Publication Details
Subspace Gaussian mixture models for speech recognition
Burget Lukáš, doc. Ing., Ph.D. (DCGM)
Agarwal Mohit
Akyazi Pinar
Feng Kai
Ghoshal Arnab
Glembek Ondřej, Ing., Ph.D.
Goel Nagendra
Karafiát Martin, Ing., Ph.D. (DCGM)
Rastrow Ariya
Rose Richard
Schwarz Petr, Ing., Ph.D. (DCGM)
Thomas Samuel
Speech Recognition, Hidden Markov Models, Gaussian Mixture Models
The paper is on subspace Gaussian mixture models for speech recognition. We describe an acoustic modeling approach in which all phonetic states share a common GMM structure.
We describe an acoustic modeling approach in which all phonetic states share a common Gaussian Mixture Model structure, and the means and mixture weights vary in a subspace of the total parameter space. We call this a Subspace Gaussian Mixture Model (SGMM). Globally shared parameters define the subspace. This style of acoustic model allows for a much more compact representation and gives better results than a conventional modeling approach, particularly with smaller amounts of training data.
@inproceedings{BUT37026,
author="Daniel {Povey} and Lukáš {Burget} and Mohit {Agarwal} and Pinar {Akyazi} and Kai {Feng} and Arnab {Ghoshal} and Ondřej {Glembek} and Nagendra {Goel} and Martin {Karafiát} and Ariya {Rastrow} and Richard {Rose} and Petr {Schwarz} and Samuel {Thomas}",
title="Subspace Gaussian mixture models for speech recognition",
booktitle="Proc. International Conference on Acoustics, Speech, and Signal Processing",
year="2010",
journal="Proc. International Conference on Acoustics, Speech, and Signal Processing",
volume="2010",
number="3",
pages="4330--4333",
publisher="IEEE Signal Processing Society",
address="Dallas",
isbn="978-1-4244-4296-6",
issn="1520-6149",
url="http://www.fit.vutbr.cz/research/groups/speech/publi/2010/povey_icassp2010_4330.pdf"
}