Automatic Speech Recognition: The Development of the Sphinx Recognition System
Automatic Speech Recognition: The Development of the Sphinx Recognition System
Hi-index | 0.00 |
Utterance normalization and multiple-template mathcing are two techniques that complement each other to cope with speaker variablity. This paper proposes a new method of normalization based on linear transformation of acoustic features of input speech using only one isolated utterance each of the five vowels of Japanese by each individual speaker. Experiments on isolated word recognition combining the proposed normalization method and multiple-template DP matching showed a marked improvement in the recognition rate especially for smaller numbers of templates per word. Together with the fact that this method reduces the dimension of the feature vector by a factor of 4, the results demonstrate the validity of the proposed method.