ICASSP
2010
IEEE
14 years 20 days ago
2010
IEEE
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...
ICASSP
2010
IEEE
14 years 20 days ago
2010
IEEE
Although research has previously been done on multilingual speech recognition, it has been found to be very difficult to improve over separately trained systems. The usual approa...