Anshu Chittora
ABSTRACT
In this paper, we propose use of modulation spectrogram-based features for stop consonants classification based on their place of articulation. Stop sounds are classified as bilabial, alveolar and velar according to their place of articulation. The modulation spectrogram which is a two- dimensional (i.e., 2-D) feature represents modulation of low frequency components with acoustic frequency. In this work, modulation spectrogram has been obtained for all stop consonants from TIMIT database and then a dimension reduction algorithm, viz., higher order singular value decomposition (HOSVD) is applied on the feature vectors. The reduced dimension feature set is then applied to a Support Vector Machine (SVM) classifier which gives an overall accuracy of 94.25% for stop classification and 95.29% for place of articulation classification.
- Ali, A. M. A., Spiegel, J. V. and Muller, P., "Robust classification of stop consonants using auditaory-based speech processing", Proc. IEEE Int. Conf. on Acoustics, Speech and Signal Processing (ICASSP), Salt Lake City, UT, vol.1, pp.81--84, 2001.Google Scholar
- Ali, A. M. A., Spiegel, J. V. and Muller, P., "Acoustic-phonetic features for the automatic classification of stop consonants", IEEE Trans. Speech and Audio Proc., vol. 9, no. 8, pp. 833--841, 2001.Google ScholarCross Ref
- Ali, A. M. A., Spiegel, J. V. and Muller, P., "Acoustic-phonetic features for the automatic recognition of stop consonants", J. Acoust. Soc. Am., vol. 103, no. 5, pp. 2777--2778, 1998.Google ScholarCross Ref
- Zheng, Y., Mark H. J., and Borys S., "Stop consonant classification by dynamic formant trajectory," In Proc. Int. Conf. on Speech and Language Proc. (ICSLP), Jeju Island, Korea, 2004.Google Scholar
- Gidas, B.; Murua, A., "Classification and clustering of stop consonants via nonparametric transformations and wavelets," in Int. Conf. on Acoustics, Speech, and Signal Processing (ICASSP), Detroit, MI, vol.1, pp.872--875 May 1995.Google Scholar
- Bush, M.A., Kopec, G.E. and Zue V.W., "Selecting acoustic features for stop consonant identification", in Proc. of Int. Conf. on Acoustics, Speech, and Signal Processing (ICASSP), vol.8, no. 5, pp.742, 74, 1983Google ScholarCross Ref
- Greenberg, S. and Kingsbury, B. E. D., "The Modulation Spectrogram: In pursuit of an invariant representation of speech", Proc. IEEE on Int. Conf. Acoustics, Speech, Signal Process.(ICASSP), Munich, Germany, 1647--1650, 1997. Google ScholarDigital Library
- Hermansky, H., "The modulation spectrum in the automatic recognition of speech,", in Proceedings of IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), Santa Barbara, CA, pp.140, 147, Dec 1997.Google ScholarCross Ref
- Ganapathy, S., Thomas, S., and Hermansky, H., "Modulation frequency features for phoneme recognition in noisy speech", J. Acoust. Soc. Am., vol. 125, no.1, pp. EL8-EL12 2009.Google ScholarCross Ref
- Thomas, S., Ganapathy, S., and Hermansky, H., "Phoneme recognition using spectral envelope and modulation frequency features", IEEE Int. Conf. on Acoustics, Speech and Signal Processing(ICASSP), pp. 4453--4456, 2009. Google ScholarDigital Library
- Ganapathy, S., Thomas, S., and Hermansky, H., "Temporal envelop compensation for robust phoneme recognition using modulation spectrum", J. Acoust. Soc. Am. Vol. 128, no. 6, pp. 3769--3780, 2000.Google ScholarCross Ref
- Atlas, L. and Shamma, A. S., "Joint Acoustic and Modulation frequency", EURASIP J. on Applied signal Proccessing, vol. 7, pp. 668--675, 2003. Google ScholarDigital Library
- Markaki, M. and Stylianou, Y., "Using modulation spectra for voice pathology detection and classification", IEEE Annual Int. Conf. on Engineering in Medicine and Biology Society (EMBC), Minneapolis, Minnesota, USA, pp. 2514--2517, 2009Google ScholarCross Ref
- Markaki, M. and Stylianou, Y., "Modulation spectral features for objective voice quality assessment", Proc. IEEE Int. Symp. On Comm., Control and Signal Proc., Limassol, Cyprus, pp 1--4, 2010Google ScholarCross Ref
- Markaki, M., and Stylianou, Y., "Voice Pathology Detection and Discrimination based on Modulation Spectral Features", IEEE Trans. on Audio, Speech, and Language Proc., vol. 19, no. 7, pp. 1938--1948, 2011. Google ScholarDigital Library
- Lathauwer, L. D., Moor, B. D. and Vandewalle, J., "A multilinear singular value decomposition", SIAM J. Matrix Anal. Appl., vol 21, no. 4, pp. 1253--1278, 2000. Google ScholarDigital Library
- Modulation Toolbox. Available online: http://www.ee.washington.edu/research/isdl/projects/modulationtoolbox (last accessed on 14th Sept 2014).Google Scholar
Index Terms
- Classification of Stop Consonants using Modulation Spectrogram-Based Features
Recommendations
Modelling of the Arabic Plosive Consonants Characteristics Based on Spectrogram
AMS '10: Proceedings of the 2010 Fourth Asia International Conference on Mathematical/Analytical Modelling and Computer SimulationThe aim of this study is to determine the place of articulation for Arabic phonemes by subjects on non-arabic spoken language namely Malay. Every phoneme must be pronounced accurately in order to obey the rule of tajweed of holy Quran. By using Fourier ...
Fake Speech Detection Using Modulation Spectrogram
Speech and ComputerAbstractNowadays, speech technology like automatic speaker verification (ASV) systems can accurately verify the speaker’s identity, and hence they are extensively used in biometrics and banks. With the advancements in deep learning, deepFake has become ...
Vowel Effects Towards Dental Arabic Consonants Based on Spectrogram
ISMS '11: Proceedings of the 2011 Second International Conference on Intelligent Systems, Modelling and SimulationThis paper discussed the effect of vowel (fatha, kasra and damma) in Arabic consonants. These vowels are added to the basic consonants with three simple diacritics using the utterances of every dental consonant concerned by Malaysian children. The ...
Comments