This paper addresses the problem of automatic identification of vowels uttered in isolation by female and child speakers. In this case, the magnitude spectrum of voiced vowels is sparsely sampled since only frequencies at integer multiples of F0 are significant. This impacts negatively on the performance of vowel identification techniques that either ignore pitch or rely on global shape models. A new pitch-dependent approach to vowel identification is proposed that emerges from the concept of timbre and that defines perceptual spectral clusters (PSC) of harmonic partials. A representative set of static PSC-related features are estimated and their performance is evaluated in automatic classification tests using the Mahalanobis distance. Linear prediction features and Mel-frequency cepstral coefficients (MFCC) coefficients are used as a reference and a database of five (Portuguese) natural vowel sounds uttered by 44 speakers (including 27 child speakers) is used for training and testing the Gaussian models. Results indicate that perceptual spectral cluster (PSC) features perform better than plain linear prediction features, but perform slightly worse than MFCC features. However, PSC features have the potential to take full advantage of the pitch structure of voiced vowels, namely in the analysis of concurrent voices, or by using pitch as a normalization parameter.
REFERENCES
1.
Bladon
, R. W.
(1982
). “Arguments against formants in the auditory representation of speech
,” in The Representation of Speech in the Peripheral Auditory System
, edited by R.
Carlson
and B.
Granstrom
(Elsevier Biomedical
, Amsterdam
), pp. 95
–102
.2.
Bruce
, I. C.
, Karkhanis
, N. V.
, Young
, E. D.
, and Sachs
, M. B.
(2002
). “Robust formant tracking in noise
,” in IEEE International Conference on Acoustics, Speech and Signal Processing
, pp. I281
–I284
, Orlando, Florida.3.
Chen
, B.
, and Loisou
, P. C.
(2004
). “Formant frequency estimation in noise
,” in IEEE International Conference on Acoustics, Speech and Signal Processing
, pp. I581
–I584
, Montreal, Canada.5.
Chistovich
, L.
, and Lublinskaja
, V.
(1979
). “The center of gravity effect in vowel spectra and critical distance between the formants: Psychoacoustical study of perception of vowel-like stimuli
,” Hear. Res.
1
, 185
–195
.6.
Davis
, S. B.
, and Mermelstein
, P.
(1980
). “Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences
,” IEEE Trans. Acoust., Speech, Signal Process.
28
, 357
–366
.6.
de Cheveigné
, A.
, and Kawahara
, H.
(1999
). “Missing-data model of vowel identification
,” J. Acoust. Soc. Am.
105
, 3497
–3508
.7.
Diehl
, R. L.
, Lindblom
, B.
, Hoemeke
, K. A.
, and Fahey
, R. P.
(1996
). “On explaining certain male-female differences in the phonetic realization of vowel categories
,” J. Phonetics
24
, 187
–208
.8.
Dusan
, S.
, and Rabiner
, L.
(2005
). “On integrating insights from human speech perception into automatic speech recognition
,” in the Ninth European Conference on Speech Communication and Technology (Interspeech-2005)
, Lisbon, Portugal, pp. 1233
–1236
.9.
10.
Ferreira
, A.
, and Sinha
, D.
(2005
). “Accurate and robust frequency estimation in the odft domain
,” in 2005 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics
, New Paltz, NY, pp. 203
–206
.11.
Ferreira
, A. J. S.
(1996a
). “Audio spectral coder
,” 100th Convention of the Audio Engineering Society
, Copenhagen, Denmark.12.
Ferreira
, A. J. S.
(1996b
). “Perceptual coding of harmonic signals
,” 100th Convention of the Audio Engineering Society
, Copenhagen, Denmark.13.
Ferreira
, A. J. S.
(1998
). “Spectral coding and post-processing of high quality audio
,” Ph.D. thesis, Faculdade de Engenharia da Universidade do Porto-Portugal, Porto, Portugal, http://telecom.inescn.pt/doc/phd_en.html (last viewed on May 12th 2007).14.
Ferreira
, A. J. S.
(2001
). “Accurate estimation in the odft domain of the frequency, phase and magnitude of stationary sinusoids
,” in 2001 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics
, New Paltz, NY, pp. 47
–50
.15.
Ferreira
, A. J. S.
(2005
). “New signal features for robust identification of isolated vowels
,” in the Ninth European Conference on Speech Communication and Technology (Interspeech-2005)
, Lisbon, Portugal, pp. 345
–348
.16.
Flexer
, A.
(2006
). “Statistical evaluation of music information retrieval experiments
,” J. New Music Res.
35
, 113
–120
.16.
Goldstein
, L. G.
(1973
). “An optimum processor theory for the central formation of the pitch of complex tones
,” J. Acoust. Soc. Am.
54
(6
), pp. 1496
–1516
.17.
Hermansky
, H.
(1990
). “Perceptual linear predictive (plp) analysis of speech
,” J. Acoust. Soc. Am.
87
, 1738
–1752
.18.
Hermansky
, H.
, Hanson
, B.
, and Wakita
, H.
(1985
). “Low-dimensional representation of vowels based on all-pole modeling in the psychophysical domain
,” Speech Commun.
4
, 181
–187
.19.
Hess
, W.
(1983
). Pitch Determination of Speech Signals—Algorithms and Devices
(Springer
, Berlin
).20.
Hillenbrand
, J. M.
, and Houde
, R. A.
(2003
). “A narrow band pattern-matching model of vowel perception
,” J. Acoust. Soc. Am.
113
, 1044
–1055
.21.
Hillenbrand
, J. M.
, Houde
, R. A.
, and Gayvert
, R. T.
(2006
). “Speech perception based on spectral peaks versus spectral shape
,” J. Acoust. Soc. Am.
119
, 4041
–4054
.22.
Honig
, F.
, Stemmer
, G.
, Hacker
, C.
, and Brugnara
, F.
(2005
). “Revisiting perceptual linear prediction (plp)
,” in the Ninth European Conference on Speech Communication and Technology (Interspeech-2005)
, Lisbon, Portugal, pp. 2997
–3000
.23.
Klatt
, D. H.
(1982
). “Prediction of perceived phonetic distance from critical-band spectra—a first step
,” in IEEE International Conference on Acoustics, Speech and Signal Processing
, Paris, France, pp. 1278
–1281
.24.
Lass
, N. J.
, ed. (1996
). Principles of Experimental Phonetics
(Mosby Year Book
, St. Louis, MO
).25.
Maurer
, D.
, Cook
, N.
, Landis
, T.
, and d’Heureuse
, C.
(1992
). “Are measured differences between the formants of men, women and children due to f0 differences?
,” J. Int. Phonetic Assoc.
21
, 66
–79
.26.
Mollis
, M. R.
(2005
). “Evaluating models of vowel perception
,” J. Acoust. Soc. Am.
118
, 1062
–1071
.27.
Moore
, B. C. J.
(1989
). An Introduction to the Psychology of Hearing
(Academic
, New York
).28.
Palethorpe
, S.
, Wales
, R.
, Clark
, J. E.
, and Senserrick
, T.
(1996
). “Vowel classification in children
,” J. Acoust. Soc. Am.
100
, 3843
–3851
.29.
Plomb
, R.
(2002
). The Intelligent Ear—On the Nature of Sound Perception
(Erlbaum
, Mahwah, NJ
).30.
Rabiner
, L.
, and Juang
, B.-H.
(1993
). Fundamentals of Speech Recognition
(Prentice-Hall
, Englewood Cliffs, NJ
).31.
Ryalls
, J. H.
, and Lieberman
, P.
(1982
). “Fundamental frequency and vowel perception
,” J. Acoust. Soc. Am.
72
, 1631
–1634
.31.
Sroka
, J. J.
, and Braida
, L. D.
(2005
). “Human and machine consonant recognition
,” Speech Commun.
45
, 401
–423
.32.
Thorpe
, C.
, and Watson
, C.
(2000
). “Vowel identification in singing at high pitch
,” in Proceedings of the Eighth Australian International Conference on Speech Science and Technology
, Canberra, Australia, pp. 280
–286
.33.
Vaidyanathan
, P. P.
(1993
). Multirate Systems and Filter Banks
(Prentice-Hall
, Englewood Cliffs, NJ
).34.
Wet
, F.
, Weber
, K.
, Boves
, L.
, Cranen
, B.
, Bengio
, S.
, and Bourlard
, H.
(2004
). “Evaluation of formant-like features on an automatic vowel classification task
,” J. Acoust. Soc. Am.
116
, 1781
–1791
.35.
Zahorian
, S. A.
, and Jagharghi
, A. J.
(1993
). “Spectral-shape features versus formants as acoustic correlates for vowels
,” J. Acoust. Soc. Am.
94
, 1966
–1982
.36.
Zwicker
, E.
(1961
). “Subdivision of the audible frequency range into critical bands
,” J. Acoust. Soc. Am.
33
, 248
–284
.© 2007 Acoustical Society of America.
2007
Acoustical Society of America
You do not currently have access to this content.
