Abstract
This paper discusses a novel technique for the recognition of Assamese phonemes using Recurrent Neural Network (RNN) based phoneme recognizer. A Multi-Layer Perceptron (MLP) has been used as phoneme segmenter for the segmentation of phonemes from isolated Assamese words. Two different RNN based approaches have been considered for recognition of the phonemes and their performances have been evaluated. MFCC has been used as the feature vector for both segmentation and recognition. With RNN based phoneme recognizer, a recognition accuracy of 91% has been achieved. The RNN based phoneme recognizer has been tested for speaker mismatched and channel mismatched conditions. It has been observed that the recognizer is robust to any unseen speaker. However, its performance degrades in channel mismatch condition. Cepstral Mean Normalization (CMN) has been used to overcome the problem of performance degradation effectively.
This is a preview of subscription content, log in via an institution to check access.
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
Schwatz, R., Makhoul, J.: Where the Phoneme Are: Dealing with Ambiguity in Accoustic-Phonetic Recognition. IEEE Trans. ASSP 23, 50–53 (1975)
Zue, V.W.: The Use of Speech Knowledge in Automatic Speech Recognition. Proceedings of the IEEE 73, 1602–1615 (1985)
Weinsterin, C.J., McCandless, S.S., Mondehin, L.F., Zue, V.W.: A System for Acoustic Phonetic Analysis of Continuous Speech. IEEE Trans. ASSP 23, 54–67 (1975)
Suh, Y., Lee, Y.: Phoneme Segmentation of Continuous Speech using Multilayer Perceptron. In: Proc. ICSLP 1996, pp. 1297–1300 (1996)
Bhattacharjee, U.: Search Key Identification in a Spoken Query using Isolated Keyword Recognition. International Journal of Computer Applications 5(8), 14–21 (2010)
Buniet, L., Fohr, D.: Continuous Speech Segmentation with the Gamma Memory Model. In: Proc. of EUROSPEECH 1995, pp. 1685–1688 (1995)
Recourse Center for Indian Language Technology Solution, IIT Guwahati, http://www.iitg.ernet.in/rcilts/phaseI/asamiya.htm
Technology Development for Indian Language, Department of Information Technology, http://tdil.mit.gov.in
Box, G.E.P., Jenkins, G.M., Reinsel, G.C.: Time Series Analysis- Forecasting and Control, 3rd edn. Prentice-Hall, Englewood Cliffs (1994)
Sodanil, M., Nitsuwat, S., Haruechaiyasak, C.: Thai Word Recognition Using Hybrid MLP-HMM. International Journal of Computer Science and Network Security 10(3), 103–110 (2010)
Tuan, P.V., Kubin, T.: DTW-Based Phonetic Groups Classification using Neural Networks. In: Proc. ICASSP, pp. 401–404 (2005)
Gelenb, E. (ed.): Neural Network: Advances and Applications. North-Holland, New York (1991)
Williams, R.J., Zipser, D.: A learning algorithm for continually running fully recurrent neural networks. Neural Computation 1, 270–280 (1989)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Bhattacharjee, U. (2012). Recognition of Assamese Phonemes Using RNN Based Recognizer. In: Ystad, S., Aramaki, M., Kronland-Martinet, R., Jensen, K., Mohanty, S. (eds) Speech, Sound and Music Processing: Embracing Research in India. CMMR FRSM 2011 2011. Lecture Notes in Computer Science, vol 7172. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-31980-8_14
Download citation
DOI: https://doi.org/10.1007/978-3-642-31980-8_14
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-31979-2
Online ISBN: 978-3-642-31980-8
eBook Packages: Computer ScienceComputer Science (R0)