Text-Dependent Speaker Recognition Using DTW and State-Dependent Parameter Weighting Method of HMM

DTW 와 HMM의 상태별 파라미터 가중 기법을 이용한 문맥 종속형 화자인식

In this paper, the speaker-recognition process based on both DTW and discrete HMM was performed using the method to evaluate state-dependent parameter weighting from training data so as the personal audio-characteristics are to be well reflected. In the suggested method below, we found the optimal state sequence using the Viterbi algorithm. The optimal path could be evaluated after comparing the sequence of base pattern which already have, with that of the other patterns. After that the frame of which the pattern was matched with the base pattern in the same state are to be found so that the reference pattern can be gained by weighting on the numbers of matched frames.