Abstract
This paper presents the experimental evaluation for recognition of consonant-vowel (CV) units under noise. Noise is one of the common degradation in real environments which strongly effects the performance of speech recognition system. In this work, initially effect of noise on recognition of CV units is studied by using two-stage CV recognition system proposed in our earlier studies. Later spectral processing based speech enhancement methods such as spectral subtraction and minimum mean square error (MMSE) are used for preprocessing to improve the CV recognition performance under noise. Performance of the CV recognition is studied on Telugu broadcast database for white and vehicle noise. Experimental results show that the speech enhancement techniques gives the improvement in the CV recognition performance under noise case.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Rabiner, L.R., Juang, B.H.: Fundamentals of speech recognition. PTR Prentice Hall, Englewood cliffs (1993)
Gangashetty, S.V.: Neural network models for recognition of consonant-vowel units of speech in Multiple Languages. PhD thesis, IIT Madras (October 2004)
Chandra Sekhar, C.: Neural Network models for recognition of stop consonant-vowel (SCV) segments in continuous speech. PhD thesis, IIT Madras (1996)
Chandra Sekhar, C., Lee, W.F., Takeda, K., Itakura, F.: Acoustic modeling of subword units using support vector machines. In: WSLP (2003)
Vuppala, A.K., Chakrabarti, S., Rao, K.S.: Effect of speech coding on recognition of Consonant-Vowel (CV) units. In: Proc. Int. Conf. contemporary computing (Springer Communications in Computer and Information Science, pp. 284–294 (August 2010) ISSN: 1865-0929
Suppression, B.S.F.: of acoustic noise in speech using spectral subtraction. IEEE Trans. Acoust., Speech, Signal Process 27, 113–120 (1979)
Ephrain, Y., Malah, D.: Speech enhancement using minimum mean square error short-time spectral amplitude estimator. IEEE Trans. Acoust., Speech, Signal Process 32, 1109–1121 (1984)
Suryakanth, V.G., Sekhar, C.C., Yegnanarayana, B.: Spotting multilingual consonant-vowel units of speech using neural networks. In: An ISCA tutorial and research workshop on non-linear speech processing, pp. 287–297 (April 2005)
Prasanna, S.R.M., Reddy, B.V.S., Krishnamoorthy, P.: Vowel onset point detection using source, spectral peaks, and modulation spectrum energies. IEEE Transactions on audio, speech, and language processing 17(4), 556–565 (2009)
Joseph, W.P.: Signal modeling techniques in speech recognition. Proceedings of the IEEE 81, 1215–1247 (1993)
Young, S., Kershaw, D., Odell, J., Ollason, D., Valtchev, V., Woodland, P.: The HTK Book Version 3.0. Cambridge University Press, Cambridge (2000)
Collobert, R., Bengio, S.: SVMTorch, support vector machines for large-scale regression problems. J. Mach. Learn. Res. 1, 143–160 (2001)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Vuppala, A.K., Rao, K.S., Chakrabarti, S. (2011). Effect of Noise on Recognition of Consonant-Vowel (CV) Units. In: Aluru, S., et al. Contemporary Computing. IC3 2011. Communications in Computer and Information Science, vol 168. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-22606-9_22
Download citation
DOI: https://doi.org/10.1007/978-3-642-22606-9_22
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-22605-2
Online ISBN: 978-3-642-22606-9
eBook Packages: Computer ScienceComputer Science (R0)