@inproceedings{meng2018speaker-invariant,
author = {Meng, Zhong and Li, Jinyu and Chen, Zhuo and Zhao, Yong and Mazalov, Vadim and Gong, Yifan and Juang, Biing-Hwang (Fred)},
title = {Speaker-Invariant Training via Adversarial Learning},
booktitle = {ICASSP},
year = {2018},
month = {April},
abstract = {We propose a novel adversarial multi-task learning scheme, aiming at actively curtailing the inter-talker feature variability while maximizing its senone discriminability so as to enhance the performance of a deep neural network (DNN) based ASR system. We call the scheme speaker-invariant training (SIT). In SIT, a DNN acoustic model and a speaker classifier network are jointly optimized to minimize the senone (tied triphone state) classification loss, and simultaneously mini-maximize the speaker classification loss. A speaker-invariant and senone-discriminative deep feature is learned through this adversarial multi-task learning. With SIT, a canonical DNN acoustic model with significantly reduced variance in its output probabilities is learned with no explicit speaker-independent (SI) transformations or speaker-specific representations used in training or testing. Evaluated on the CHiME-3 dataset, the SIT achieves 4.99% relative word error rate (WER) improvement over the conventional SI acoustic model. With additional unsupervised speaker adaptation, the speaker-adapted (SA) SIT model achieves 4.86% relative WER gain over the SA SI acoustic model.},
publisher = {IEEE},
url = {http://approjects.co.za/?big=en-us/research/publication/speaker-invariant-training-via-adversarial-learning/},
}