用于 CHiME-8 挑战赛 DASR 任务的 NTT 多说话人 ASR 系统
NTT Multi-Speaker ASR System for the DASR Task of CHiME-8 Challenge
AI总结:
本文提出面向 CHiME-8 DASR 赛道的多说话人远场 ASR 系统,融合 EEND-VC、TS-VAD、多通道说话人计数、改进 GSS 与预训练 ASR 模型,开发集 tcpWER 降至 21.3%。
摘要:
我们介绍了一套为 CHiME-8 DASR 赛道开发的远场自动语音识别(DASR)系统。该系统采用先进行说话人日志的流水线。在说话人日志方面,我们使用带向量聚类的端到端说话人日志(EEND-VC),随后通过目标说话人语音活动检测(TS-VAD)进行细化。为处理不同数量的说话人,我们开发了一种新的多通道说话人计数方法。随后,我们应用相对基线系统作出若干改进的引导源分离(GSS)。最后,我们结合由强预训练模型构建的多个系统执行 ASR。我们提出的系统在开发集上取得 21.3% 的宏 tcpWER,相对基线实现 57% 的提升。
英文摘要:
We present a distant automatic speech recognition (DASR) system developed for the CHiME-8 DASR track. It consists of a diarization first pipeline. For diarization, we use end-to-end diarization with vector clustering (EEND-VC) followed by target speaker voice activity detection (TS-VAD) refinement. To deal with various numbers of speakers, we developed a new multi-channel speaker counting approach. We then apply guided source separation (GSS) with several improvements to the baseline system. Finally, we perform ASR using a combination of systems built from strong pre-trained models. Our proposed system achieves a macro tcpWER of 21.3 % on the dev set, which is a 57 % relative improvement over the baseline.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。