":"2310.00230","title":"SLM: Bridge the thin gap between speech and text foundation models","created":"2023-09-30","cited_by_count":67,"area":null},{"id":"2405.08295","title":"SpeechVerse: A Large-scale Generalizable Audio Language Model","created":"2024-05-14","cited_by_count":63,"area":null},{"id":"2410.06424","title":"Restructuring Vector Quantization with the Rotation Trick","created":"2024-10-08","cited_by_count":51,"area":null},{"id":"2407.00837","title":"Towards Robust Speech Representation Learning for Thousands of Languages","created":"2024-06-30","cited_by_count":50,"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":"2210.00705","title":"SpeechCLIP: Integrating Speech with Pre-Trained Vision and Language Model","created":"2022-10-03","cited_by_count":29,"area":null},{"id":"2204.12765","title":"Why does Self-Supervised Learning for Speech Recognition Benefit Speaker Recognition?","created":"2022-04-27","cited_by_count":27,"area":null},{"id":"2203.12668","title":"Pseudo Label Is Better Than Human Label","created":"2022-03-22","cited_by_count":25,"area":null},{"id":"2210.07353","title":"JOIST: A Joint Speech and Text Streaming Model For ASR","created":"2022-10-13","cited_by_count":24,"area":null},{"id":"2303.01664","title":"Miipher: A Robust Speech Restoration Model Integrating Self-Supervised Speech and Text Representations","created":"2023-03-03","cited_by_count":22,"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":"2211.00115","title":"Textless Direct Speech-to-Speech Translation with Discrete Speech Representation","created":"2022-10-31","cited_by_count":19,"area":null},{"id":"2509.12508","title":"Fun-ASR Technical Report","created":"2025-09-15","cited_by_count":19,"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":"2410.01162","title":"Frozen Large Language Models Can Perceive Paralinguistic Aspects of Speech","created":"2024-10-02","cited_by_count":18,"area":null},{"id":"2310.16931","title":"CL-MASR: A Continual Learning Benchmark for Multilingual ASR","created":"2023-10-25","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":"2303.16501","title":"AVFormer: Injecting Vision into Frozen Speech Models for Zero-Shot AV-ASR","created":"2023-03-29","cited_by_count":16,"area":null},{"id":"2208.12345","title":"Light-weight probing of unsupervised representations for Reinforcement Learning","created":"2022-08-25","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":"2403.02522","title":"HeAR -- Health Acoustic Representations","created":"2024-03-04","cited_by_count":15,"area":null},{"id":"2206.10125","title":"Supervision-Guided Codebooks for Masked Prediction in Speech Pre-training","created":"2022-06-21","cited_by_count":14,"area":null},{"id":"2404.09841","title":"Anatomy of Industrial Scale Multilingual ASR","created":"2024-04-15","cited_by_count":14,"area":null},{"id":"2503.19611","title":"Analyzable Chain-of-Musical-Thought Prompting for High-Fidelity Music Generation","created":"2025-03-25","cited_by_count":14,"area":null},{"id":"2302.01496","title":"Efficient Domain Adaptation for Speech Foundation Models","created":"2023-02-03","cited_by_count":13,"area":null},{"id":"2401.00273","title":"Investigating Zero-Shot Generalizability on Mandarin-English Code-Switched ASR and Speech-to-text Translation of Recent Foundation Models with Self-Supervision and Weak Supervision","created":"2023-12-30","cited_by_count":13,"area":null},{"id":"2508.16790","title":"TaDiCodec: Text-aware Diffusion Speech Tokenizer for Speech Language Modeling","created":"2025-08-22","cited_by_count":13,"area":null},{"id":"2408.13040","title":"SpeechPrompt: Prompting Speech Language Models for Speech Processing Tasks","created":"2024-08-23","cited_by_count":12,"area":null},{"id":"2409.06029","title":"SongCreator: Lyrics-based Universal Song Generation","created":"2024-09-09","cited_by_count":12,"area":null},{"id":"2403.14402","title":"XLAVS-R: Cross-Lingual Audio-Visual Speech Representation Learning for Noise-Robust Speech Perception","created":"2024-03-21","cited_by_count":11,"area":null},{"id":"2205.05227","title":"Towards Improved Zero-shot Voice Conversion with Conditional DSVAE","created":"2022-05-11","cited_by_count":10,"area":null},{"id":"2304.04974","title":"Wav2code: Restore Clean Speech Representations via Codebook Lookup for Noise-Robust ASR","created":"2023-04-11","cited_by_count":10,"area":null},{"id":"2405.17809","title":"TransVIP: Speech to Speech Translation System with Voice and Isochrony Preservation","created":"2024-05-28","cited_by_count":10,"area":null},{"id":"2302.10915","title":"Conformers are All You Need for Visual Speech Recognition","created":"2023-02-17","cited_by_count":9,"area":null},{"id":"2405.04296","title":"Open Implementation and Study of BEST-RQ for Speech Processing","created":"2024-05-07","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":"2509.16195","title":"FocalCodec-Stream: Streaming Low-Bitrate Speech Coding via Causal Distillation","created":"2025-09-19","cited_by_count":9,"area":null},{"id":"2309.15317","title":"Joint Prediction and Denoising for Large-scale Multilingual Self-supervised Learning","created":"2023-09-26","cited_by_count":8,"area":null},{"id":"2503.20212","title":"Dolphin: A Large-Scale Automatic Speech Recognition Model for Eastern Languages","created":"2025-03-26","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":"2402.16321","title":"Self-Supervised Speech Quality Estimation and Enhancement Using Only Clean Speech","created":"2024-02-26","cited_by_count":7,"area":null},{"id":"2408.05758","title":"VQ-CTAP: Cross-Modal Fine-Grained Sequence Representation Learning for Speech Processing","created":"2024-08-11","cited_by_count":7,"area":null},{"id":"2601.02391","title":"WearVox: An Egocentric Multichannel Voice Assistant Benchmark for Wearables","created":"2025-12-25","cited_by_count":7,"area":null},{"id":"2310.15970","title":"Accented Speech Recognition With Accent-specific Codebooks","created":"2023-10-24","cited_by_count":6,"area":null},{"id":"2412.18566","title":"Zero-resource Speech Translation and Recognition with LLMs","created":"2024-12-24","cited_by_count":6,"area":null},{"id":"2512.14697","title":"Spherical Leech Quantization for Visual Tokenization and Generation","created":"2025-12-16","cited_by_count":6,"area":null},{"id":"2603.00632","title":"Stop Treating Collisions Equally: Qualification-Aware Semantic ID Learning for Recommendation at Industrial Scale","created":"2026-02-28","cited_by_count":6,"area":null},{"id":"2309.17395","title":"AV-CPL: Continuous Pseudo-Labeling for Audio-Visual Speech Recognition","created":"2023-09-29","cited_by_count":5,"area":null},{"id":"2310.11739","title":"Unintended Memorization in Large ASR Models, and How to Mitigate It","created":"2023-10-18","cited_by_count":5,"area":null},{"id":"2401.06980","title":"Joint Unsupervised and Supervised Training for Automatic Speech Recognition via Bilevel Optimization","created":"2024-01-13","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":"2410.20336","title":"Get Large Language Models Ready to Speak: A Late-fusion Approach for Speech Generation","created":"2024-10-27","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":"2503.00733","title":"UniWav: Towards Unified Pre-training for Speech Representation Learning and Generation","created":"2025-03-02","cited_by_count":5,"area":null},{"id":"2504.18539","title":"Multi-Task Corrupted Prediction for Learning Robust Audio-Visual Speech Representation","created":"2025-01-23","cited_by_count":5,"area":null},{"id":"2505.21138","title":"Leveraging LLM and Self-Supervised Training Models for Speech Recognition in Chinese Dialects: A Comparative Analysis","created":"2025-05-27","cited_by_count":5,"area":null},{"id":"2509.26469","title":"DiVeQ: Differentiable Vector Quantization Using the Reparameterization Trick","created":"2025-09-30","cited_by_count":5,"area":null},{"id":"2306.04374","title":"Label Aware Speech Representation Learning For Language Identification","created":"2023-06-07","cited_by_count":4,"area":null},{"id":"2309.08023","title":"USM-SCD: Multilingual Speaker Change Detection Based on Large Pretrained Foundation Models","created":"2023-09-14","cited_by_count":4,"area":null},{"id":"2309.09996","title":"Improving Speech Recognition for African American English With Audio Classification","created":"2023-09-16","cited_by_count":4,"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":"2409.02384","title":"STAB: Speech Tokenizer Assessment Benchmark","created":"2024-09-04","cited_by_count":4,"area":null},{"id":"2412.11538","title":"MERaLiON-SpeechEncoder: Towards a Speech Foundation Model for Singapore and Beyond","created":"2024-12-16","cited_by_count":4,"area":null},{"id":"2505.11352","title":"LegoSLM: Connecting LLM with Speech Encoder using CTC Posteriors","created":"2025-05-16","cited_by_count":4,"area":null},{"id":"2505.16306","title":"Layer-wise Investigation of Large-Scale Self-Supervised Music Representation Models","created":"2025-05-22","cited_by_count":4,"area":null},{"id":"2509.22220","title":"StableToken: A Noise-Robust Semantic Speech Tokenizer for Resilient SpeechLLMs","created":"2025-09-26","cited_by_count":4,"area":null},{"id":"2607.20253","title":"Pushing the Frontier of Full-Song Generation: Hierarchical Autoregressive Planning Meets Flow-Matching Rendering","created":"2026-07-22","cited_by_count":4,"area":null},{"id":"2211.02712","title":"Resource-Efficient Transfer Learning From Speech Foundation Model Using Hierarchical Feature Fusion","created":"2022-11-04","cited_by_count":3,"area":null},{"id":"2312.03406","title":"Does Vector Quantization Fail in Spatio-Temporal Forecasting? Exploring a Differentiable Sparse Soft-Vector Quantization Approach","created":"2023-12-06","cited_by_count":3,"area":null},{"id":"2312.09369","title":"Audio-visual fine-tuning of audio-only ASR models","created":"2023-12-14","cited_by_count":3,"area":null},{"id":"2404.02052","title":"Noise Masking Attacks and Defenses for Pretrained Speech Models","created":"2024-04-02","cited_by_count":3,"area":null},{"id":"2409.08680","title":"NEST-RQ: Next Token Prediction for Speech Self-Supervised Pre-Training","created":"2024-09-13","cited_by_count":3,"area":null},{"id":"2505.19014","title":"Tokenizing Electron Cloud in Protein-Ligand Interaction Learning","created":"2025-05-25","cited_by_count":3,"area":null},{"id":"2509.01588","title":"From Discord to Harmony: Decomposed Consonance-based Training for Improved Audio Chord Estimation","created":"2025-09-01","cited_by_count":3,"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":"2312.10087","title":"Revisiting the Entropy Semiring for Neural Speech Recognition","created":"2023-12-13","cited_by_count":2,"area":null},{"id":"2403.19709","title":"Hierarchical Recurrent Adapters for Efficient Multi-Task Adaptation of Large Speech Models","created":"2024-03-25","cited_by_count":2,"area":null},{"id":"2405.00420","title":"Self-supervised Pre-training of Text Recognizers","created":"2024-05-01","cited_by_count":2,"area":null},{"id":"2406.02004","title":"Efficiently Train ASR Models that Memorize Less and Perform Better with Per-core Clipping","created":"2024-06-04","cited_by_count":2,"area":null},{"id":"2406.06664","title":"ASTRA: Aligning Speech and Text Representations for Asr without Sampling","created":"2024-06-10","cited_by_count":2,"area":null},{"id":"2407.13377","title":"Linear-Complexity Self-Supervised Learning for Speech Processing","created":"2024-07-18","cited_by_count":2,"area":null},{"id":"2408.00674","title":"ChordSync: Conformer-Based Alignment of Chord Annotations to Music Audio","created":"2024-08-01","cited_by_count":2,"area":null},{"id":"2408.11873","title":"Parameter-Efficient Transfer Learning under Federated Learning for Automatic Speech Recognition","created":"2024-08-19","cited_by_count":2,"area":null},{"id":"2409.02596","title":"An Analysis of Linear Complexity Attention Substitutes with BEST-RQ","created":"2024-09-04","cited_by_count":2,"area":null},{"id":"2409.13953","title":"Training Large ASR Encoders with Differential Privacy","created":"2024-09-21","cited_by_count":2,"area":null},{"id":"2412.00049","title":"A Survey of Recent Advances and Challenges in Deep Audio-Visual Correlation Learning","created":"2024-11-24","cited_by_count":2,"area":null},{"id":"2509.15579","title":"Chunk Based Speech Pre-training with High Resolution Finite Scalar Quantization","created":"2025-09-19","cited_by_count":2,"area":null},{"id":"2510.24570","title":"BEST-RQ-Based Self-Supervised Learning for Whisper Domain Adaptation","created":"2025-10-28","cited_by_count":2,"area":null},{"id":"2602.06602","title":"Scaling Speech Tokenizers with Diffusion Autoencoders","created":"2026-02-06","cited_by_count":2,"area":null},{"id":"2603.21900","title":"Ara-Best-RQ: Multi Dialectal Arabic SSL","created":"2026-03-23","cited_by_count":2,"area":null},{"id":"2301.00656","title":"TriNet: stabilizing self-supervised learning from complete or slow collapse on ASR","created":"2022-12-12","cited_by_count":1,"area":null}],"next_cursor":"100"}