{"total":101,"rows":[{"id":"2212.04356","title":"Robust Speech Recognition via Large-Scale Weak Supervision","created":"2022-12-06","cited_by_count":4057,"area":null},{"id":"2411.04996","title":"Mixture-of-Transformers: A Sparse and Scalable Architecture for Multi-Modal Foundation Models","created":"2024-11-07","cited_by_count":163,"area":null},{"id":"2406.16020","title":"AudioBench: A Universal Benchmark for Audio Large Language Models","created":"2024-06-23","cited_by_count":128,"area":null},{"id":"2305.13009","title":"Textually Pretrained Speech Language Models","created":"2023-05-22","cited_by_count":101,"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":"2305.15255","title":"Spoken Question Answering and Speech Continuation Using Spectrogram-Powered LLM","created":"2023-05-24","cited_by_count":94,"area":null},{"id":"2311.00430","title":"Distil-Whisper: Robust Knowledge Distillation via Large-Scale Pseudo Labelling","created":"2023-11-01","cited_by_count":90,"area":"distill"},{"id":"2411.13577","title":"WavChat: A Survey of Spoken Dialogue Models","created":"2024-11-15","cited_by_count":90,"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":"2506.09344","title":"Ming-Omni: A Unified Multimodal Model for Perception and Generation","created":"2025-06-11","cited_by_count":66,"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":"2410.02678","title":"Distilling an End-to-End Voice Assistant Without Instruction Training Data","created":"2024-10-03","cited_by_count":39,"area":null},{"id":"2406.11546","title":"GigaSpeech 2: An Evolving, Large-Scale and Multi-domain ASR Corpus for Low-Resource Languages with Automated Crawling, Transcription and Refinement","created":"2024-06-17","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":"2505.03739","title":"VITA-Audio: Fast Interleaved Cross-Modal Token Generation for Efficient Large Speech-Language Model","created":"2025-05-06","cited_by_count":31,"area":null},{"id":"2506.00338","title":"OWSM v4: Improving Open Whisper-Style Speech Models via Data Scaling and Cleaning","created":"2025-05-31","cited_by_count":27,"area":null},{"id":"2511.12609","title":"Uni-MoE-2.0-Omni: Scaling Language-Centric Omnimodal Large Model with Advanced MoE, Training and Data","created":"2025-11-16","cited_by_count":21,"area":"moe"},{"id":"2201.10207","title":"SPIRAL: Self-supervised Perturbation-Invariant Representation Learning for Speech Pre-Training","created":"2022-01-25","cited_by_count":19,"area":"distill"},{"id":"2410.15608","title":"Moonshine: Speech Recognition for Live Transcription and Voice Commands","created":"2024-10-21","cited_by_count":19,"area":null},{"id":"2202.01327","title":"Adaptive Sampling Strategies to Construct Equitable Training Datasets","created":"2022-01-31","cited_by_count":18,"area":null},{"id":"2210.13352","title":"ESB: A Benchmark For Multi-Domain End-to-End Speech Recognition","created":"2022-10-24","cited_by_count":18,"area":null},{"id":"2206.13135","title":"TALCS: An Open-Source Mandarin-English Code-Switching Corpus and a Speech Recognition Baseline","created":"2022-06-27","cited_by_count":17,"area":null},{"id":"2511.05516","title":"Ming-UniAudio: Speech LLM for Joint Understanding, Generation and Editing with Unified Representation","created":"2025-10-26","cited_by_count":17,"area":null},{"id":"2402.05706","title":"Paralinguistics-Aware Speech-Empowered Large Language Models for Natural Conversation","created":"2024-02-08","cited_by_count":14,"area":null},{"id":"2410.01036","title":"MOSEL: 950,000 Hours of Speech Data for Open-Source Speech Foundation Model Training on EU Languages","created":"2024-10-01","cited_by_count":14,"area":null},{"id":"2504.02398","title":"Scaling Analysis of Interleaved Speech-Text Language Models","created":"2025-04-03","cited_by_count":14,"area":null},{"id":"2504.09081","title":"SIFT-50M: A Large-Scale Multilingual Dataset for Speech Instruction Fine-Tuning","created":"2025-04-12","cited_by_count":14,"area":null},{"id":"2603.06577","title":"Omni-Diffusion: Unified Multimodal Understanding and Generation with Masked Discrete Diffusion","created":"2026-03-06","cited_by_count":13,"area":"mllm"},{"id":"2502.15814","title":"Slamming: Training a Speech Language Model on One GPU in a Day","created":"2025-02-19","cited_by_count":12,"area":null},{"id":"2503.01879","title":"Nexus: An Omni-Perceptive And -Interactive Model for Language, Audio, And Vision","created":"2025-02-26","cited_by_count":12,"area":null},{"id":"2505.19598","title":"Evaluating Robustness of Large Audio Language Models to Audio Injection: An Empirical Study","created":"2025-05-26","cited_by_count":12,"area":null},{"id":"2212.08704","title":"Speech Aware Dialog System Technology Challenge (DSTC11)","created":"2022-12-16","cited_by_count":10,"area":null},{"id":"2306.05644","title":"WSPAlign: Word Alignment Pre-training via Large-Scale Weakly Supervised Span Prediction","created":"2023-06-09","cited_by_count":10,"area":null},{"id":"2306.07944","title":"Speech-to-Text Adapter and Speech-to-Entity Retriever Augmented LLMs for Speech Understanding","created":"2023-06-08","cited_by_count":9,"area":null},{"id":"2310.18877","title":"Pre-trained Speech Processing Models Contain Human-Like Biases that Propagate to Speech Emotion Recognition","created":"2023-10-29","cited_by_count":9,"area":null},{"id":"2406.18301","title":"MSR-86K: An Evolving, Multilingual Corpus with 86,300 Hours of Transcribed Audio for Speech Recognition Research","created":"2024-06-26","cited_by_count":9,"area":null},{"id":"2505.21578","title":"Loquacious Set: 25,000 Hours of Transcribed and Diverse English Speech Recognition Data for Research and Commercial Use","created":"2025-05-27","cited_by_count":9,"area":null},{"id":"2309.06981","title":"MASTERKEY: Practical Backdoor Attack Against Speaker Verification Systems","created":"2023-09-13","cited_by_count":8,"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":"2410.03458","title":"Multi-Dialect Vietnamese: Task, Dataset, Baseline Models and Challenges","created":"2024-10-04","cited_by_count":6,"area":null},{"id":"2410.17485","title":"VoiceTextBlender: Augmenting Large Language Models with Speech Capabilities via Single-Stage Joint Speech-Text Supervised Fine-Tuning","created":"2024-10-23","cited_by_count":6,"area":null},{"id":"2601.01373","title":"UltraEval-Audio: A Unified Framework for Comprehensive Evaluation of Audio Foundation Models","created":"2026-01-04","cited_by_count":6,"area":null},{"id":"2305.12793","title":"Zero-Shot End-to-End Spoken Language Understanding via Cross-Modal Selective Self-Training","created":"2023-05-22","cited_by_count":5,"area":null},{"id":"2309.03978","title":"LanSER: Language-Model Supported Speech Emotion Recognition","created":"2023-09-07","cited_by_count":5,"area":null},{"id":"2402.00235","title":"Exploring the limits of decoder-only models trained on public speech recognition corpora","created":"2024-01-31","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":"2406.05547","title":"Exploring the Benefits of Tokenization of Discrete Acoustic Units","created":"2024-06-08","cited_by_count":4,"area":null},{"id":"2406.09618","title":"Multi-Modal Retrieval For Large Language Model Based Speech Recognition","created":"2024-06-13","cited_by_count":4,"area":"mllm"},{"id":"2406.15284","title":"The Greek podcast corpus: Competitive speech models for low-resourced languages with weakly supervised data","created":"2024-06-21","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":"2508.20869","title":"OLMoASR: Open Models and Data for Training Robust Speech Recognition Models","created":"2025-08-28","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":"2406.11022","title":"Outlier Reduction with Gated Attention for Improved Post-training Quantization in Large Sequence-to-sequence Speech Foundation Models","created":"2024-06-16","cited_by_count":3,"area":"distill"},{"id":"2503.06211","title":"LF${}^{2}$AR: Accounting for Layerwise Dynamics to Improve Multimodal Adaptation of Language Models","created":"2025-03-08","cited_by_count":3,"area":null},{"id":"2506.01439","title":"Whale: Large-Scale multilingual ASR model with w2v-BERT and E-Branchformer with large speech data","created":"2025-06-02","cited_by_count":3,"area":null},{"id":"2507.21138","title":"TTS-1 Technical Report","created":"2025-07-22","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":"2512.02201","title":"Swivuriso: The South African Next Voices Multilingual Speech Dataset","created":"2025-12-01","cited_by_count":3,"area":null},{"id":"2305.15055","title":"Iteratively Improving Speech Recognition and Voice Conversion","created":"2023-05-24","cited_by_count":2,"area":null},{"id":"2312.02931","title":"WhisBERT: Multimodal Text-Audio Language Modeling on 100M Words","created":"2023-12-05","cited_by_count":2,"area":null},{"id":"2409.16654","title":"Speech Recognition Rescoring with Large Speech-Text Foundation Models","created":"2024-09-25","cited_by_count":2,"area":"mllm"},{"id":"2410.02597","title":"HAINAN: Fast and Accurate Transducer for Hybrid-Autoregressive ASR","created":"2024-10-03","cited_by_count":2,"area":null},{"id":"2411.00266","title":"A Systematic Review of NeurIPS Dataset Management Practices","created":"2024-10-31","cited_by_count":2,"area":null},{"id":"2502.12408","title":"On the Robust Approximation of ASR Metrics","created":"2025-02-18","cited_by_count":2,"area":null},{"id":"2504.12254","title":"Advancing Arabic Speech Recognition Through Large-Scale Weakly Supervised Learning","created":"2025-04-16","cited_by_count":2,"area":null},{"id":"2606.13544","title":"Adaptive Turn-Taking for Real-time Multi-Party Voice Agents","created":"2026-06-11","cited_by_count":2,"area":"agents"},{"id":"2607.16107","title":"Audio-Visual Flamingo: Open Audio-Visual Intelligence for Long and Complex Videos","created":"2026-07-17","cited_by_count":2,"area":"lr"},{"id":"2204.00218","title":"End-to-End Multi-speaker ASR with Independent Vector Analysis","created":"2022-04-01","cited_by_count":1,"area":null},{"id":"2311.07014","title":"Teach me with a Whisper: Enhancing Large Language Models for Analyzing Spoken Transcripts using Speech Embeddings","created":"2023-11-13","cited_by_count":1,"area":"mllm"},{"id":"2504.07229","title":"Visual-Aware Speech Recognition for Noisy Scenarios","created":"2025-04-09","cited_by_count":1,"area":null},{"id":"2506.16738","title":"LM-SPT: LM-Aligned Semantic Distillation for Speech Tokenization","created":"2025-06-20","cited_by_count":1,"area":null},{"id":"2508.01178","title":"Advancing the Foundation Model for Music Understanding","created":"2025-08-02","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":"2509.26276","title":"Optimizing Speech Language Models for Acoustic Consistency","created":"2025-09-30","cited_by_count":1,"area":null},{"id":"2601.09239","title":"DSA-Tokenizer: Disentangled Semantic-Acoustic Tokenization via Flow Matching-based Hierarchical Fusion","created":"2026-01-14","cited_by_count":1,"area":"diffusion"},{"id":"2604.08003","title":"Rethinking Entropy Allocation in LLM-based ASR: Understanding the Dynamics between Speech Encoders and LLMs","created":"2026-04-09","cited_by_count":1,"area":"lr"},{"id":"2604.16767","title":"When Misinformation Speaks and Converses: Rethinking Fact-Checking in Audio Platforms","created":"2026-04-18","cited_by_count":1,"area":null},{"id":"2605.06765","title":"VITA-QinYu: Expressive Spoken Language Model for Role-Playing and Singing","created":"2026-05-07","cited_by_count":1,"area":null},{"id":"2606.06837","title":"SEAM: Shortcut-Aware Real-Time Detection of Scripted vs. Spontaneous Speech for Interview Guardrails","created":"2026-06-05","cited_by_count":1,"area":"safety"},{"id":"2606.25391","title":"From Sounds to Scenes: A Benchmark for Evaluating Context-Aware Auditory Scene Understanding in Large Audio Language Models","created":"2026-06-24","cited_by_count":1,"area":null},{"id":"2112.11478","title":"LSH methods for data deduplication in a Wikipedia artificial dataset","created":"2021-12-10","cited_by_count":0,"area":null},{"id":"2406.10223","title":"Diffusion Synthesizer for Efficient Multilingual Speech to Speech Translation","created":"2024-06-14","cited_by_count":0,"area":null},{"id":"2502.12714","title":"Playing with Voices: Tabletop Role-Playing Game Recordings as a Diarization Challenge","created":"2025-02-18","cited_by_count":0,"area":null},{"id":"2506.17019","title":"Instituto de Telecomunica\\c{c}\\~oes at IWSLT 2025: Aligning Small-Scale Speech and Language Models for Speech-to-Text Learning","created":"2025-06-20","cited_by_count":0,"area":null},{"id":"2506.21990","title":"Analyzing and Fine-Tuning Whisper Models for Multilingual Pilot Speech Transcription in the Cockpit","created":"2025-06-27","cited_by_count":0,"area":null},{"id":"2509.19271","title":"WolBanking77: Wolof Banking Speech Intent Classification Dataset","created":"2025-09-23","cited_by_count":0,"area":null},{"id":"2603.14779","title":"Vietnamese Automatic Speech Recognition: A Revisit","created":"2026-03-16","cited_by_count":0,"area":null},{"id":"2605.10199","title":"How Should LLMs Listen While Speaking? A Study of User-Stream Routing in Full-Duplex Spoken Dialogue","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2605.12387","title":"A Semi-Supervised Framework for Speech Confidence Detection using Whisper","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2606.22473","title":"Interleaved Speech Language Models Latently Work In Text","created":"2026-06-21","cited_by_count":0,"area":null},{"id":"2606.28728","title":"Improving Large-Scale Weakly Supervised ASR by Filtering and Selection","created":"2026-06-27","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":"2607.10371","title":"GigaAM Multilingual: Foundation Model for Underrepresented Languages","created":"2026-07-11","cited_by_count":0,"area":null},{"id":"2608.22908","title":"Do Spoken Language Models Hear Speech as They Read Text? Bridging Structural Gaps Between Speech and Text","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2609.27980","title":"Six Layers Less: Encoder Pruning for Whisper with Label-Free Recovery","created":"2026-09-23","cited_by_count":0,"area":null},{"id":"2609.28758","title":"BiMamba2 Masked Discrete-Unit Prediction for Multilingual Speech Representation for Unsupervised Speech in the Wild Challenge","created":"2026-09-23","cited_by_count":0,"area":"ssm"},{"id":"2609.32082","title":"mu-bench: A Multilingual Utterance Transcription Benchmark","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2609.32560","title":"How to Reduce Whisper Hallucination","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.33650","title":"FuseAlign: Forced Alignment in the Wild","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2610.13447","title":"O\\'ido: Open-Vocabulary Speech Recognition on a $5 Microcontroller without a Neural Accelerator","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":"100"}