Individual speech recognition in noise, the audiogram and more: Using automatic speech recognition (ASR) as a modelling tool

  • Birger Kollmeier Medizinische Physik and Cluster of Excellence Hearing4all, Universität Oldenburg, Oldenburg, Germany
  • Marc René Schädler Medizinische Physik and Cluster of Excellence Hearing4all, Universität Oldenburg, Oldenburg, Germany
  • Anna Warzybok Medizinische Physik and Cluster of Excellence Hearing4all, Universität Oldenburg, Oldenburg, Germany
  • Bernd T. Meyer Medizinische Physik and Cluster of Excellence Hearing4all, Universität Oldenburg, Oldenburg, Germany
  • Thomas Brand Medizinische Physik and Cluster of Excellence Hearing4all, Universität Oldenburg, Oldenburg, Germany

Abstract

To characterize the individual patient’s hearing impairment, a framework for auditory discrimination experiments (FADE, Schädler et al., 2015) was extended here using different degrees of individualization. FADE has been shown to predict the outcome of both speech recognition tests and psychoacoustic experiments based on simulations using an automatic speech recognition (ASR) system which  requires only few assumptions. It builds on the closed-set matrix sentence recognition test which is advantageous for testing individual speech recognition in a way comparable across languages. Individual predictions of speech recognition thresholds in stationary and in fluctuating noise were derived using the audiogram and an estimate of the internal detector noise (“level uncertainty”). Either “typical” audiogram shapes with or without a “typical” level uncertainty or the individual data were used for individual predictions. As a result, the individualisation of the level uncertainty was found to be more important than the exact shape of the individual audiogram to accurately model the outcome of the German matrix test in stationary or fluctuating noise for listeners with hearing impairment.

References

ANSI (1997). S3.5 Methods for Calculation of the Speech Intelligibility Index. Standards Secretariat, Acoustical Society of America.

Bisgaard, N., Vlaming, M.S., and Dahlquist, M. (2010) “Standard audiograms for the IEC 60118-15 measurement procedure,” Trends Amplif., 14, 113-120.

Brand,T. and Kollmeier, B. (2002). “Vorhersage der Sprachverständlichkeit in Ruhe und im Störgeräusch aufgrund des Reintonaudiogramms,” Proc. 5. Jahrestagung der Deutschen Gesellschaft für Audiologie, Zürich.

Dau, T., Kollmeier, B., and Kohlrausch, A. (1997). “Modeling auditory processing of amplitude modulation: I. Detection and masking with narrow band carrier,” J. Acoust. Soc. Am., 102, 2892-2905.

Holube, I. and Kollmeier, B. (1996). “Speech intelligibility prediction in hearing‐impaired listeners based on a psychoacoustically motivated perception model,” J. Acoust. Soc. Am., 100, 1703-1716.

Jürgens, T. and Brand, T. (2009). “Microscopic prediction of speech recognition for listeners with normal hearing in noise using an auditory model,” J. Acoust. Soc. Am., 126, 2635-2648.

Kollmeier, B., Warzybok, A., Hochmuth, S., Zokoll, M., Uslar, V.N., Brand, T., and Wagener, K.C. (2015). “The multilingual matrix test: principles, applications and comparison across languages - a review,” Int. J. Audiol. Suppl., 54, 3-16.

Meyer, R.M. and Brand, T. (2013). “Comparison of different short-term Speech Intelligibility Index procedures in fluctuating noise for listeners with normal and impaired hearing,” Acta Acust. United Ac., 99, 442-446.

Plomp, R. (1978). “Auditory handicap of hearing impairment and the limited benefit of hearing aids,” J. Acoust. Soc. Am., 63, 533-549.

Schädler, M., Warzybok, A., Hochmuth, S., and Kollmeier, B. (2015). “Matrix sentence intelligibility prediction using an automatic speech recognition system,” Int. J. Audiol. Suppl., 54, 100-107.

Schädler, M.R., Warzybok, A., Ewert, S.F., and Kollmeier, B. (2016). “A simulation framework for auditory discrimination experiments: Revealing the importance of across-frequency processing in speech perception,” Submitted.

Wagener, K.C., Brand, T., Kollmeier, B. (2006). “The role of silent intervals for sentence intelligibility in fluctuating noise in hearing-impaired listeners,” Int. J. Audiol., 45, 26-33.
Published
2015-12-15
How to Cite
KOLLMEIER, Birger et al. Individual speech recognition in noise, the audiogram and more: Using automatic speech recognition (ASR) as a modelling tool. Proceedings of the International Symposium on Auditory and Audiological Research, [S.l.], v. 5, p. 149-156, dec. 2015. Available at: <https://proceedings.isaar.eu/index.php/isaarproc/article/view/2015-17>. Date accessed: 20 nov. 2017.