Filter-bank outputs are extended into tensors to yield precise acoustic features for speech recognition using deep neural networks (DNNs). The filter-bank outputs with temporal contexts form a time-frequency pattern of speech and have been shown to be effective as a feature parameter for DNN-based acoustic models. We attempt to project the filter-bank outputs onto a tensor product space using decorrelation followed by a bilinear map to improve acoustic separability in feature extraction. This extension makes extracting a more precise structure of the time-frequency pattern possible because the bilinear map yields higher-order correlations of features. Experimental comparisons carried out in phoneme recognition demonstrate that the tensor feature provides comparable results to the filter-bank feature, and the fusion of the two features yields an improvement over each feature.
Cite as: Ogawa, T., Ueda, K., Katsurada, K., Kobayashi, T., Nitta, T. (2015) Bilinear map of filter-bank outputs for DNN-based speech recognition. Proc. Interspeech 2015, 16-20, doi: 10.21437/Interspeech.2015-4
@inproceedings{ogawa15_interspeech,
author={Tetsuji Ogawa and Kenshiro Ueda and Kouichi Katsurada and Tetsunori Kobayashi and Tsuneo Nitta},
title={{Bilinear map of filter-bank outputs for DNN-based speech recognition}},
year=2015,
booktitle={Proc. Interspeech 2015},
pages={16--20},
doi={10.21437/Interspeech.2015-4}
}