Effectiveness of linear prediction characteristics of the speech wave for automatic speaker identification and verification

Journal of the Acoustical Society of America

Volumn 55, Issue 6, 1974, Pages 1304-1312

  Atal, B S ^a  

^a LUCENT TECHNOLOGIES   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

AUDITION;

SPEECH;

DIAGNOSIS; MAJOR CLINICAL STUDY; MATHEMATICAL MODEL; METHODOLOGY; MODEL; SPEECH;

ACOUSTICS; FEMALE; HUMAN; MATHEMATICS; PATTERN RECOGNITION; SPEECH;

EID: 0016067897     PISSN: 00014966     EISSN: NA     Source Type: Journal    
DOI: 10.1121/1.1914702     Document Type: Article

References (19)

1. B. S. Atal and M. R. Schroeder, “Adaptive Predictive Coding of Speech Signals,” Bell System Tech. J. 49, 1973-1986 (1970).
2. B. S. Atal and S. L. Hanauer, “Speech Analysis and Synthesis by Linear Preduction,” J. Acoust. Soc. Am. 50, 637-655 (1971).
3. Throughout this paper, the word, “recognition” is used to include both identification and vertification.
4. S. Pruzansky, “Pattern-Matching Procedure for Automatic Talker Recognition”, J. Acoust. Soc. Am. 35, 354-358 (1963).
5. K. P. Li, J. E. Dammann, and W. D. Chapman, “Experimental Studies in Speaker Verification Using an Adaptive System,” J. Acoust. Soc. Am. 40, 966-978 (1966).
6. P. D. Bricker, R. Gnanadesikan, M. V. Mathews, S. Pruzansky, P. A. Tukey, K. W. Wachter, and J. L. Warner, “Statistical Techniques for lalker Identification,” Bell System Tech. J. 50, 1427-1454 (1971).
7. S. K. Das and W. S. Mohn, “Pattern Recognition in Speaker Verification”, AFIPS Conf. Proc., Fall Joint Computer Conf. 35, 721-732 (1969).
8. B. S. Atal, “Automatic Speaker Recognition Based on Pitch Contours”, Ph. D. Thesis, Polytechnic Inst. Brooklyn (June 1968).
9. B. S. Atal, “Automatic Speaker Recognition Based on Pitch Contours,” J. Acoust. Soc. Am. 52, 1687-1697 (1972).
10. G. R. Doddington, “A New Method of Speaker Verification,” J. Acoust. Soc. Am. 49, 139(A) (1971).
11. J. L. Flanagan, Speech Analysis and Perception, (Springer- Verlag, New York, 1972), pp. 199-204.
12. J. R. Ragazzini and G. F. Franklin, Sampled-Data Control Systems (McGraw-Hill, New York, 1958).
13. Ref. 2, pp. 642-643.
14. Ref. 2, pp. 653-655.
15. A. V. Oppenheim and R. W. Schafer, “Homomorphic Analysis of Speech,” IEEE Trans. Audio Electroacoust. AU-16, 221-226 (1968).
16. It may be pointed out here that the cepstrum obtained from Eqs. 15 or 17 is not identical with the cepstrum obtained by taking the logarithm of the short-time Fourier transform of the signal even when the transfer function has no zeros. The difference between the two is due to the truncation of the signal to a finite duration prior to Fourier analysis which produces a time series with zeros only irrespective of whether the transfer function has poles or zeros. The cepstrum obtained from the predictor coefficients, on the other hand, is based on the explicit assumption that the transfer function has only poles.
17. The cutoff frequency of the low-pass filter was 5.0 kHz.
18. G. S. Sebestyen, Decision-Making Processes in Pattern Recognition (The Macmillan Company, New York, 1962), pp. 24-30.
19. P. D. Bricker and S. Pruzansky, “Effect of Stimulus Content and Duration on Talker Identification,” J. Acoust. Soc. Am. 40, 1441-1449 (1966).