Deep Learning Based Dereverberation of Temporal Envelopesfor Robust Speech Recognition
This work addresses the problem of automatic speech recognition in noisy, reverberant environments for applications like voice assistants, but it is incremental as it builds on existing envelope-based methods with neural enhancements.
The paper tackles robust speech recognition in reverberant conditions by proposing a neural model to enhance sub-band temporal envelopes for dereverberation, resulting in average relative improvements of 21% on the development set and 11% on the evaluation set in word error rates on the REVERB challenge dataset.
Automatic speech recognition in reverberant conditions is a challenging task as the long-term envelopes of the reverberant speech are temporally smeared. In this paper, we propose a neural model for enhancement of sub-band temporal envelopes for dereverberation of speech. The temporal envelopes are derived using the autoregressive modeling framework of frequency domain linear prediction (FDLP). The neural enhancement model proposed in this paper performs an envelop gain based enhancement of temporal envelopes and it consists of a series of convolutional and recurrent neural network layers. The enhanced sub-band envelopes are used to generate features for automatic speech recognition (ASR). The ASR experiments are performed on the REVERB challenge dataset as well as the CHiME-3 dataset. In these experiments, the proposed neural enhancement approach provides significant improvements over a baseline ASR system with beamformed audio (average relative improvements of 21% on the development set and about 11% on the evaluation set in word error rates for REVERB challenge dataset).