Industrial Technology Research Institute

Jau-Hung Chen

Chih-Chung Kuo

Chi-Shiang Kuo

Yung-An Kao

An automatic speech segmentation and verification system and method is disclosed, which has a known text script and a recorded speech corpus corresponding to the known text script. A speech unit segmentor segments the recorded speech corpus into N test speech unit segments referring to the phonetic information of the known text script. Then, a segmental verifier is applied to obtain a confidence measure of syllable segmentation for verifying the correctness of the cutting points of test speech unit segments. A phonetic verifier obtains a confidence measure of syllable verification by using verification models for verifying whether the recorded speech corpus is correctly recorded. Finally, a speech unit inspector integrates the confidence measure of syllable segmentation and the confidence measure of syllable verification to determine whether the test speech unit segment is accepted or not.

Automatic speech segmentation and verification using segment confidence measures

A method of pitch mark determination for a speech includes the following steps. First, a fundamental frequency and fundamental frequency passband signals are acquired by using an adaptable filter. Then, a number of passing zero positions of the fundamental frequency passband signals are detected. After that, at least a candidate set of pitch marks from a number of passing zero positions are generated. Lastly, the candidate set of pitch marks is estimated to generate the best set of pitch marks.

Growing community of inventors

Hsinchu, Taiwan

Jau-Hung Chen