Subspace Gaussian Mixture Models for speech recognition

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.


Published in:
2010 IEEE International Conference on Acoustics, Speech and Signal Processing, 4330-4333
Presented at:
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2010
Year:
2010
Keywords:
Laboratories:




 Record created 2014-11-19, last modified 2018-03-17


Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)