Advertisement

Automatic Identification of Phonetic Similarity Based on Underspecification

  • Mark Kane
  • Julie Mauclair
  • Julie Carson-Berndsen
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6562)

Abstract

This paper presents a novel approach to the identification of phonetic similarity using properties observed during the speech recognition process. Experiments are presented whereby specific phones are removed during the training phase of a statistical speech recognition system so that the behaviour of the system can be analysed to see which alternative phone is selected. The domain of the analysis is restricted to specific contexts and the alternatively recognised (or substituted) phones are analysed with respect to a number of factors namely, the common phonetic properties, the phonetic neighbourhood and the frequency of occurrence with respect to a particular corpus. The results indicate that a measure of phonetic similarity based on alternatively recognised observed properties can be predicted based on a combination of these factors and as such can serve as an important additional source of information for the purposes of modelling pronunciation variation.

Keywords

speech recognition phonetic similarity 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Halberstadt, A., Glass, J.: Heterogeneous acoustic measurements for phonetic classification. In: Eurospeech Proceedings, pp. 401–404 (1997)Google Scholar
  2. 2.
    Scanlon, P., Ellis, D., Reilly, R.: Using broad phonetic group experts for improved speech recognition. IEEE Transactions on Audio, Speech and Language Processing 15(3), 803–812 (2007)CrossRefGoogle Scholar
  3. 3.
    Garofolo, J., Lamel, L., Fisher, W., Fiscus, J., Pallett, D., Dahlgren, N.: The DARPA TIMIT Acoustic-Phonetic Continuous Speech Corpus CDROM (1993)Google Scholar
  4. 4.
    Mauclair, J., Aioanei, D., Carson-Berndsen, J.: Exploiting phonetic and phonological similarities as a first step for robust speech recognition. In: EUSIPCO Proceedings (2009)Google Scholar
  5. 5.
    Van Thuan, P., Kubin, G.: Dwt-based phonetic groups classification using neural networks. In: ICASSP Proceedings, pp. 401–404 (2005)Google Scholar
  6. 6.
    Ghiselli-Crippa, T., El-Jaroudi, A.: Voiced-unvoiced-silence classification of speech using neural nets. In: IJCNN Proceedings, pp. 851–856 (1991)Google Scholar
  7. 7.
    The-International-Phonetic-Alphabet (2005), http://www.langsci.ucl.ac.uk/ipa/
  8. 8.
    Young, S., Evermann, G., Gales, M., Hain, T., Kershaw, D., Liu, X., Moore, G., Odell, J., Ollason, D., Povey, D., Valtchev, V., Woodland, P.: Hidden markov model toolkit (htk) (2009), http://htk.eng.cam.ac.uk/, Version 3.4.1
  9. 9.
    IPDS, CD-ROM#2: The Kiel Corpus of Spontaneous Speech, vol. 1, Kiel, IPDS (1995)Google Scholar
  10. 10.
    Chomsky, N., Halle, M.: The sound pattern of english. Harper & Row, New York (1968)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Mark Kane
    • 1
  • Julie Mauclair
    • 2
  • Julie Carson-Berndsen
    • 1
  1. 1.School of Computer Science and InformaticsUniversity College DublinIreland
  2. 2.LIPADEUniversity Paris DescartesFrance

Personalised recommendations