Duration Distribution Based MFM Model for Speech Recognition

In order to overcome the defects of the duration modeling of homogeneous HMM in speech recognition and the unrealistic assumption that successive observations are independent and identically distribution within a state, Markov family model (MFM) is proposed 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 proposed 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 classical HMM recognition models