{"total":17,"rows":[{"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":"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":"2103.08393","title":"Wav2vec-C: A Self-supervised Model for Speech Representation Learning","created":"2021-03-09","cited_by_count":25,"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":"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":"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":"2608.25218","title":"TurnBench: A Multi-Domain Benchmark for Turn-Taking Dynamics in Spoken Dialogue","created":"2026-08-25","cited_by_count":7,"area":null},{"id":"2406.18972","title":"Applying LLMs for Rescoring N-best ASR Hypotheses of Casual Conversations: Effects of Domain Adaptation and Context Carry-over","created":"2024-06-27","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":"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":"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":"2607.08111","title":"PS4: Proxy-Supervised Joint Training for Real Target Speaker Extraction","created":"2026-07-09","cited_by_count":1,"area":null},{"id":"2603.22709","title":"Who Spoke What When? Evaluating Spoken Language Models for Conversational ASR with Semantic and Overlap-Aware Metrics","created":"2026-03-24","cited_by_count":0,"area":null},{"id":"2604.15929","title":"MUSCAT: MUltilingual, SCientific ConversATion Benchmark","created":"2026-04-17","cited_by_count":0,"area":null},{"id":"2606.17542","title":"Evaluating Large Language Models Abilities for Addressee, Turn-change, and Next Speaker Prediction in Meetings","created":"2026-06-16","cited_by_count":0,"area":null},{"id":"2608.01724","title":"TIDES: A Longitudinal Bilingual Dataset for Modeling Multi-Party Social Dynamics","created":"2026-08-03","cited_by_count":0,"area":null}],"next_cursor":null}