Extracting Characteristics of Speaker’s Voice Harmonic Spectrum - Design of Human Voice Feature Extraction Technique

Oldrich Horák, Jan Capek

2013

Abstract

This paper describes the design of a technique used to extract harmonic spectrum characteristics of human voice. The voice characteristic can be used for a speaker identification process. The cepstral analysis is the most popular method, which uses a Mel-Frequency Cepstral Coefficient vector as unique characteristics of given speaker voice. This method provides only limited reliability. The harmonic spectrum based on fundamental frequency of speaker’s voice can extend the characteristic vector by more values. The extended characteristics can provide better reliability of the speaker identification.

References

  1. Abdulla, W. H., 2002. Auditory based feature vectors for speech recognition systems. In: Advances in Communications and Software Technologies.WSEAS Press, Stevens Point, Wisconsin, USA.
  2. Atassi, H., 2008. Metody detekce základního tónu reci. In: Elektrorevue, Vol.4.
  3. Campbell, Jr, J. P., 1997. Speaker recognition: a tutorial. In: IEEE 85.
  4. Horák, O., 2012. The Voice Segment Type Determination using the Autocorrelation Compared to Cepstral Method. In: WSEAS Transactions on Signal Processing, vol. 8, issue 1.
  5. Horák, O., 2012. Phoneme Recognizer Based Verification of the Voice Segment Type Determination. In: Proceedings of the 3rd International conference on Applied Informatics and Computing Theory (AICT 7812). WSEAS Press, Stevens Point, Wisconsin, USA.
  6. Jung, J. S., Kim, J. K., and Bae, M. J., 2004. Speaker Recognition System Using the Prosodic Information. In: WSEAS Transactions on Systems. Vol. 3, Issue 3.
  7. Marchetto, E., Avanzini, F., and Flego, F., 2009. An Automatic Speaker Recognition System for Intelligence Applications. In: Proceedings of the 17th European Signal Processing Conference (EUSPICO 2009). Glasgow, Scotland.
  8. Moisa, C., Silaghi, H., and Silaghi, A., 2010. Speech and Speaker Recognition for the Command of an Industrial Robot. In Proceedings of the 12th WSEAS international conference on Mathematical methods and computational techniques in electrical engineering. WSEAS Press, Stevens Point, Wisconsin, USA.
  9. Petry, A., et al., 2008. A Distributed Speaker Authentication System. In: Applied Computing Conference (ACC 7808). Istanbul, Turkey.
  10. Tadokoro, Y., et al., 2007. Pitch Estimation for Musical Sound Including Percussion Sound Using Comb Filters and Autocorrelation Function. In: Proceedings of the 8th WSEAS International Conference on Acoustics & Music: Theory & Applications. Vancouver, Canada.
Download


Paper Citation


in Harvard Style

Horák O. and Capek J. (2013). Extracting Characteristics of Speaker’s Voice Harmonic Spectrum - Design of Human Voice Feature Extraction Technique . In Proceedings of the 8th International Joint Conference on Software Technologies - Volume 1: ICSOFT-EA, (ICSOFT 2013) ISBN 978-989-8565-68-6, pages 273-277. DOI: 10.5220/0004593502730277


in Bibtex Style

@conference{icsoft-ea13,
author={Oldrich Horák and Jan Capek},
title={Extracting Characteristics of Speaker’s Voice Harmonic Spectrum - Design of Human Voice Feature Extraction Technique},
booktitle={Proceedings of the 8th International Joint Conference on Software Technologies - Volume 1: ICSOFT-EA, (ICSOFT 2013)},
year={2013},
pages={273-277},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004593502730277},
isbn={978-989-8565-68-6},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 8th International Joint Conference on Software Technologies - Volume 1: ICSOFT-EA, (ICSOFT 2013)
TI - Extracting Characteristics of Speaker’s Voice Harmonic Spectrum - Design of Human Voice Feature Extraction Technique
SN - 978-989-8565-68-6
AU - Horák O.
AU - Capek J.
PY - 2013
SP - 273
EP - 277
DO - 10.5220/0004593502730277