Abstract
HMM speech recogniser with a small number of acoustic observations based on 2-D cepstrum (TDC) is proposed. TDC represents both static and dynamic features of speech implicitly in matrix form. It is shown that TDC analysis enables a compact representation of speech signals. Thus a great advantage of the proposed model is a massive reduction of speech features used for recognition what lessens computational and memory requirements, so it may be favourable for limited-power ASR applications. Experiments on isolated Slovak digits recognition task show that the method gives comparable results as the conventional MFCC approach. For speech degraded by additive white noise, it reaches better performance than the MFCC method.
This research was supported by Science and Technology Assistance Agency under the contract No. APVT-20-044102 and by a Marie Curie European Reintegration Grant within the 6th European Community Framework Programme.
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
OShaugnessy, D.: Interacting with computer by voice: Automatic Speech Recognition and Synthesis. Proceedings of the IEEE 91(9), 1272–1305 (2003)
Ariki, Y., Mizuta, S., Nagata, M., Sakai, T.: Spoken-Word Recognition Using Dynamic Features Analysed by Two-Dimensional Cepstrum. Proceedings of IEE Pt.I 136(2), 133–140 (1989)
Kanedera, N., Hermansky, H., Arai, T.: Desired characteristics of modulation spectrum for robust automatic speech recognition. In: Proc. of ICASSP 1998, Seatle, USA, pp. 613–616 (1998)
Pai, H.-F., Wang, H.-C.: A Study of the Two-Dimensional Cepstrum Approach for Speech Recognition. Computer Speech and Language 6, 361–375 (1992)
Lin, C.-T., Nein, H.-W., Hwu, J.-Y.: GA-Based Noisy Speech Recognition Using Two- Dimensional Cepstrum. IEEE Trans. on Speech and Audio Processing 8(6), 664–675 (2000)
Milner, B.P., Vaseghi, S.-V.: Speech modelling using cepstral-time feature matrices and Hidden Markov Models. In: Proc. of ICASSP 1994, Adelaide Australia, pp. 601–604 (1994)
Kanedera, N., Arai, T., Hermansky, H., Misha, P.: On the importance of various modulation frequencies for speech recognition. In: Proc. of Eurospeech 1997, Rhodos, Greece, pp. 1079–1082 (1997)
Milner, B.: Cepstral-Time Matrices and LDA for Improved Connected digit and Sub-word Recognition Accuracy. In: Proc. of Eurospeech 1997, Rhodos Greece, vol. 1, pp. 405–408 (1997)
Jarina, R., Kuba, M.: Speech Recognition Using Hidden Markov Model with Low Redundancy in the Observation Space. Komunikacie 6(4), 17–21 (2004)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Jarina, R., Kuba, M., Paralic, M. (2005). Compact Representation of Speech Using 2-D Cepstrum – An Application to Slovak Digits Recognition. In: Matoušek, V., Mautner, P., Pavelka, T. (eds) Text, Speech and Dialogue. TSD 2005. Lecture Notes in Computer Science(), vol 3658. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11551874_44
Download citation
DOI: https://doi.org/10.1007/11551874_44
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-28789-6
Online ISBN: 978-3-540-31817-0
eBook Packages: Computer ScienceComputer Science (R0)