Advertisement

International Journal of Speech Technology

, Volume 10, Issue 1, pp 57–62 | Cite as

Innovative wavelet based speech model using optimal mother wavelet generated from pitch synchronous LPC trajectory

  • S. D. ApteEmail author
Article

Abstract

The paper proposes an innovative technique for generation of optimal mother wavelet using LPC trajectory with special reference to speech recognition. A new wavelet based model is proposed for speech signal processing. Lower order linear predictor coefficients (LPC) are related to the vocal tract area near lip that is the articulating organ. The trajectory of second LPC is proposed for the generation of mother wavelet for speech recognition. The observation interval is selected as the pitch period that represents one complete cycle of speech waveform. LPC of order 10 are evaluated for each pitch synchronous (PS) segment. An innovative technique is proposed for the generation of mother wavelet. The mother wavelet is separately generated for each word utterance. This generates a multidimensional space for speech words and increases the recognition accuracy. The wavelet transform (WT) coefficients are evaluated with respect to the generated mother wavelet for each word utterance and are stored as template along with the generated mother wavelet for each word utterance. The data base consists of 30 word utterances recorded locally using the sound recorder facility. In the recognition mode, the external word utterance is scanned and is divided into PS segments. The trajectory of second LPC is tracked. WT coefficients are evaluated with respect to the mother wavelet of each word in the vocabulary and are compared with the template for each word. The results indicate 100% recognition accuracy.

Keywords

Pitch synchronous Wavelet transform Average magnitude difference function F-ratio 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Dante, H. M., & Sarma, V. S. (1979). Automatic speaker identification for a large population. IEEE Transactions on Acoustics, Speech and Signal Processing, 27(3), 255–263. CrossRefMathSciNetGoogle Scholar
  2. Evangelista, G. (1993). Pitch synchronous wavelet representations of speech and music signals. IEEE Transactions on Signal Processing, 41(12), 3313–3330. zbMATHCrossRefGoogle Scholar
  3. Evangelista, G. (1994). Comb and multiplexed wavelet transforms and their applications to signal processing. IEEE Transactions on Signal Processing, 42(2), 292–303. CrossRefGoogle Scholar
  4. Grenier, Y. (1983). Time dependent ARMA modeling of non stationary signals. IEEE Transactions on Acoustics, Speech and Signal Processing, 31(4), 899–911. CrossRefGoogle Scholar
  5. Kadambe, S., & Bartels, F. B. (1992). Application of wavelet transform for pitch detection of speech signals. IEEE Transactions on Information Theory, 38(2), 917–923. CrossRefGoogle Scholar
  6. Markel, J. E., & Gray, A. H. (1982). Linear prediction of speech (pp. 76–82). Berlin: Springer. Google Scholar
  7. Parsons (1986). Voice and speech processing (pp. 203–204). New York: McGraw–Hill. Google Scholar
  8. Tewfik, A. H., Sinha, D., & Jorgensen, P. (1992). On the optimal choice of a wavelet for signal representation. IEEE Transactions on Information Theory, 38(2), 747–765. CrossRefGoogle Scholar
  9. Tsatsanis, M. K., & Giannakis, G. B. (1993). Time varying system identification and model validation using wavelets. IEEE Transactions on Signal Processing, 41(12), 3512–3523. zbMATHCrossRefGoogle Scholar
  10. Young, R. K. (1993a). Wavelet theory and its applications (pp. 12–14). Dordrecht: Kluwer Academic. Google Scholar
  11. Young, R. K. (1993b). Wavelet theory and its applications (pp. 140–183). Dordrecht: Kluwer Academic. Google Scholar

Copyright information

© Springer Science+Business Media, LLC 2009

Authors and Affiliations

  1. 1.Electronics DepartmentRajarshee Shahu College of EngineeringPuneIndia
  2. 2.Walchand College of EngineeringSangliIndia

Personalised recommendations