Time-Frequency Energy Features for Articulator Position Inference on Stop Consonants
Main Article Content
Keywords
acoustic-to-Articulatory inversion, Gaussian mixture models, articulatory phonetics, time-frequency features.
Abstract
Acoustic-to-Articulatory inversion offers new perspectives and interesting applicationsin the speech processing field; however, it remains an open issue. This paper presents a method to estimate the distribution of the articulatory informationcontained in the stop consonants’ acoustics, whose parametrizationis achieved by using the wavelet packet transform. The main focus is on measuringthe relevant acoustic information, in terms of statistical association, forthe inference of the position of critical articulators involved in stop consonantsproduction. The rank correlation Kendall coefficient is used as the relevance measure. The maps of relevant time–frequency features are calculated for theMOCHA–TIMIT database; from which, stop consonants are extracted andanalysed. The proposed method obtains a set of time–frequency components closely related to articulatory phenemenon, which offers a deeper understanding into the relationship between the articulatory and acoustical phenomena.The relevant maps are tested into an acoustic–to–articulatory mapping systembased on Gaussian mixture models, where it is shown they are suitable for improvingthe performance of such a systems over stop consonants. The method could be extended to other manner of articulation categories, e.g. fricatives,in order to adapt present method to acoustic-to-articulatory mapping systemsover whole speech.
PACS: 87.85Ng
MSC: 68T10
Downloads
References
[2] J. Schroeter, M. Sondhi, “Speech coding based on physiological models of speech production,” in Advances in Speech Signal Processing, S. Furui and M. M. Sondhi, Eds. NewYork: Marcel Dekker Inc, 1992, ch. 8. Referenced in 37
[3] S. King, J. Frankel, K. Livescu, E. McDermott, K. Richmond, M.Wester, “Speech production knowledge in automatic speech recognition”, The Journal of the Acoustical Society of America, vol. 121, n.o 2, pp. 723-742, 2007. Referenced in 37
[4] P. Jackson, V. Singampalli, “Statistical identification of articulation constraints in the production of speech”, Speech Communication, vol. 51, n.o 8, pp. 695-710, ago. 2009. Referenciado en 37, 45
[5] H. H. Yang, S. V. Vuuren, S. Sharma, H. Hermansky, “Relevance of time-frequency features for phonetic and speaker-channel classification”, Speech Communication, vol. 31, n.o 1, pp. 35-50, may 2000. Referenced in 37
[6] Mark Hasegawa-Johnson. Time-frequency distribution of partial phonetic information measured using mutual information. Beijing, 2000. [Online] Available: http://www.isle.illinois.edu/sst/pubs/2000/hasegawa-johnson00interspeech.pdf, In InterSpeech, pp. 133-136. Referenced in 37
[7] J. Schroeter, M. Sondhi, “Techniques for estimating vocal-tract shapes from the speech signal”, IEEE Trans. on Speech and Audio Processing, vol. 2, pp. 133-150, 1994. Referenced in 37
[8] V. Sorokin, A. Leonov, A. Trushkin, “Estimation of stability and accuracy of inverse problem solution for the vocal tract”, Speech Communication, vol. 30, n.o 1, pp. 55-74, 2000. Referenced in 37
[9] G. Papcun, et. al., “Inferring articulation and recognizing gestures from acoustics with a neural network trained on x-ray microbeam data”, J. Acoust. Soc. Am., vol. 92 n.o 2, pp. 688-700, 1992. Referenced in 37
[10] Gh. Choueiter, J. Glass, “An Implementation of Rational Wavelets and Filter Design for Phonetic Classi cation”, IEEE Transactions on Audio, Speech, and Language Processing, vol. 15 n.o 3, pp. 939-948, 2007. Referenced in 38
[11] J. Silva, Shrikanth Narayanan, “Discriminative Wavelet Packet Filter Bank Selection for Pattern Recognition”, IEEE Transactions on Signal Processing, vol. 57, n.o 5, pp. 1796-1810 ,2009. Referenced in 38
[12] P. Addison, The Illustrated Wavelet Transform Handbook, 1st ed. Taylor & Francis, 2002. Referenced in 38
[13] S. Mallat, A Wavelet Tour of Signal Processing, Third Edition: The SparseWay, Academic Press, 1998. Referenced in 38
[14] A. Akansu, P. Haddad, Multiresolution Signal Decomposition, Second Edition: Transforms, Subbands, and Wavelets, 2.a ed. Academic Press, 2000. Referenced in 39
[15] O. Farooq, S. Datta, “Mel filter-like admissible wavelet packet structure for speech recognition”, Signal Processing Letters, IEEE, vol. 8, n.o 7, pp. 196 -198, jul. 2001. Referenced in 39, 40
[16] K. Richmond, S. King, P. Taylor, “Modelling the uncertainty in recovering articulation from acoustics”, Computer Speech & Language, vol. 17, n.o 2-3, pp. 153-172, abr. 2003. Referenced in 40, 44
[17] J. Gibbons, S. Chakraborti, G. Gibbons, Nonparametric Statistical Inference, Marcel Dekker Inc., 2003. Referenced in 42, 43
[18] Alan Wrench. “MOCHA-TIMIT”, The Centre for Speech TechnologyResearch. [Online]. Available: http://www.cstr.ed.ac.uk/research/projects/artic/mocha.html. Referenced in 44
[19] Korin Richmond, Articulatory feature recognition from the acoustic speech signal. PhD. thesis, University of Edinburgh. [Online]. Available: http://www.cstr.ed.ac.uk/publications/users/korin.html. Referenced in 45
[20] Tomoki Toda, Alan Black, Keiichi Tokuda, “Statistical Mapping between Articulatory Movements and Acoustic Spectrum using Gaussian Mixture Models”, Speech Communication, vol. 50 n.o3, pp. 215-227, 2008. Referenced in 48, 51
[21] C. Bishop, Pattern Recognition and Machine Learning, 1st ed. 2006. Corr. 2nd printing. Springer, 2007. Referenced in 48
[22] R. Kent, Charles Read, Acoustic Analysis of Speech, Thomson Learning, 2002. Referenced in 50