Deep Q-network-based noise suppression for robust speech recognition

Authors

TAE-JUN PARK
JOON-HYUK CHANG

DOI

10.3906/elk-2011-144

Abstract

This study develops the deep Q-network (DQN)-based noise suppression for robust speech recognition purposes under ambient noise. We thus design a reinforcement algorithm that combines DQN training with a deep neural networks (DNN) to let reinforcement learning (RL) work for complex and high dimensional environments like speech recognition. For this, we elaborate on the DQN training to choose the best action that is the quantized noise suppression gain by the observation of noisy speech signal with the rewards of DQN including both the word error rate (WER) and objective speech quality measure. Experiments demonstrate that the proposed algorithm improves speech recognition in various noisy conditions while reducing the computational burden compared to the DNN-based noise suppression method.

Keywords

Deep Q-network, reinforcement learning, speech recognition, noise suppression, speech enhancement, deep neural network

First Page

2362

Last Page

2373

Recommended Citation

PARK, TAE-JUN and CHANG, JOON-HYUK (2021) "Deep Q-network-based noise suppression for robust speech recognition," Turkish Journal of Electrical Engineering and Computer Sciences: Vol. 29: No. 5, Article 7. https://doi.org/10.3906/elk-2011-144
Available at: https://journals.tubitak.gov.tr/elektrik/vol29/iss5/7