Advertisement

Articulation Rate Recognition by Using Artificial Neural Networks

  • Izabela Szczurowska
  • Wiesława Kuniszyk-Jóźkowiak
  • Elzbieta Smołka
Part of the Advances in Soft Computing book series (AINSC, volume 45)

Abstract

This works concerns the problem of the application of artificial neural networks in the modelling of the hearing process. The aim of the research was to answer the question whether artificial neural networks are able to evaluate speech rate. Speech samples, first recorded during reading of a story with normal and next with slow articulation rate were used as research material. The experiment proceeded in two phases. In the first stage Kohonen network was used. The purpose of that network was to reduce the dimensions of the vector describing the input signals and to obtain the amplitude-time relationship. As a result of the analysis, an output matrix consisting of the neurons winning in a particular time frame was received. The matrix was taken as input for the following networks in the second phase of the experiment. Various types of artificial neural networks were examined with respect to their ability to classify correctly utterances with different speech rates into two groups. Good examination results were accomplished and classification correctness exceeded 88%.

Keywords

Speech Signal Radial Basis Function Neural Network Automatic Speech Recognition Speech Rate Speaker Recognition 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Koopmans-vanBeinum FJ, vanDonzel ME (1996) Relationship between discourse structure and dynamic speech rate. In: Bunnell HT, Idsardi W (Eds), Proceedings ICSLP96, Vol 3, 1724–1727Google Scholar
  2. 2.
    Zheng J, Franco H, Stolcke A (2000) Rate-dependent acoustic modeling for large vocabulary conversational speech recognition. In: Proceeding ISCA Tutorial and Research Workshop on Automatic Speech Recognition: Challenges for the new Millennium, Paris, France, 145–149Google Scholar
  3. 3.
    Ververidis D, Kotropoulos C (2006) Emotional speech recognition: Resources, features and methods. Speech Communication 48, 1162–1181CrossRefGoogle Scholar
  4. 4.
    Verhasselt JP Martens JP (1996) A fast and reliable rate of speech detector, Proceedings ICSLP96, Vol 3, 2258–2261Google Scholar
  5. 5.
    Guitar B, Kopff-Schaefer H, Donahu-Kilburg G, Bond L (1992) Parent verbal interactions and speech rate: A case study in stuttering. Journal of Speech and Hearing Research 35, 742–754Google Scholar
  6. 6.
    Howell P, Sackin S (2000) Speech rate modification and its effects on fluency reversal in fluent speakers and people who stutter. Journal of Developmental and Physical Disabilities 12(4)Google Scholar
  7. 7.
    Chen WY, Chen SH, Lin CHJ (1996) A speech recognition method based on the sequential Multi-layer Perceptrons. Neural Networks 9(4), 655–669CrossRefGoogle Scholar
  8. 8.
    Farrell K, Mamione R, Assaleh K (1994) Speaker recognition using neural networks and conventional classifiers. IEEE Transaction on Speech and Audio Processing 2(1), part 2, 194–205CrossRefGoogle Scholar
  9. 9.
    Kohonen T (2001) Self-Organizing Maps. Springer, Berlin, Heidelberg, New YorkGoogle Scholar
  10. 10.
    Kestler HA, Schwenker F (2000) Classification of high-resolution ECG signals, In Howlett R, Jain L Radial basis function neural networks: theory and applications. Heidelberg: Physica-VerlagGoogle Scholar
  11. 11.
    Schwenker F, Kestler HA, Palm G (2001) Three learning phases for radial-basisfunction networks. Neural Networks 14, 439–458.CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2007

Authors and Affiliations

  • Izabela Szczurowska
    • 1
  • Wiesława Kuniszyk-Jóźkowiak
    • 2
  • Elzbieta Smołka
    • 2
  1. 1.Department of PhysicsAgricultural UniversityLublinPoland
  2. 2.Laboratory of Biocybernetics, Institute of Computer ScienceMaria Curie-Sklodowska UniversityLublinPoland

Personalised recommendations