2017
Beamnet: End-to-end training of a beamformer-supported multi-channel ASR system
ICASSP 2017accepted
This paper presents an end-to-end training approach for a beamformer-supported multi-channel ASR system. A neural network which estimates masks for a statistically optimum beamformer is jointly trained with a network for acoustic modeling. To update its parameters, we propagate the gradients from th…