论文信息 - Statistical tests and distance measures for LPC coefficients

Statistical tests and distance measures for LPC coefficients

This paper considers the problem of comparing two sets of (LPC) coefficients or, more generally, that of comparing two short segments of speech via LPC techniques. It is shown that Itakura's prediction-residual ratio is intuitively unsatisfactory and theoretically misleading as a distance measure. Two slower, but more accurate statistical means of comparison are suggested, and these are supported by evidence from a simulation study.

P. de Souza | P. D. Souza

[1] A. Wald,et al. On the Statistical Treatment of Linear Stochastic Difference Equations , 1943 .

[2] B. Atal,et al. Speech analysis and synthesis by linear prediction of the speech wave. , 1971, The Journal of the Acoustical Society of America.

[3] James Durbin,et al. The fitting of time series models , 1960 .

[4] George M. White,et al. Speech Recognition: A Tutorial Overview , 1976, Computer.

[5] M. H. Quenouille. The Comparison of Correlations in Time‐Series , 1958 .

[6] G. Yule. On a Method of Investigating Periodicities in Disturbed Series, with Special Reference to Wolfer's Sunspot Numbers , 1927 .

[7] E. Parzen. Approach to empirical time series analysis , 1964 .

[8] Gilbert T. Walker,et al. On Periodicity in Series of Related Terms , 1931 .

[9] Calyampudi Radhakrishna Rao,et al. Linear Statistical Inference and its Applications , 1967 .

[10] F. Itakura,et al. Minimum prediction residual principle applied to speech recognition , 1975 .

[11] G. White,et al. Speech recognition experiments with linear predication, bandpass filtering, and dynamic programming , 1976 .

[12] T. W. Anderson. An Introduction to Multivariate Statistical Analysis , 1959 .

[13] J. Makhoul,et al. Linear prediction: A tutorial review , 1975, Proceedings of the IEEE.