arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2409.05554eess.AS
收藏

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

Naoyuki Kamo, Naohiro Tawara, Atsushi Ando, Takatomo Kano, Hiroshi Sato, Rintaro Ikeshita, Takafumi Moriya, Shota Horiguchi, Kohei Matsuura, Atsunori Ogawa, Ale… 展开作者

Naoyuki Kamo, Naohiro Tawara, Atsushi Ando, Takatomo Kano, Hiroshi Sato, Rintaro Ikeshita, Takafumi Moriya, Shota Horiguchi, Kohei Matsuura, Atsunori Ogawa, Alexis Plaquet, Takanori Ashihara, Tsubasa Ochiai, Masato Mimura, Marc Delcroix, Tomohiro Nakatani, Taichi Asami, Shoko Araki

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。

↑