Investigating deep neural network based transforms of robust audio features for LVCSR
Lists
Only you see this
Abstract
Micro-modulation components such as the formant frequencies are very important characteristics of spoken speech that have allowed great performance improvements in small-vocabulary ASR tasks. Yet they have limited use in large vocabulary ASR applications. To enable the successful application, in real-life tasks, of these frequency measures, we investigate their combination with traditional features (MFCC's and PLP's) by linear (e.g. HDA), and non-linear (bottleneck MLP) feature transforms. Our experiments show that such integration, using non-linear MLP-based transforms, of micro-modulation and cepstral features greatly improves the ASR with respect to the cepstral features alone. We have applied this novel feature extraction scheme onto two very different tasks, i.e. a clean speech task (DARPA-WSJ) and a real-life, open-vocabulary, mobile search task (Speak4it <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">SM</sup> ), always reporting improved performance. We report relative error rate reduction of 15% for the Speak4it <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">SM</sup> task, and similar improvements, up to 21%, for the WSJ task.
BibTeX
@inproceedings{bocchieri2013investigating,
author = {Enrico Bocchieri and Dimitrios Dimitriadis},
title = {{Investigating deep neural network based transforms of robust audio features for LVCSR}},
booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
year = {2013},
doi = {10.1109/icassp.2013.6638960},
}Loading related content...