BERT for Joint Multichannel Speech Dereverberation with Spatial-aware Tasks
This addresses speech enhancement for applications like hearing aids or communication systems, but it appears incremental as it adapts existing transformer methods to a specific domain.
The paper tackled the problem of joint multichannel speech dereverberation with direction-of-arrival estimation and speech separation by proposing a method based on BERT-inspired transformers for sequence-to-sequence mapping, and experimental results demonstrated its effectiveness.
We propose a method for joint multichannel speech dereverberation with two spatial-aware tasks: direction-of-arrival (DOA) estimation and speech separation. The proposed method addresses involved tasks as a sequence to sequence mapping problem, which is general enough for a variety of front-end speech enhancement tasks. The proposed method is inspired by the excellent sequence modeling capability of bidirectional encoder representation from transformers (BERT). Instead of utilizing explicit representations from pretraining in a self-supervised manner, we utilizes transformer encoded hidden representations in a supervised manner. Both multichannel spectral magnitude and spectral phase information of varying length utterances are encoded. Experimental result demonstrates the effectiveness of the proposed method.