ACOUSTIC INVARIANT APPROACH TO SPEECH SOUND ANALYSIS FOR BRAND NEW SPEECH RECOGNITION SYSTEMS (UKRAINIAN AND ENGLISH)

Authors

  • Maksym O. Vakulenko

DOI:

https://doi.org/10.47839/ijc.6.3.455

Keywords:

Speech recognition, acoustic phonetics, acoustic invariants, speaker-independent characteristics

Abstract

On the basis of acoustic invariant speech analysis (AISA), the permanent spectral characteristics of the Ukrainian vowels are obtained for various ways of pronunciation including ordinary speech, whisper and changing tone. It is shown that the lowest phonemic frequencies due to vocal fold oscillations or to Helmholtz resonance are not associated with persistent sound features. It is conjectured that the only phonemic invariant is the ratio between formant frequencies, not their absolute values. This analysis is complemented by the computer sound synthesis. We show also that the acoustic invariants of the Ukrainian sound [i] are close to that of English [I]. The results obtained may be useful for specialists in the field of experimental phonetics and speech modelling.

References

K.N. Stevens, Acoustic Phonetics. MIT Press, 1998. 607 p.

G. Fant, Acoustic theory of speech production. The Hague, Netherlands, 1960.

J.L. Flanagan, Speech analysis, synthesis, and perception. Berlin: Springer-Verlag, 1972.

H.M. Hanson, "Glottal characteristics of female speakers: Acoustic correlates," J. of the Acoustical Soc. of America, 101, 1997, pp. 466-481.

K.N. Stevens, and H.M. Hanson, "Classification of glottal vibration from acoustic measurements." In: Vocal fold physiology: Voice quantity control / O. Fujimura, M. Hirano, Eds. San Diego: Singular, 1995. Pp. 147-170.

H.M. Hanson, Glottal characteristics of female speakers. PhD dissertation, Harvard University, Cambridge MA, 1995.

O. Fujimura, and J. Lindqvist, "Sweep-tone measurements of vocal-tract characteristics," J. of the Acoustical Soc. of America, 49, 1971, pp. 541-558.

G.Fant, L. Nord, and P. Branderud, "A note on the vocal tract wall impedance," Speech Transmission Laboratory Quarterly Progress and Status Report 4, Royal Institute of Technology, Stockholm, Sweden, 1976. Pp. 13-27.

E.B. Holmberg, R.E. Hillman, and J.S. Perkell, "Glottal airflow and transglottal air pressure measurements for male and female speakers in soft, normal and loud voice," J. of the Acoustical Soc. of America, 84, 1988, pp. 511-529.

D.H. Klatt, and L.C. Klatt, "Analysis, synthesis, and perception of voice quality variations among female and male talkers," J. of the Acoustical Soc. of America, 87, 1990, pp. 820-857.

H. Traunmueller, "Perceptual dimensions of openness in vowels," – J. of the Acoustical Soc. of America, 69, 1981, pp. 1465-1475.

K.A. Hoemeke, and R.L. Diehl, "Perception of vowel height: The role of F1-F0 distance," – J. of the Acoustical Soc. of America, 96, 1994, pp. 661-674.

R. Carlson, B. Granstroem, and G. Fant, "Some studies concerning perception of isolated vowels," Speech Transmission Laboratory Quarterly Progress and Status Report 2-3, Royal Institute of Technology, Stockholm, Sweden, 1970. Pp. 19-35.

Zh. Zhang, J. Neubauer, and D.A. Berry, "The influence of subglottal acoustics on laboratory models of phonation," – J. of the Acoustical Soc. of America, 120, 2006, pp. 1558-1569.

L. Menard, J.-L. Schwartz, L.-J. Boё, and J. Aubin, "Articulatory-acoustic relationships during vocal tract growth for French vowels: Analysis of real data and simulations with an articulatory model," J. of Phonetics, 35, 2007, pp. 1-19.

N.I. Tocka, Vowel phonemes of Ukrainian literature language. Kyjiv, Kyjiv University publishing house, 1973, 193 p. (in Ukrainian).

T.M. Nearey, and P.F. Assmann, "Information conveyed by f0 for vowel identification," J. of the Acoustical Soc. of America, 119, 2006, pp. 3339.

T. Dubeda, and E. Keller, "Microprosodic aspects of vowel dynamics – an acoustic study of French, English and Czech," J. of Phonetics, 33, 2005, pp. 447-464.

M.O. Vakulenko, "Analysis and synthesis of the sound spectra of human speech," Pulsar, № 6-7, 1999, pp. 20-23.

M.O. Vakulenko, "Acoustic characteristics and invariants of the Ukrainian sounds", Scholarly News of the KSLU UNESCO Chair. Philology, Pedagogics, Psychology. Vol. 1. Kyjiv, 2000, pp. 62–66 (in Ukrainian).

M.O. Vakulenko, and O.V. Vakulenko, "Ukrainian spelling: view from Ukraine". Scientific reports of the Higher School Academy of Sciences of Ukraine. Vol.4. Kyjiv-Khreshhatyk, 2002, pp.129-138 (in Ukrainian).

Maksym Vakulenko, Russian-Ukrainian Dictionary of Physical Terminology / Prof. O.V. Vakulenko, Ed. Kyjiv, 1996, 236 p. (in Ukrainian).

Maksym Vakulenko, On the "difficult" problems of Ukrainian spelling. Kyjiv, "Kurs", 1997. 32 p. (in Ukrainian).

Maksym Vakulenko, "Spelling aspects of the terminology as a science". Book Chamber News. Kyjiv, 1998, #11, pp.15-17.

Studies in Communicative Phonetics and Foreign Language Teaching Methodology / M.P. Dvorzhetska, A.A. Kalita, Eds. K., Lenvit, 1997.

M.O. Vakulenko, "Transliteration Through a Slavonic Latin Alphabet: Saving Information and Expenses," Kyjiv Linguistic University News. – Philology. – V.2, №1, 1999, pp. 85-94.

Maksym Vakulenko, "Ukrainian Latin alphabet as Standardized Addition to Ukrainian Orthography". Library News, 1998, #2, pp.10-12 (in Ukrainian).

Trends in Speech Recognition / Wayne A. Lea, Ed. – Prentice-Hall, Inc., Englewood Cliffs, New Jersey, 1980.

T.K. Vincjuk, Analysis, perception and interpretation of the speech signals. Kyjiv, 1987, 262 p. (in Russian).

The Feynman lectures on physics // Richard P. Feynman, Robert B. Leighton, Matthew Sands. Vol.1. Addison-Wesley publishing company, 1963.

Downloads

Published

2014-08-01

How to Cite

Vakulenko, M. O. (2014). ACOUSTIC INVARIANT APPROACH TO SPEECH SOUND ANALYSIS FOR BRAND NEW SPEECH RECOGNITION SYSTEMS (UKRAINIAN AND ENGLISH). International Journal of Computing, 6(3), 79-86. https://doi.org/10.47839/ijc.6.3.455

Issue

Section

Articles