This paper proposes an HMM training technique using multiple phonetic decision trees and evaluates it in speech recognition. In the use of context dependent models, the decision tree based context clustering is applied to find a parameter tying structure. However, the clustering is usually performed based on statistics of HMM state sequences which are obtained by unreliable models without conte...

How to do parameter tying and how this relates to Backprop through time.

This paper proposes a novel speaker adaptation method that exibly controls state-sharing of HMMs according to the amount of adaptation data. In our scheme, acoustic modeling is combined with adaptation to e ciently utilize the acoustic models sharing characteristics for adaptation. The shared-state set of HMMs is determined by using tree-structured shared-state HMMs created from the history rec...

In this paper, we experiment with decision trees as replacements for Gaussian mixture models to compute the observation likelihoods for a given HMM state in a speech recognition system. Decision trees have a number of advantageous properties, such as that they do not impose restrictions on the number or types of features, and that they automatically perform feature selection. In fact, due to th...

Using speech as the input of the human-machine interface, we need to consider the effect of the pronunciation variations on speech recognition. We usually use the speaker adaptation and speech adaptation technique to solve above problem, but the result of accent speech recognition is not good enough. This paper presents a framework to combine two phone models to reconstruct acoustic model. Firs...