Student-Teacher Learning for BLSTM Mask-based Speech Enhancement
This addresses speech distortion in single-channel enhancement for speech recognition, but it is incremental as it adapts an existing multichannel method.
The paper tackles the problem of single-channel speech enhancement by proposing a student-teacher learning paradigm, where a student network with single-channel input mimics soft masks from a teacher network using beamformed multichannel input, resulting in improved ASR performance on CHiME-4 data.
Spectral mask estimation using bidirectional long short-term memory (BLSTM) neural networks has been widely used in various speech enhancement applications, and it has achieved great success when it is applied to multichannel enhancement techniques with a mask-based beamformer. However, when these masks are used for single channel speech enhancement they severely distort the speech signal and make them unsuitable for speech recognition. This paper proposes a student-teacher learning paradigm for single channel speech enhancement. The beamformed signal from multichannel enhancement is given as input to the teacher network to obtain soft masks. An additional cross-entropy loss term with the soft mask target is combined with the original loss, so that the student network with single-channel input is trained to mimic the soft mask obtained with multichannel input through beamforming. Experiments with the CHiME-4 challenge single channel track data shows improvement in ASR performance.