@inproceedings{hou2021cross-domain,
author = {Hou, Wenxin and Wang, Jindong and Tan, Xu and Qin, Tao and Shinozaki, Takahiro},
title = {Cross-domain Speech Recognition with Unsupervised Character-level Distribution Matching},
booktitle = {Interspeech 2021},
year = {2021},
month = {April},
abstract = {End-to-end automatic speech recognition (ASR) can achieve promising performance with large-scale training data. However, it is known that domain mismatch between training and testing data often leads to a degradation of recognition accuracy. In this work, we focus on the unsupervised domain adaptation for ASR and propose CMatch, a Character-level distribution matching method to perform fine-grained adaptation between each character in two domains. First, to obtain labels for the features belonging to each character, we achieve frame-level label assignment using the Connectionist Temporal Classification (CTC) pseudo labels. Then, we match the character-level distributions using Maximum Mean Discrepancy. We train our algorithm using the self-training technique. Experiments on the Libri-Adapt dataset show that our proposed approach achieves 14.39% and 16.50% relative Word Error Rate (WER) reduction on both cross-device and cross-environment ASR. We also comprehensively analyze the different strategies for frame-level label assignment and Transformer adaptations.},
url = {http://approjects.co.za/?big=en-us/research/publication/cross-domain-speech-recognition-with-unsupervised-character-level-distribution-matching/},
}