A Novel Duration Model for Speech Recognition

L. Yuan and C. Wan (PRC)


Markov Family models, Hidden Markov models, Duration, Speech recognition


In order to overcome the defects of the duration modeling of homogeneous HMM in speech recognition and the unreaistic assumption that successive observations are independent and identically distribution within a state. Markov Family model (MFM), a new statistical model is introduced in this paper. Independence assumption is placed by conditional independence assumption in Markov Family model. We have successfully applied Markov Family model to speech recognition and propose duration distribution based MFM recognition model (DDBMFM) which takes duration distribution into account. The speaker independent continuous speech recognition experiments show that DDBMFMs have higher performance than DDBHMMs (duration distribution Based HMM recognition models) and standard HMM recognition models.

Important Links:

Go Back