Speaker adaptation using tree structured shared-state HMMs

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 recorded for acoustic model generation. The proposed method is applied to the parameter-tying and parameter-smoothing techniques. Experiments have been performed on a Japanese phoneme recognition test using continuous density mixture Gaussian HMMs. Using 50 adaptation phrases, a 42% reduction in the phoneme recognition error rate from the speaker-independent model was achieved.