Orthogonal gradient penalty for fast training of Wasserstein GaN based multi-task autoencoder toward robust speech recognition

Chao Yuan Kao, Sangwook Park, Alzahra Badi, David K. Han, Hanseok Ko

Research output: Contribution to journalArticle

Abstract

Performance in Automatic Speech Recognition (ASR) degrades dramatically in noisy environments. To alleviate this problem, a variety of deep networks based on convolutional neural networks and recurrent neural networks were proposed by applying L1 or L2 loss. In this Letter, we propose a new orthogonal gradient penalty (OGP) method for Wasserstein Generative Adversarial Networks (WGAN) applied to denoising and despeeching models. WGAN integrates a multi-task autoencoder which estimates not only speech features but also noise features from noisy speech. While achieving 14.1% improvement in Wasserstein distance convergence rate, the proposed OGP enhanced features are tested in ASR and achieve 9.7%, 8.6%, 6.2%, and 4.8% WER improvements over DDAE, MTAE, R-CED(CNN) and RNN models.

Original languageEnglish
Pages (from-to)1195-1198
Number of pages4
JournalIEICE Transactions on Information and Systems
VolumeE103D
Issue number5
DOIs
Publication statusPublished - 2020 May

Keywords

  • Deep learning
  • Generative adversarial networks
  • Robust speech recognition
  • Speech enhancement

ASJC Scopus subject areas

  • Software
  • Hardware and Architecture
  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering
  • Artificial Intelligence

Fingerprint Dive into the research topics of 'Orthogonal gradient penalty for fast training of Wasserstein GaN based multi-task autoencoder toward robust speech recognition'. Together they form a unique fingerprint.

  • Cite this