Unsupervised Domain Adaptation by Adversarial Learning for Robust Speech Recognition

2018/07/30 by Denisov, Pavel, Vu, Ngoc Thang, Font, Marc Ferras
#Artificial Intelligence (cs.AI) #Audio and Speech Processing (eess.AS) #Computation and Language (cs.CL) #FOS: Computer and information sciences #FOS: Electrical engineering #Sound (cs.SD) #electronic engineering #information engineering

paper · doi:10.48550/arxiv.1807.11284

Abstract

In this paper, we investigate the use of adversarial learning for unsupervised adaptation to unseen recording conditions, more specifically, single microphone far-field speech. We adapt neural networks based acoustic models trained with close-talk clean speech to the new recording conditions using untranscribed adaptation data. Our experimental results on Italian SPEECON data set show that our proposed method achieves 19.8% relative word error rate (WER) reduction compared to the unadapted models. Furthermore, this adaptation method is beneficial even when performed on data from another language (i.e. French) giving 12.6% relative WER reduction.

Related

• Unsupervised Adaptation with Interpretable Disentangled Representations\n for Distant Conversational Speech Recognition
• Adversarial Learning of Raw Speech Features for Domain Invariant Speech Recognition
• Unsupervised Speech Domain Adaptation Based on Disentangled Representation Learning for Robust Speech Recognition
• Unsupervised domain adaptation for speech recognition with unsupervised error correction
• Unsupervised Domain Adaptation for Robust Speech Recognition via Variational Autoencoder-Based Data Augmentation