{"total":71,"rows":[{"id":"2310.13025","title":"Powerset multi-class cross entropy loss for neural speaker diarization","created":"2023-10-19","cited_by_count":111,"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":"2507.02768","title":"DeSTA2.5-Audio: Toward General-Purpose Large Audio Language Model with Self-Generated Cross-Modal Alignment","created":"2025-07-03","cited_by_count":50,"area":"synth"},{"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":"2502.18778","title":"M2-omni: Advancing Omni-MLLM for Comprehensive Modality Support with Competitive Performance","created":"2025-02-26","cited_by_count":19,"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":"2306.15354","title":"3D-Speaker: A Large-Scale Multi-Device, Multi-Distance, and Multi-Dialect Corpus for Speech Representation Disentanglement","created":"2023-06-27","cited_by_count":15,"area":null},{"id":"2411.07076","title":"StoryTeller: Improving Long Video Description through Global Audio-Visual Character Identification","created":"2024-11-11","cited_by_count":15,"area":"mllm"},{"id":"2507.05727","title":"ContextASR-Bench: A Massive Contextual Speech Recognition Benchmark","created":"2025-07-08","cited_by_count":15,"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":"2305.18747","title":"Adapting Multi-Lingual ASR Models for Handling Multiple Talkers","created":"2023-05-30","cited_by_count":11,"area":null},{"id":"2401.04152","title":"Cross-Speaker Encoding Network for Multi-Talker Speech Recognition","created":"2024-01-08","cited_by_count":9,"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":"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":"2305.12927","title":"Exploring Speaker-Related Information in Spoken Language Understanding for Better Speaker Diarization","created":"2023-05-22","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":"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":"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":"2409.12388","title":"Disentangling Speakers in Multi-Talker Speech Recognition with Speaker-Aware CTC","created":"2024-09-19","cited_by_count":4,"area":null},{"id":"2410.06459","title":"Mamba-based Segmentation Model for Speaker Diarization","created":"2024-10-09","cited_by_count":4,"area":"ssm"},{"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":"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":"2202.01614","title":"The RoyalFlush System of Speech Recognition for M2MeT Challenge","created":"2022-02-03","cited_by_count":3,"area":null},{"id":"2202.04261","title":"The Volcspeech system for the ICASSP 2022 multi-channel multi-party meeting transcription challenge","created":"2022-02-09","cited_by_count":3,"area":null},{"id":"2202.04814","title":"Royalflush Speaker Diarization System for ICASSP 2022 Multi-channel Multi-party Meeting Transcription Challenge","created":"2022-02-10","cited_by_count":3,"area":null},{"id":"2303.13939","title":"MUG: A General Meeting Understanding and Generation Benchmark","created":"2023-03-24","cited_by_count":3,"area":null},{"id":"2403.06570","title":"Improving Speaker Assignment in Speaker-Attributed ASR for Real Meeting Applications","created":"2024-03-11","cited_by_count":3,"area":null},{"id":"2507.16136","title":"SDBench: A Comprehensive Benchmark Suite for Speaker Diarization","created":"2025-07-22","cited_by_count":3,"area":null},{"id":"2603.00595","title":"UNICBench: UNIfied Counting Benchmark for MLLM","created":"2026-02-28","cited_by_count":3,"area":"mllm"},{"id":"2608.10878","title":"X2-Turn: Frame-Synchronous Dual-Head Modeling for Joint Streaming ASR and Turn State Prediction","created":"2026-08-11","cited_by_count":3,"area":null},{"id":"2203.09767","title":"Speaker Embedding-aware Neural Diarization: an Efficient Framework for Overlapping Speech Diarization in Meeting Scenarios","created":"2022-03-18","cited_by_count":2,"area":null},{"id":"2307.13012","title":"Joint speech and overlap detection: a benchmark over multiple audio setup and speech domains","created":"2023-07-24","cited_by_count":2,"area":null},{"id":"2408.09688","title":"Recording for Eyes, Not Echoing to Ears: Contextualized Spoken-to-Written Conversion of ASR Transcripts","created":"2024-08-19","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":"2509.26177","title":"Benchmarking Diarization Models","created":"2025-09-30","cited_by_count":2,"area":null},{"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":"2609.25611","title":"Qwen3.8-Omni: Towards Native Omni-Modal Agents","created":"2026-09-22","cited_by_count":2,"area":"agents"},{"id":"2210.14653","title":"TSUP Speaker Diarization System for Conversational Short-phrase Speaker Diarization Challenge","created":"2022-10-26","cited_by_count":1,"area":null},{"id":"2309.08454","title":"Combining TF-GridNet and Mixture Encoder for Continuous Speech Separation for Meeting Transcription","created":"2023-09-15","cited_by_count":1,"area":null},{"id":"2406.03251","title":"ASoBO: Attentive Beamformer Selection for Distant Speaker Diarization in Meetings","created":"2024-06-05","cited_by_count":1,"area":null},{"id":"2409.15885","title":"On the calibration of powerset speaker diarization models","created":"2024-09-24","cited_by_count":1,"area":null},{"id":"2505.23207","title":"Towards Robust Overlapping Speech Detection: A Speaker-Aware Progressive Approach Using WavLM","created":"2025-05-29","cited_by_count":1,"area":null},{"id":"2509.10143","title":"Error Analysis in a Modular Meeting Transcription System","created":"2025-09-12","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":"2603.09556","title":"ALARM: Audio-Language Alignment for Reasoning Models","created":"2026-03-10","cited_by_count":1,"area":"lr"},{"id":"2605.30899","title":"A Unified and Reproducible Experimentation Framework for Speech Understanding","created":"2026-05-29","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},{"id":"2609.36903","title":"MultiTalk: Scaling Full-Duplex Speech Models to Long, Multi-Party, Bilingual Conversation","created":"2026-09-29","cited_by_count":1,"area":null},{"id":"2202.04855","title":"The USTC-Ximalaya system for the ICASSP 2022 multi-channel multi-party meeting transcription (M2MeT) challenge","created":"2022-02-10","cited_by_count":0,"area":null},{"id":"2303.16763","title":"Meeting Action Item Detection with Regularized Context Modeling","created":"2023-03-27","cited_by_count":0,"area":null},{"id":"2410.21849","title":"Joint Beamforming and Speaker-Attributed ASR for Real Distant-Microphone Meeting Transcription","created":"2024-10-29","cited_by_count":0,"area":null},{"id":"2502.16584","title":"Audio-FLAN: An Instruction-Following Dataset for Unified Audio Understanding and Generation of Speech, Music, and Sound","created":"2025-02-23","cited_by_count":0,"area":null},{"id":"2507.21642","title":"Whilter: A Whisper-based Data Filter for \"In-the-Wild\" Speech Corpora Using Utterance-level Multi-Task Classification","created":"2025-07-29","cited_by_count":0,"area":null},{"id":"2601.18037","title":"SpatialEmb: Extract and Encode Spatial Information for 1-Stage Multi-channel Multi-speaker ASR on Arbitrary Microphone Arrays","created":"2026-01-25","cited_by_count":0,"area":null},{"id":"2601.22792","title":"CALM: Joint Contextual Acoustic-Linguistic Modeling for Personalization of Multi-Speaker ASR","created":"2026-01-30","cited_by_count":0,"area":null},{"id":"2603.12837","title":"Mask2Flow-TSE: Two-Stage Target Speaker Extraction with Masking and Flow Matching","created":"2026-03-13","cited_by_count":0,"area":"diffusion"},{"id":"2606.25959","title":"SE-AGCNet: An End-to-End Framework for Joint Speech Enhancement and Loudness Control in Meeting Scenarios","created":"2026-06-24","cited_by_count":0,"area":null},{"id":"2608.11898","title":"On-Policy Self-Distillation for Multi-Dialect ASR: Mastering Dialects, Retaining Mandarin","created":"2026-08-12","cited_by_count":0,"area":"distill"},{"id":"2608.24048","title":"Don't Just Listen, Try Planning: Graph-based Retrieval-Generation Agent for Long-form Audio Meeting Understanding","created":"2026-08-25","cited_by_count":0,"area":"agents"},{"id":"2609.08672","title":"X2Streaming-ASR: wait when uncertain, emit when ready for streaming ASR","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2609.12154","title":"Neural Multichannel Distant Speaker Diarization with Heavy-tailed Source Separation Model","created":"2026-09-10","cited_by_count":0,"area":null},{"id":"2609.20833","title":"Transsion's Speaker-Attributed Multilingual ASR System for the MLC-SLM 2026 Challenge","created":"2026-07-24","cited_by_count":0,"area":null},{"id":"2609.30439","title":"Inference-Time Target Speaker Unlearning in LLM-Based Automatic Speech Recognition","created":"2026-09-24","cited_by_count":0,"area":"safety"},{"id":"2610.08828","title":"When Forgetting Looks Like Improvement: Metric Masking in Streaming Diarizer Adaptation and the Price of Rehearsal","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2610.20327","title":"Anuvani-Diarization: Zero Shot Speaker Diarization and Annotation Conventions Across 22 Languages","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}