Multi-Task Autoencoder for Noise-Robust Speech Recognition

Haoyi Zhang; Conggui Liu; Nakamasa Inoue; Koichi Shinoda

ICASSP 2018accepted0 citations

Multi-Task Autoencoder for Noise-Robust Speech Recognition

Haoyi Zhang, Conggui Liu, Nakamasa Inoue, Koichi Shinoda

Abstract

For speech recognition in noisy environments, we propose a multi-task autoencoder which estimates not only clean speech features but also noise features from noisy speech. We introduce the deSpeeching autoencoder, which excludes speech signals from noisy speech, and combine it with the conventional denoising autoencoder to form a unified multi-task au-toencoder (MTAE). We evaluate it using the Aurora 2 dataset and CHIME 3 dataset. It reduced WER by 15.7% from the conventional denoising autoencoder in the Aurora 2 test set A.

BibTeX

@inproceedings{icassp2018_multitaskautoenc,
  title = {Multi-Task Autoencoder for Noise-Robust Speech Recognition},
  author = {Haoyi Zhang and Conggui Liu and Nakamasa Inoue and Koichi Shinoda},
  booktitle = {ICASSP 2018},
  year = {2018}
}