Two-Stage Enhancement of Noisy and Reverberant Microphone Array Speech for Automatic Speech Recognition Systems Trained with Only Clean Speech
Quandong Wang, Sicheng Wang, Fengpei Ge, Chang Woo Han, Jaewon Lee, Lianghao Guo, Chin‐Hui Lee · 2018
We propose a two-stage approach to enhancement of far-field microphone array speech collected in reverberant conditions corrupted by interfering speakers and noises. We intend to produce top-quality enhanced speech to be used by a black-box automatic speech recognition (ASR) system already trained with clean speech. We explore different deep neural network (DNN) architectures and the best configuration comprises two stages. First, in pre-enhancement, we utilize features in temporal context in a subset of microphones to perform enhancement. Second, in integration, we concatenate the enhanced and noisy features from all microphones to estimate anechoic speech of a reference channel as the overall output. Tested on eight speakers, each with 5 minutes of speech for DNN training, from the Wall Street Journal corpus, at a signal-to-interference-plus-noise-ratio level of 5-15dB, at a distance of l-5m and a reverberation time of 0.2-0.3s, our best 8-channel, speaker-dependent enhancement system attains a perceptual evaluation of speech quality score of 2.95, up from 2.43 for our single-channel system. Followed by speaker-independent ASR for a 230K-word recognition task, we achieve a word error rate of 6.56%, down from 17.89% for enhanced speech of the single-channel system, and from 48.47% for unprocessed noisy speech of the reference channel.