Student-Teacher Learning for BLSTM Mask-based Speech Enhancement

Aswin Shanmugam Subramanian, Szu-Jui Chen, Shinji Watanabe

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.

 DOI: 10.21437/Interspeech.2018-2440

Cite as: Subramanian, A.S., Chen, S., Watanabe, S. (2018) Student-Teacher Learning for BLSTM Mask-based Speech Enhancement. Proc. Interspeech 2018, 3249-3253, DOI: 10.21437/Interspeech.2018-2440.

  author={Aswin Shanmugam Subramanian and Szu-Jui Chen and Shinji Watanabe},
  title={Student-Teacher Learning for BLSTM Mask-based Speech Enhancement},
  booktitle={Proc. Interspeech 2018},