Lorenz Diener, Matthias Janke, Tanja Schultz
Reference:
Codebook Clustering for Unit Selection Based EMG-to-Speech Conversion (Lorenz Diener, Matthias Janke, Tanja Schultz), at INTERSPEECH 2015 - 16th Annual Conference of the International Speech Communication Association, September 2015
Bibtex Entry:
@inproceedings{diener2015codebook,
title = {Codebook Clustering for Unit Selection Based EMG-to-Speech Conversion},
author = {Diener, Lorenz and Janke, Matthias and Schultz, Tanja},
year = 2015,
month = sep,
booktitle = {{INTERSPEECH} 2015 - 16th Annual Conference of the International Speech
Communication Association},
pages = {2420--2424},
doi = {10.21437/Interspeech.2015-523},
abstract = {This paper reports on our recent advances in using Unit Selection to directly
synthesize speech from facial surface electromyographic (EMG) signals generated by movement of
the articulatory muscles during speech production. We achieve a robust Unit Selection mapping by
using a more sophisticated unit codebook. This codebook is generated from a set of base units
using a two stage unit clustering process. The units are first clustered based on the audio and
afterwards on the EMG feature vectors they cover, and a new codebook is generated using these
cluster assignments. We evaluate different cluster counts for both stages and revisit our
evaluation of unit sizes in light of this clustering approach. Our final system achieves a
significantly better Mel-Cepstral distortion score than the Unit Selection based EMG-to-Speech
conversion system from our previous work while, due to the reduced codebook size, taking less
time to perform the conversion.},
keywords = {electromyography, silent speech interface, unit selection},
url = {https://halcy.de/cites/pdf/diener2015codebook.pdf},
}