Information based speech transduction

Authors

  • Peter Juel Henrichsen Center for Computational Modelling of Language, Copenhagen Business School
  • Thomas Ulrich Christiansen Centre for Applied Hearing Research, Technical University of Denmark, DK-2800 Lyngby, Denmark

Abstract

Modern hearing aids use a variety of advanced digital signal processing methods in order to improve speech intelligibility. These methods are based on knowledge about the acoustics outside the ear as well as psychoacoustics. We present a novel observation based on the fact that acoustic prominence is not equal to information prominence for time intervals at the syllabic and sub-syllabic levels. The idea is that speech elements with a high degree of information can be robustly identified based on basic acoustic properties. We evaluated the correlation of (information rich) content words in the DanPASS corpus with fundamental frequency (F0) and spectral tilt across four frequency bands. Our results show a correlation of certain band-level differences and the presence of content words. Similarly, but to a lesser extent, a correlation between F0 and the presence of content words was found. The principle described here has the potential to improve the “information-to-noise” ratio in hearing aids. In addition, this concept may also be applicable in automatic speech recognition systems.

References

Black, A. W. and K. A. Lenzo (2007). “Building Synthetic Voices, Carnegie Mellon University” www.festvox.org/, www.cs.cmu.edu/~lenzo/.

Boersma, P. (2001). ”Praat, a system for doing phonetics by computer” Glot International, 5 (9/10), 341–345.

Dik, S. C. (1997). The Theory of Functional Grammar, Part 1: The Structure of the Clause, 2nd ed., Mouton de Gruyter, Berlin.

Grønnum, N. (2009). “A Danish phonetically annotated spontaneous speech corpus (DanPASS)” Speech Communication 51, 594–603.

Henrichsen, P. J. (2011). “Fishing in a speech stream, angling for a lexicon” Proceedings of 18th Nordic conference of computational linguistics NODALIDA, Pedersen, B. S., Nespore, G. and Skadina, I. (Eds.), pp. 90–97.

Jurafsky, D. and Martin, J. H. (2009). Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition, 2nd edition. Prentice-Hall.

Klammer, T., Schulz, M. R. and Volpe, A. D. (2009). Analyzing English Grammar 6th edition, Longman.

Moore, B. J. C. M. (2003). An introduction to the psychology of Hearing, 5th edition, Academic Press, pp. 72-75.

Uneson, M. and P. J. Henrichsen (2011). ”Expanding a Corpus of Closed-World Descriptions by Semantic Unit Selection” accepted for the Proceedings of Computational Linguistic Applications, Warsaw, October 2011

Additional Files

Published

2011-12-15

How to Cite

Henrichsen, P. J., & Christiansen, T. U. (2011). Information based speech transduction. Proceedings of the International Symposium on Auditory and Audiological Research, 3, 457–464. Retrieved from http://proceedings.isaar.eu/index.php/isaarproc/article/view/2011-53

Issue

Section

2011/4. Recent concepts in hearing-instrument processing and fitting