Statistical spectral estimation and discriminant analysis of the time series-an application to the speech recognition on Chinese speaking of two speakers

• Main Authors: Chang,Hui-Chin, 張惠琴
• Other Authors: Chilo
• Format: Others
• Language: zh-TW
• Published: 2007
• Online Access: http://ndltd.ncl.edu.tw/handle/01556817291816917329

碩士 === 中華大學 === 應用數學系碩士班 === 95 === The extension of classical pattern-recognition techniques to experimental time series data is a problem of great practical interest. An important potential application in engineering is to the problem of discriminating between various speech patterns. Throughout the engineering literature, most approaches assumed very specific Gaussian additive signal and noise models and then developed the discriminant criteria to minimize errors. In general, this requires that we assume prior knowledge of the signal waveforms and spectra under each of the hypotheses, so that discriminant functions can be calculated for an observed time series. In this dissertation, we assume the spectra of two speakers on speaking Chinese words “open door sesame” are unknown. The estimation and hypothesis-testing problems are formulated in terms of sample spectral densities with sample approximate distributions. Finally, we use frequency domain approximations to the optimum discriminant functions to identify the speech patterns of two speakers. The estimated quadratic discriminant function is quite well in classifying the two speakers’ voices because both the apparent error rate and the error rate by Lachenbruch’s holdout procedure are 0%. Also, the average apparent error rate of 45 pairs of 10 speakers is only about 3.47%. This indicates that it is a good way to apply the frequency domain discriminant analysis of time series to do the speech recognition on Chinese speaking of two speakers.