We investigate the effectiveness of generative adversarial networks (GANs)
for speech enhancement, in the context of improving noise robustness of
automatic speech recognition (ASR) systems. Prior work demonstrates that GANs
can effectively suppress additive noise in raw waveform speech signals,
improving perceptual quality metrics; however this technique was not justified
in the context of ASR. In this work, we conduct a detailed study to measure the
effectiveness of GANs in enhancing speech contaminated by both additive and
reverberant noise. Motivated by recent advances in image processing, we propose
operating GANs on log-Mel filterbank spectra instead of waveforms, which
requires less computation and is more robust to reverberant noise. While GAN
enhancement improves the performance of a clean-trained ASR system on noisy
speech, it falls short of the performance achieved by conventional multi-style
training (MTR). By appending the GAN-enhanced features to the noisy inputs and
retraining, we achieve a 7% WER improvement relative to the MTR system.

本文研究生成对抗网络（Generative Adversarial Networks, GANs）在语音增强领域中的有效性，通过操作 GANs 在 log-Mel 滤波器组上而非波形上以增强受到加性和混响噪声污染的语音信号，并通过将 GAN 增强特征附加至含噪输入并再次训练而获得了相对于传统多风格训练（Multi-style Training, MTR）系统的 7％错误率改进。