{"total":132,"rows":[{"id":"2212.04356","title":"Robust Speech Recognition via Large-Scale Weak Supervision","created":"2022-12-06","cited_by_count":4057,"area":null},{"id":"2101.09624","title":"A Review of Speaker Diarization: Recent Advances with Deep Learning","created":"2021-01-24","cited_by_count":124,"area":null},{"id":"2109.13226","title":"BigSSL: Exploring the Frontier of Large-Scale Semi-Supervised Learning for Automatic Speech Recognition","created":"2021-09-27","cited_by_count":88,"area":null},{"id":"2104.02133","title":"SpeechStew: Simply Mix All Available Speech Recognition Data to Train One Large Neural Network","created":"2021-04-05","cited_by_count":83,"area":null},{"id":"2201.01763","title":"Robust Self-Supervised Audio-Visual Speech Recognition","created":"2022-01-05","cited_by_count":75,"area":null},{"id":"2104.11348","title":"Earnings-21: A Practical Benchmark for ASR in the Wild","created":"2021-04-22","cited_by_count":62,"area":null},{"id":"2203.16844","title":"Open Source MagicData-RAMC: A Rich Annotated Mandarin Conversational(RAMC) Speech Dataset","created":"2022-03-31","cited_by_count":40,"area":null},{"id":"2202.00842","title":"Streaming Multi-Talker ASR with Token-Level Serialized Output Training","created":"2022-02-02","cited_by_count":37,"area":null},{"id":"2104.02128","title":"End-to-End Speaker-Attributed ASR with Transformer","created":"2021-04-05","cited_by_count":35,"area":null},{"id":"2103.16776","title":"Large-Scale Pre-Training of End-to-End Multi-Talker ASR for Meeting Transcription with Single Distant Microphone","created":"2021-03-31","cited_by_count":33,"area":null},{"id":"2107.04174","title":"EasyCom: An Augmented Reality Dataset to Support Algorithms for Easy Communication in Noisy Environments","created":"2021-07-09","cited_by_count":31,"area":null},{"id":"2406.08402","title":"Understanding Sounds, Missing the Questions: The Challenge of Object Hallucination in Large Audio-Language Models","created":"2024-06-12","cited_by_count":31,"area":null},{"id":"2307.11394","title":"MeetEval: A Toolkit for Computation of Word Error Rates for Meeting Transcription Systems","created":"2023-07-21","cited_by_count":28,"area":null},{"id":"2110.03151","title":"Transcribe-to-Diarize: Neural Speaker Diarization for Unlimited Number of Speakers using End-to-End Speaker-Attributed ASR","created":"2021-10-07","cited_by_count":22,"area":null},{"id":"2306.13734","title":"The CHiME-7 DASR Challenge: Distant Meeting Transcription with Multiple Devices in Diverse Scenarios","created":"2023-06-23","cited_by_count":22,"area":null},{"id":"2401.08887","title":"NOTSOFAR-1 Challenge: New Datasets, Baseline, and Tasks for Distant Meeting Transcription","created":"2024-01-16","cited_by_count":21,"area":null},{"id":"2401.03506","title":"DiarizationLM: Speaker Diarization Post-Processing with Large Language Models","created":"2024-01-07","cited_by_count":16,"area":null},{"id":"2107.01545","title":"Towards Neural Diarization for Unlimited Numbers of Speakers Using Global and Local Attractors","created":"2021-07-04","cited_by_count":15,"area":null},{"id":"2409.06656","title":"Sortformer: A Novel Approach for Permutation-Resolved Speaker Supervision in Speech-to-Text Systems","created":"2024-09-10","cited_by_count":15,"area":null},{"id":"2203.16685","title":"Streaming Speaker-Attributed ASR with Token-Level Speaker Embeddings","created":"2022-03-30","cited_by_count":14,"area":null},{"id":"2310.01688","title":"One model to rule them all ? Towards End-to-End Joint Speaker Diarization and Speech Recognition","created":"2023-10-02","cited_by_count":12,"area":null},{"id":"2403.04245","title":"A Study of Dropout-Induced Modality Bias on Robustness to Missing Video Frames for Audio-Visual Speech Recognition","created":"2024-03-07","cited_by_count":12,"area":null},{"id":"2203.15974","title":"Multi-scale Speaker Diarization with Dynamic Scale Weighting","created":"2022-03-30","cited_by_count":11,"area":null},{"id":"2305.18747","title":"Adapting Multi-Lingual ASR Models for Handling Multiple Talkers","created":"2023-05-30","cited_by_count":11,"area":null},{"id":"2409.09785","title":"Large Language Model Based Generative Error Correction: A Challenge and Baselines for Speech Recognition, Speaker Tagging, and Emotion Recognition","created":"2024-09-15","cited_by_count":11,"area":null},{"id":"2107.02852","title":"A Comparative Study of Modular and Joint Approaches for Speaker-Attributed ASR on Monaural Long-Form Audio","created":"2021-07-06","cited_by_count":10,"area":null},{"id":"2408.17431","title":"Advancing Multi-talker ASR Performance with Large Language Models","created":"2024-08-30","cited_by_count":10,"area":null},{"id":"2107.01091","title":"CrowdSpeech and VoxDIY: Benchmark Datasets for Crowdsourced Audio Transcription","created":"2021-07-02","cited_by_count":9,"area":null},{"id":"2408.09215","title":"Generating Data with Text-to-Speech and Large-Language Models for Conversational Speech Recognition","created":"2024-08-17","cited_by_count":9,"area":null},{"id":"2206.02432","title":"Online Neural Diarization of Unlimited Numbers of Speakers Using Global and Local Attractors","created":"2022-06-06","cited_by_count":8,"area":null},{"id":"2212.11377","title":"ReVISE: Self-Supervised Speech Resynthesis with Visual Input for Universal and Generalized Speech Enhancement","created":"2022-12-21","cited_by_count":8,"area":null},{"id":"2405.14161","title":"Self-Taught Recognizer: Toward Unsupervised Adaptation for Speech Foundation Models","created":"2024-05-23","cited_by_count":8,"area":null},{"id":"2406.04927","title":"LLM-based speaker diarization correction: A generalizable approach","created":"2024-06-07","cited_by_count":8,"area":null},{"id":"2510.16567","title":"Hallucination Benchmark for Speech Foundation Models","created":"2025-10-18","cited_by_count":8,"area":null},{"id":"2101.01853","title":"Hypothesis Stitcher for End-to-End Speaker-attributed ASR on Long-form Multi-talker Recordings","created":"2021-01-06","cited_by_count":7,"area":null},{"id":"2103.10661","title":"USTC-NELSLIP System Description for DIHARD-III Challenge","created":"2021-03-19","cited_by_count":7,"area":null},{"id":"2208.13085","title":"Target Speaker Voice Activity Detection with Transformers and Its Integration with End-to-End Neural Diarization","created":"2022-08-27","cited_by_count":7,"area":null},{"id":"2209.04974","title":"VarArray Meets t-SOT: Advancing the State of the Art of Streaming Distant Conversational Speech Recognition","created":"2022-09-12","cited_by_count":7,"area":null},{"id":"2506.18623","title":"Efficient and Robust Speaker Diarization via Structured Pruning of Self-Supervised Models","created":"2025-06-23","cited_by_count":7,"area":"distill"},{"id":"2507.09318","title":"ZipVoice-Dialog: Non-Autoregressive Spoken Dialogue Generation with Flow Matching","created":"2025-07-12","cited_by_count":7,"area":"diffusion"},{"id":"2203.00725","title":"A Conformer Based Acoustic Model for Robust Automatic Speech Recognition","created":"2022-03-01","cited_by_count":6,"area":null},{"id":"2306.10608","title":"STHG: Spatial-Temporal Heterogeneous Graph Learning for Advanced Audio-Visual Diarization","created":"2023-06-18","cited_by_count":6,"area":null},{"id":"2406.08396","title":"Neural Blind Source Separation and Diarization for Distant Speech Recognition","created":"2024-06-12","cited_by_count":6,"area":null},{"id":"2406.09494","title":"The Second DISPLACE Challenge : DIarization of SPeaker and LAnguage in Conversational Environments","created":"2024-06-13","cited_by_count":6,"area":null},{"id":"2105.13802","title":"DIVE: End-to-end Speech Diarization via Iterative Speaker Embedding","created":"2021-05-28","cited_by_count":5,"area":null},{"id":"2203.16834","title":"A Comparative Study on Speaker-attributed Automatic Speech Recognition in Multi-party Meetings","created":"2022-03-31","cited_by_count":5,"area":null},{"id":"2305.13716","title":"BA-SOT: Boundary-Aware Serialized Output Training for Multi-Talker ASR","created":"2023-05-23","cited_by_count":5,"area":null},{"id":"2309.08007","title":"DiariST: Streaming Speech Translation with Speaker Diarization","created":"2023-09-14","cited_by_count":5,"area":null},{"id":"2405.15216","title":"Revisiting ASR Error Correction with Specialized Models","created":"2024-05-24","cited_by_count":5,"area":null},{"id":"2505.00059","title":"BERSting at the Screams: A Benchmark for Distanced, Emotional and Shouted Speech Recognition","created":"2025-04-30","cited_by_count":5,"area":null},{"id":"2508.05554","title":"SPGISpeech 2.0: Transcribed multi-speaker financial audio for speaker-tagged transcription","created":"2025-08-07","cited_by_count":5,"area":null},{"id":"2508.20474","title":"Unifying Diarization, Separation, and ASR with Multi-Speaker Encoder","created":"2025-08-28","cited_by_count":5,"area":null},{"id":"2601.06896","title":"TagSpeech: End-to-End Multi-Speaker ASR and Diarization with Fine-Grained Temporal Grounding","created":"2026-01-11","cited_by_count":5,"area":null},{"id":"2104.02879","title":"Adapting Speaker Embeddings for Speaker Diarisation","created":"2021-04-07","cited_by_count":4,"area":null},{"id":"2204.03232","title":"Leveraging Real Conversational Data for Multi-Channel Continuous Speech Separation","created":"2022-04-07","cited_by_count":4,"area":null},{"id":"2305.20054","title":"UNSSOR: Unsupervised Neural Speech Separation by Leveraging Over-determined Training Mixtures","created":"2023-05-31","cited_by_count":4,"area":null},{"id":"2306.12173","title":"Mixture Encoder for Joint Speech Separation and Recognition","created":"2023-06-21","cited_by_count":4,"area":null},{"id":"2311.12564","title":"Summary of the DISPLACE Challenge 2023 - DIarization of SPeaker and LAnguage in Conversational Environments","created":"2023-11-21","cited_by_count":4,"area":null},{"id":"2409.00819","title":"LibriheavyMix: A 20,000-Hour Dataset for Single-Channel Reverberant Multi-Talker Speech Separation, ASR and Speaker Diarization","created":"2024-09-01","cited_by_count":4,"area":null},{"id":"2409.20301","title":"Alignment-Free Training for Transducer-based Multi-Talker ASR","created":"2024-09-30","cited_by_count":4,"area":null},{"id":"2410.01481","title":"SonicSim: A customizable simulation platform for speech processing in moving sound source scenarios","created":"2024-10-02","cited_by_count":4,"area":null},{"id":"2411.18152","title":"MSA-ASR: Efficient Multilingual Speaker Attribution with frozen ASR Models","created":"2024-11-27","cited_by_count":4,"area":null},{"id":"2505.10975","title":"Survey of End-to-End Multi-Speaker Automatic Speech Recognition for Monaural Audio","created":"2025-05-16","cited_by_count":4,"area":null},{"id":"2505.13971","title":"The Multimodal Information Based Speech Processing (MISP) 2025 Challenge: Audio-Visual Diarization and Recognition","created":"2025-05-20","cited_by_count":4,"area":null},{"id":"2507.05724","title":"Omni-Router: Sharing Routing Decisions in Sparse Mixture-of-Experts for Speech Recognition","created":"2025-07-08","cited_by_count":4,"area":"moe"},{"id":"2510.19358","title":"M3-SLU: Evaluating Speaker-Attributed Reasoning in Multimodal Large Language Models","created":"2025-10-22","cited_by_count":4,"area":"lr"},{"id":"2510.23276","title":"A Cocktail-Party Benchmark: Multi-Modal dataset and Comparative Evaluation Results","created":"2025-10-27","cited_by_count":4,"area":null},{"id":"2104.02819","title":"Learning to Rank Microphones for Distant Speech Recognition","created":"2021-04-06","cited_by_count":3,"area":null},{"id":"2202.12719","title":"Ask2Mask: Guided Data Selection for Masked Speech Modeling","created":"2022-02-24","cited_by_count":3,"area":null},{"id":"2208.08042","title":"The Conversational Short-phrase Speaker Diarization (CSSD) Task: Dataset, Evaluation Metric and Baselines","created":"2022-08-17","cited_by_count":3,"area":null},{"id":"2211.06493","title":"Handling Trade-Offs in Speech Separation with Sparsely-Gated Mixture of Experts","created":"2022-11-11","cited_by_count":3,"area":"moe"},{"id":"2211.17094","title":"Better Transcription of UK Supreme Court Hearings","created":"2022-11-29","cited_by_count":3,"area":null},{"id":"2506.07515","title":"Speaker-Distinguishable CTC: Learning Speaker Distinction Using CTC for Multi-Talker Speech Recognition","created":"2025-06-09","cited_by_count":3,"area":null},{"id":"2510.12827","title":"Automatic Speech Recognition in the Modern Era: Architectures, Training, and Evaluation","created":"2025-10-11","cited_by_count":3,"area":null},{"id":"2111.00320","title":"Speaker conditioning of acoustic models using affine transformation for multi-speaker speech recognition","created":"2021-10-30","cited_by_count":2,"area":null},{"id":"2203.00648","title":"Measuring the Impact of Individual Domain Factors in Self-Supervised Pre-Training","created":"2022-03-01","cited_by_count":2,"area":null},{"id":"2210.10879","title":"G-Augment: Searching for the Meta-Structure of Data Augmentation Policies for ASR","created":"2022-10-19","cited_by_count":2,"area":null},{"id":"2303.12002","title":"End-to-End Integration of Speech Separation and Voice Activity Detection for Low-Latency Diarization of Telephone Conversations","created":"2023-03-21","cited_by_count":2,"area":null},{"id":"2306.10240","title":"Neural Fast Full-Rank Spatial Covariance Analysis for Blind Source Separation","created":"2023-06-17","cited_by_count":2,"area":null},{"id":"2402.00067","title":"Online speaker diarization of meetings guided by speech separation","created":"2024-01-30","cited_by_count":2,"area":null},{"id":"2408.12102","title":"Integrating Audio, Visual, and Semantic Information for Enhanced Multimodal Speaker Diarization","created":"2024-08-22","cited_by_count":2,"area":null},{"id":"2501.17304","title":"Summary of the NOTSOFAR-1 Challenge: Highlights and Learnings","created":"2025-01-28","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":"2502.13446","title":"Adopting Whisper for Confidence Estimation","created":"2025-02-19","cited_by_count":2,"area":null},{"id":"2507.08660","title":"The Impact of Automatic Speech Transcription on Speaker Attribution","created":"2025-07-11","cited_by_count":2,"area":null},{"id":"2602.04776","title":"Speaker-Aware Simulation Improves Conversational Speech Recognition","created":"2026-02-04","cited_by_count":2,"area":null},{"id":"2607.14846","title":"RW-Voice-EQ Bench: A Real World Benchmark for Evaluating Voice AI Systems","created":"2026-07-16","cited_by_count":2,"area":null},{"id":"2607.27756","title":"Cocktail-Talker: Multi-Speaker Dialog Modeling in Noisy Social Environments with Turn Action GRPO","created":"2026-07-30","cited_by_count":2,"area":null},{"id":"2203.16757","title":"Exploiting Single-Channel Speech for Multi-Channel End-to-End Speech Recognition: A Comparative Study","created":"2022-03-31","cited_by_count":1,"area":null},{"id":"2306.04054","title":"RescueSpeech: A German Corpus for Speech Recognition in Search and Rescue Domain","created":"2023-06-06","cited_by_count":1,"area":null},{"id":"2406.08914","title":"Transcription-Free Fine-Tuning of Speech Separation Models for Noisy and Reverberant Multi-Speaker Automatic Speech Recognition","created":"2024-06-13","cited_by_count":1,"area":null},{"id":"2501.08421","title":"SEAL: Speaker Error Correction using Acoustic-conditioned Large Language Models","created":"2025-01-14","cited_by_count":1,"area":null},{"id":"2505.18217","title":"ABHINAYA -- A System for Speech Emotion Recognition In Naturalistic Conditions Challenge","created":"2025-05-23","cited_by_count":1,"area":null},{"id":"2509.18722","title":"LOTUSDIS: A Thai far-field meeting corpus for robust conversational ASR","created":"2025-09-23","cited_by_count":1,"area":null},{"id":"2510.09307","title":"Target speaker anonymization in multi-speaker recordings","created":"2025-10-10","cited_by_count":1,"area":null},{"id":"2510.23320","title":"LibriConvo: Simulating Conversations from Read Literature for ASR and Diarization","created":"2025-10-27","cited_by_count":1,"area":null},{"id":"2601.19949","title":"RIR-Mega-Speech: A Reverberant Speech Corpus with Comprehensive Acoustic Metadata and Reproducible Evaluation","created":"2026-01-25","cited_by_count":1,"area":null},{"id":"2602.03285","title":"MeetBench-XL: Calibrated Multi-Dimensional Evaluation and Learned Dual-Policy Agents for Real-Time Meetings","created":"2026-02-03","cited_by_count":1,"area":null},{"id":"2607.08111","title":"PS4: Proxy-Supervised Joint Training for Real Target Speaker Extraction","created":"2026-07-09","cited_by_count":1,"area":null},{"id":"2607.23808","title":"Indic DiarBench: A Multilingual Joint Diarization and ASR Benchmark for Indian Languages","created":"2026-07-26","cited_by_count":1,"area":null}],"next_cursor":"100"}