European Portuguese Accent in Acoustic Models for Non-native English Speakers

  • Carla Simões
  • Carlos Teixeira
  • Miguel Dias
  • Daniela Braga
  • António Calado
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4756)

Abstract

The development of automatic speech recognition systems poses several known difficulties. One of them concerns the recognizer’s accuracy when dealing with non-native speakers of a given language. Normally a recognizer precision is lower for non-native users, hence our goal is to improve this low accuracy rate when the speech recognition system is confronted with a foreign accent. A typical usage scenario is to apply these models in applications where European Portuguese is dominant, but where English may also frequently occur. Therefore, several experiments were performed using cross-word triphone based models, which were then trained with speech corpora containing European Portuguese native speakers, English native speakers and English spoken by European Portuguese native speakers.

Keywords

Acoustic Models European Portuguese accent Speech Recognition 

References

  1. 1.
    Teixeira, C., Trancoso, I., Serralheiro, A.: Recognition of Non-Native Accents. In: Eurospeech, vol. 5, pp. 2375–2378 (1997)Google Scholar
  2. 2.
    Teixeira, C., Trancoso, I.: Word Rejection using Multiple Sink Models. In: Proc. ICSLP, pp. 1443–1446, Banff (1992)Google Scholar
  3. 3.
    Zavaliagkos, G., Schwartz, R., Makhoul, I.: Batch, Incremental and Instantaneous Adaptation Techniques for Speech Recognition. In: Proc. ICASSP (1995)Google Scholar
  4. 4.
    Kunzmann, S., Fischer, V., Gonzalez, J., Emam, O., Gunther, C., Janke, E.: Multilingual Acoustic Models for Speech Recognition and Synthesis, IEEE. In: ICASSP (2004)Google Scholar
  5. 5.
    Kohler, J.: Multi-lingual Phoneme Recognition Exploiting Acoustic-Phonetic Similarities of Sounds, Siemens AG, Munich, GermanyGoogle Scholar
  6. 6.
    Bartkova, K., Jouvet, D.: Multiple models for improved speech recognition for non-native speakers. In: SPECOM (2004)Google Scholar
  7. 7.
    Livescu, K., Glass, J.: Lexical Modelling of Non-Native Speech for Automatic Speech Recognition. In: ICASSP (2000)Google Scholar
  8. 8.
    Steidl, S., Stemmer, G., Hacker, C., Nöth, E.: Adaptation in the Pronunciation Space for Non-Native Speech Recognition. In: ICSLP, Korea (2004)Google Scholar
  9. 9.
    Rabiner, L.R.: A tutorial on hidden Markov models and selected applications in speech recognition. Proceedings of the IEEE 77(2), 257–286 (1989)CrossRefGoogle Scholar
  10. 10.
    Flege, J.E., Schirru, C., MacKay, I.: Interaction between the native and second language phonetic subsystems. Speech Communication 467–491 (2003)Google Scholar
  11. 11.
    Arslan, L.M., Hansen, J.H.L.: Selective Training in Hidden Markov Model Recognition. IEEE Transactions on Speech and Audio Processing 7(1), 46–54 (1999)CrossRefGoogle Scholar
  12. 12.
    Leggetter, C.J., Woodland, P.C.: Speaker Adaptation of HMMs Using Linear Regression (1994)Google Scholar
  13. 13.
    Wung, Z., Schultz, T., Waibel, A.: Comparison of Acoustic Model Adaptation Techniques on Non-Native Speech, IEEE. In: ICASSP (2003)Google Scholar
  14. 14.
    Morton, R.: The Training Guide, A Guide for Training Acoustic Models, Microsoft DocumentGoogle Scholar
  15. 15.
    Young, S., Kershaw, D., Odell, J., Ollason, D., Valtchev, V., Woodland, P.: The HTK Book (1999)Google Scholar
  16. 16.
    Woodland, P., Young, S.: The HTK Tied-State Continuous Speech Recognition. In: Proc. Eurospeech (1993)Google Scholar
  17. 17.
    Ferreira: Variação linguística: perspectiva dialectológica, in Faria et al. 1996. Introdução à Linguística Geral e Portuguesa,Lisboa, Caminho: 483 Google Scholar
  18. 18.
    Fromkin, Rodman: Introdução à Linguagem, Coimbra, Almedina: 273Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2007

Authors and Affiliations

  • Carla Simões
    • 1
    • 2
  • Carlos Teixeira
    • 2
  • Miguel Dias
    • 1
  • Daniela Braga
    • 1
  • António Calado
    • 1
  1. 1.Microsoft Language Development Center, Av. Prof. Doutor Aníbal Cavaco Silva, 2744-010 Porto SalvoPortugal
  2. 2.Departamento de Informática, Faculdade de Ciências da Universidade de Lisboa, Campo Grande, 1749-016 LisboaPortugal

Personalised recommendations