NTT Multi-Speaker ASR System for the DASR Task of CHiME-8 Challenge

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

doi:10.21437/CHiME.2024-15

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, Alexis Plaquet, Takanori Ashihara, Tsubasa Ochiai, Masato Mimura, Marc Delcroix, Tomohiro Nakatani, Taichi Asami, Shoko Araki

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 multichannel 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 22.0 % on the dev set, which is a more than 60% relative improvement over the baseline.