Estimation of DRT Scores Using Objective Measures

Chapter
Part of the Signals and Communication Technology book series (SCT)

Abstract

In this chapter, two different attempts at estimating the DRT scores using objective measures are described. Since subjective intelligibility is a time-consuming and laborious task, if estimation of intelligibility without using human listeners is possible, at least at some degree of accuracy, the cost reduction should be significant.

Keywords

Automatic Speech Recognition Mean Opinion Score Speech Quality Noise Type Speech Intelligibility 
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.

References

  1. 1.
    Barker, J., Cooke, M.: Modeling speaker intelligibility in noise. Speech Commun. 49(5), 402–417 (2007)CrossRefGoogle Scholar
  2. 2.
    Chen, G., Parsa, V.: Bayesian model based nonintrusive speech quality evaluation. In: Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, vol. I, pp. 385–388. Philadelphia, PA (2005)Google Scholar
  3. 3.
    Hansen, J.H.L., Pellom, B.L.: An effective quality evaluation protocol for speech enhancement algorithms. In: Proceedings of the International Conference on Spoken Language Processing (ICSLP), vol. 7, pp. 2819–2822 (1998)Google Scholar
  4. 4.
    Hori, T., Katoh, M., Ito, A., Kohda, M.: A study on HMNets using phonetic decision tree-based successive state splitting. IEICE Trans. Inform. Syst. J80-D-II(10), 2645–2654 (1997)Google Scholar
  5. 5.
    Hu, Y., Loizou, P.C.: Evaluation of objective quality measures for speech enhancement. IEEE Trans. Audio, Speech Lang. Process. 16(1), 229–238 (2008)Google Scholar
  6. 6.
    ITU-T: ITU-T Recommendation P.862.1: Mapping functions for transforming P.862 raw result scores to MOS-LQO (2003)Google Scholar
  7. 7.
    ITU-T: ITU-T Recommendation P.862.2: Wideband extension to Recommendation P.862 for the assessment of wideband telephone networks and speech codecs (2007)Google Scholar
  8. 8.
    Kondo, K.: Estimation of speech intelligibility using objective measures. In: Proceedings of the Inter-noise 2011. International Institute of Noise Control Engineering, Osaka (2011)Google Scholar
  9. 9.
    Kondo, K.: Improving accuracy of estimated speech intelligibility scores by speech recognizers using multi-condition noise-adapted models. In: Proceedings of the Inter-noise 2011. International Institute of Noise Control Engineering, Osaka (2011)Google Scholar
  10. 10.
    Kondo, K.: Optimum orientation of parallel parametric speakers for simultaneous guide audio with minimum crosstalk. In: Proceedings of the Inter-noise 2011. International Institute of Noise Control Engineering, Osaka (2011)Google Scholar
  11. 11.
    Kondo, K., Izumi, R., Fujimori, M., Kaga, R., Nakagawa, K.: On a two-to-one selection based Japanese intelligibility test. J. Acoust. Soc. Jpn. 63(4), 196–205 (2007)Google Scholar
  12. 12.
    Kondo, K., Takano, Y.: Estimation of two-to-one forced selection intelligibility scores by speech recognizers using noise-adapted models. In: Proceedings of Interspeech, pp. 302–305. Tokyo, Japan (2010)Google Scholar
  13. 13.
    Leggeter, C.J., Woodland, P.J.: Maximum likelihood linear regression for speaker adaptation of continuous density hidden Markov models. Comput. Speech Lang. 9(2), 171–185 (1995)CrossRefGoogle Scholar
  14. 14.
    Ma, J., Hu, Y., Loizou, P.C.: Objective measures for predicting speech intelligibility in noisy conditions based on new band-importance functions. J. Acoust. Soc. Am. 125(5), 3387–3405 (2009)CrossRefGoogle Scholar
  15. 15.
    Maekawa, K., Koiso, H., Furui, S., Isahara, H.: Spontaneous speech corpus of Japanese. In: Proc. Second International Conference on Language Resources and Evaluation, pp. 947–952. AthensGoogle Scholar
  16. 16.
    Middag, C., Margens, J.P., Nuffelen, G.V.: Automated intelligibility assessment of pathological speech using phonological features. EURASIP J. Adv. Signal Process. M.D. (2009). (2009)Google Scholar
  17. 17.
    Rice University: Signal Processing Information Base (SPIB). http://spib.rice.edu/spib/select_noise.html
  18. 18.
    Takano, Y., Kondo, K.: Estimation of speech intelligibility using speech recognition systems. IEICE Trans. Inf. Sys. 93-D(12), 3368–3376 (2010)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  1. 1.Department of Electrical Engineering, Graduate School of Science and EngineeringYamagata UniversityYamagataJapan

Personalised recommendations