May, 2023
使用旁路分离器进行多说话人重叠语音识别和说话人分离的统一建模
Unified Modeling of Multi-Talker Overlapped Speech Recognition and Diarization with a Sidecar Separator
Lingwei Meng, Jiawen Kang, Mingyu Cui, Haibin Wu, Xixin Wu...
TL;DR通过在单输出识别(ASR)模型中插入侧耳声分离器,结合说话人分离(diarization)任务,提出了一种能够同时定位多个讲话者的多讲话人重叠语音识别语音模型。