Loading [a11y]/accessibility-menu.js
Exploring Practical Aspects of Neural Mask-Based Beamforming for Far-Field Speech Recognition | IEEE Conference Publication | IEEE Xplore

Exploring Practical Aspects of Neural Mask-Based Beamforming for Far-Field Speech Recognition


Abstract:

This work examines acoustic beamformers employing neural networks (NNs) for mask prediction as front -end for automatic speech recognition (ASR) systems for practical sce...Show More

Abstract:

This work examines acoustic beamformers employing neural networks (NNs) for mask prediction as front -end for automatic speech recognition (ASR) systems for practical scenarios like voice-enabled home devices. To test the versatility of the mask predicting network, the system is evaluated with different recording hardware, different microphone array designs, and different acoustic models of the downstream ASR system. Significant gains in recognition accuracy are obtained in all configurations despite the fact that the NN had been trained on mismatched data. Unlike previous work, the NN is trained on a feature level objective, which gives some performance advantage over a mask related criterion. Furthermore, different approaches for realizing online, or adaptive, NN-based beamforming are explored, where the online algorithms still show significant gains compared to the baseline performance.
Date of Conference: 15-20 April 2018
Date Added to IEEE Xplore: 13 September 2018
ISBN Information:
Electronic ISSN: 2379-190X
Conference Location: Calgary, AB, Canada

References

References is not available for this document.