Multi-Task Autoencoder for Noise-Robust Speech Recognition
Haoyi Zhang, Conggui Liu, Nakamasa Inoue, Koichi Shinoda · 2018
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.