{"total":15,"rows":[{"id":"2605.20183","title":"MSAVBench: Towards Comprehensive and Reliable Evaluation of Multi-Shot Audio-Video Generation","created":"2026-05-19","cited_by_count":10,"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":"2511.13529","title":"Toward Conversational Hungarian Speech Recognition: Introducing the BEA-Large and BEA-Dialogue Datasets","created":"2025-11-17","cited_by_count":3,"area":null},{"id":"2509.26177","title":"Benchmarking Diarization Models","created":"2025-09-30","cited_by_count":2,"area":null},{"id":"2510.03723","title":"Adapting Diarization-Conditioned Whisper for End-to-End Multi-Talker Speech Recognition","created":"2025-10-04","cited_by_count":2,"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":"2511.22696","title":"Probabilistic Fusion and Calibration of Neural Speaker Diarization Models","created":"2025-11-27","cited_by_count":1,"area":null},{"id":"2603.17769","title":"Modeling Overlapped Speech with Shuffles","created":"2026-03-18","cited_by_count":0,"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":"2603.25750","title":"Sommelier: Scalable Open Multi-turn Audio Pre-processing for Full-duplex Speech Language Models","created":"2026-03-20","cited_by_count":0,"area":null},{"id":"2607.00986","title":"Automatic Detection of Stress from Speech in the Trier Social Stress Test","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2609.20504","title":"Model-Agnostic and Language-Agnostic Voice Pipeline Improvement for the Agriculture Domain","created":"2026-09-17","cited_by_count":0,"area":null},{"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":"2610.14643","title":"AegisVox: Factorized Privacy and Clinical Preservation for Long-Form Speech","created":"2026-10-10","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}