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

no code implementations • 9 Sep 2024 • 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.

Action Detection Activity Detection +3

Applying LLMs for Rescoring N-best ASR Hypotheses of Casual Conversations: Effects of Domain Adaptation and Context Carry-over

no code implementations • 27 Jun 2024 • Atsunori Ogawa, Naoyuki Kamo, Kohei Matsuura, Takanori Ashihara, Takafumi Moriya, Takatomo Kano, Naohiro Tawara, Marc Delcroix

We investigate the effects of domain adaptation of the LLM and context carry-over when performing N-best rescoring.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +2

Iterative Shallow Fusion of Backward Language Model for End-to-End Speech Recognition

no code implementations • 17 Oct 2023 • Atsunori Ogawa, Takafumi Moriya, Naoyuki Kamo, Naohiro Tawara, Marc Delcroix

In experiments using an attention-based encoder-decoder ASR system, we confirmed that ISF using the PBLM shows comparable performance with SF using the FLM.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +4

Target Speech Extraction with Conditional Diffusion Model

no code implementations • 8 Aug 2023 • Naoyuki Kamo, Marc Delcroix, Tomohiro Nakatani

TSE is realized by conditioning the extraction process on a clue identifying the target speaker.

Denoising Speech Denoising +2

Learning to Enhance or Not: Neural Network-Based Switching of Enhanced and Observed Signals for Overlapping Speech Recognition

no code implementations • 11 Jan 2022 • Hiroshi Sato, Tsubasa Ochiai, Marc Delcroix, Keisuke Kinoshita, Naoyuki Kamo, Takafumi Moriya

To mitigate the degradation, we introduced a rule-based method to switch the ASR input between the enhanced and observed signals, which showed promising results.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +2

Switching Independent Vector Analysis and Its Extension to Blind and Spatially Guided Convolutional Beamforming Algorithms

no code implementations • 20 Nov 2021 • Tomohiro Nakatani, Rintaro Ikeshita, Keisuke Kinoshita, Hiroshi Sawada, Naoyuki Kamo, Shoko Araki

This paper develops a framework that can perform denoising, dereverberation, and source separation accurately by using a relatively small number of microphones.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +3

Should We Always Separate?: Switching Between Enhanced and Observed Signals for Overlapping Speech Recognition

no code implementations • 2 Jun 2021 • Hiroshi Sato, Tsubasa Ochiai, Marc Delcroix, Keisuke Kinoshita, Takafumi Moriya, Naoyuki Kamo

', we analyze ASR performance on observed and enhanced speech at various noise and interference conditions, and show that speech enhancement degrades ASR under some conditions even for overlapping speech.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +3

End-to-End Dereverberation, Beamforming, and Speech Recognition with Improved Numerical Stability and Advanced Frontend

no code implementations • 23 Feb 2021 • Wangyou Zhang, Christoph Boeddeker, Shinji Watanabe, Tomohiro Nakatani, Marc Delcroix, Keisuke Kinoshita, Tsubasa Ochiai, Naoyuki Kamo, Reinhold Haeb-Umbach, Yanmin Qian

Recently, the end-to-end approach has been successfully applied to multi-speaker speech separation and recognition in both single-channel and multichannel conditions.

Action Detection Activity Detection +4