{"total":20,"rows":[{"id":"2602.12160","title":"DreamID-Omni: Unified Framework for Controllable Human-Centric Audio-Video Generation","created":"2026-02-12","cited_by_count":20,"area":null},{"id":"2603.18090","title":"MOSS-TTS Technical Report","created":"2026-03-18","cited_by_count":14,"area":null},{"id":"2606.01802","title":"MOSS-Audio Technical Report","created":"2026-06-01","cited_by_count":11,"area":null},{"id":"2603.28086","title":"MOSS-VoiceGenerator: Create Realistic Voices with Natural Language Descriptions","created":"2026-03-30","cited_by_count":3,"area":null},{"id":"2507.18161","title":"Recent Trends in Distant Conversational Speech Recognition: A Review of CHiME-7 and 8 DASR Challenges","created":"2025-07-24","cited_by_count":2,"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":"2511.22696","title":"Probabilistic Fusion and Calibration of Neural Speaker Diarization Models","created":"2025-11-27","cited_by_count":1,"area":null},{"id":"2601.19946","title":"MK-SGC-SC: Multiple Kernel Guided Sparse Graph Construction in Spectral Clustering for Unsupervised Speaker Diarization","created":"2026-01-24","cited_by_count":1,"area":null},{"id":"2602.23070","title":"Make It Hard to Hear, Easy to Learn: Long-Form Bengali ASR and Speaker Diarization via Extreme Augmentation and Perfect Alignment","created":"2026-02-26","cited_by_count":1,"area":null},{"id":"2603.02030","title":"TCG CREST System Description for the DISPLACE-M Challenge","created":"2026-03-02","cited_by_count":0,"area":null},{"id":"2603.03158","title":"An Investigation Into Various Approaches For Bengali Long-Form Speech Transcription and Bengali Speaker Diarization","created":"2026-03-03","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":"2604.05830","title":"\"OK Aura, Be Fair With Me\": Demographics-Agnostic Training for Bias Mitigation in Wake-up Word Detection","created":"2026-04-07","cited_by_count":0,"area":null},{"id":"2607.12468","title":"An Omnilingual-ASR-Based Speech-LLM System for the 2nd MLC-SLM Challenge","created":"2026-07-14","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":"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":"2609.39162","title":"Training-Free Affinity Fusion of Neural and Embedding-Based Speaker Diarization","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2609.39344","title":"Who Said What, and Will It Be Remembered? Evaluating Persistent Speaker Attribution Across Meetings","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.02941","title":"FASTDIAR: Frame-level speaker encoder for Streaming Diarization","created":"2026-10-02","cited_by_count":0,"area":null}],"next_cursor":null}