Speaker Adaptation for Multichannel End-to-End Speech Recognition
Tsubasa Ochiai, Shinji Watanabe, Shigeru Katagiri, Takaaki Hori, John R. Hershey
Abstract
Recent work on multichannel end-to-end automatic speech recognition (ASR) has shown that multichannel speech enhancement and speech recognition functions can be integrated into a deep neural network (DNN)-based system, and promising experimental results have been shown using the CHiME-4 and AMI corpora. In other recent DNN-based hidden Markov model (DNN-HMM) hybrid architectures, the effectiveness of speaker adaptation has been well established. Motivated by these results, we propose a multi-path adaptation scheme for end-to-end multichannel ASR, which combines the unprocessed noisy speech features with a speech-enhanced pathway to improve upon previous end-to-end ASR approaches. Experimental results using CHiME-4 show that (1) our proposed multi-path adaptation scheme improves ASR performance and (2) adapting the encoder network is more effective than adapting the neural beamformer, attention mechanism, or decoder network.
BibTeX
@inproceedings{icassp2018_speakeradaptatio,
title = {Speaker Adaptation for Multichannel End-to-End Speech Recognition},
author = {Tsubasa Ochiai and Shinji Watanabe and Shigeru Katagiri and Takaaki Hori and John R. Hershey},
booktitle = {ICASSP 2018},
year = {2018}
}