16 papers
DiaScriber: A Speech LLM for Joint Diarization and Transcription in Multi-Speaker Scenarios
Bingshen Mu, Xian Shi, Xiong Wang +6
Multi-speaker automatic speech recognition (MSASR) aims to jointly predict content transcriptions, speaker identities, and timestamps, thereby addressing the key question of "who s…
On-Policy Self-Distillation for Multi-Dialect ASR: Mastering Dialects, Retaining Mandarin
Shuiyuan Wang, Bingshen Mu, Pengshen Zhang +6
Recent large-scale ASR models already achieve strong Mandarin recognition accuracy and have some ability to recognize Chinese dialects. However, their dialect recognition accuracy…
Listening with Time: Precise Temporal Awareness for Long-Form Audio Understanding
Mingchen Shao, Hang Su, Wenjie Tian +6
While Large Audio Language Models (LALMs) achieve strong performance on short audio, they degrade on long-form inputs. This degradation is more severe in temporal awareness tasks,…
Semantic-Aware Interruption Detection in Spoken Dialogue Systems: Benchmark, Metric, and Model
Kangxiang Xia, Bingshen Mu, Xian Shi +2
Achieving natural full-duplex interaction in spoken dialogue systems (SDS) remains a challenge due to the difficulty of accurately detecting user interruptions. Current solutions a…
Seeing the Context: Rich Visual Context-Aware Speech Recognition via Multimodal Reasoning
Wenjie Tian, Mingchen Shao, Bingshen Mu +8
Audio-visual speech recognition (AVSR) is an extension of ASR that incorporates visual signals. Current AVSR approaches primarily focus on lip motion, largely overlooking rich cont…
LLM-ForcedAligner: A Non-Autoregressive and Accurate LLM-Based Forced Aligner for Multilingual and Long-Form Speech
Bingshen Mu, Xian Shi, Xiong Wang +3
Forced alignment (FA) predicts start and end timestamps for words or characters in speech, but existing methods are language-specific and prone to cumulative temporal shifts. The m…