Discriminative tonal feature extraction method in mandarin speech recognition

摘要

To utilize the supra-segmental nature of Mandarin tones, this article proposes a feature extraction method for hidden markov model (HMM) based tone modeling. The method uses linear transforms to project F_0 (fundamental frequency) features of neighboring syllables as compensations, and adds them to the original F_0 features of the current syllable. The transforms are discriminatively trained by using an objective function termed as "minimum tone error", which is a smooth approximation of tone recognition accuracy. Experiments show that the new tonal features achieve 3.82% tone recognition rate improvement, compared with the baseline, using maximum likelihood trained HMM on the normal F_0 features. Further experiments show that discriminative HMM training on the new features is 8.78% better than the baseline.