Proposes multichannel Itakura-Saito divergence losses for training DNN mask estimators used in mask-based beamforming for supervised speech source separation.
Deep beam- forming networks for multi-channel speech recognition,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SD 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Multichannel Loss Function for Supervised Speech Source Separation by Mask-based Beamforming
Proposes multichannel Itakura-Saito divergence losses for training DNN mask estimators used in mask-based beamforming for supervised speech source separation.