A segment-based C0 adaptation scheme for PMC-based noisy Mandarin speech recognition

A segment-based C0 (the zero-th order of cepstral coefficient) adaptation scheme for PMC-based Mandarin speech recognition is proposed in this paper. It incorporates a new C0 model of speech signal into the PMC method to improve the gain matching between the clean-speech HMM models and the current noise model. The C0 model is constructed in the training phase by jointly modeling the normalized C0 with other MFCC recognition features to form C0-normalized HMM models. In the testing phase, it pre-segments the input utterance into syllablelike segments, performs C0-denormaliztion operations to expand the C0-normalized HMM models, and uses them in the PMC method. Compared with the conventional PMC method, the proposed method can achieve a much better noise compensation effect due to the use of more precise gain matching in the PMC model combination. Experimental results showed that the basesyllable accuracy rate was significantly upgraded for continuous noisy Mandarin speech recognition.