ISCA Archive Interspeech 2013
ISCA Archive Interspeech 2013

Language-universal speech audiometry with automated scoring

Bart Vaerenberg, Louis ten Bosch, Wojtek Kowalczyk, Martine Coene, Herwig De Smet, Paul J. Govaerts

The clinical assessment of speech discrimination by professional audiologists is resource intensive. Yet discrepancies in language or dialect between the test subject and the audiologist may cause a significant bias in the test result. To address these issues, a speech audiometric test (SAT) has been designed to be language/dialect independent and to allow automated scoring by means of an MFCCbased Dynamic Time Warping alignment measure. A Pearson correlation of 0.83 was found between the automatic scores and human phoneme scoring. Normative data were obtained and compared to conventional SATs which revealed differences in speech reception thresholds within 2 dB.


doi: 10.21437/Interspeech.2013-317

Cite as: Vaerenberg, B., Bosch, L.t., Kowalczyk, W., Coene, M., Smet, H.D., Govaerts, P.J. (2013) Language-universal speech audiometry with automated scoring. Proc. Interspeech 2013, 3608-3612, doi: 10.21437/Interspeech.2013-317

@inproceedings{vaerenberg13_interspeech,
  author={Bart Vaerenberg and Louis ten Bosch and Wojtek Kowalczyk and Martine Coene and Herwig De Smet and Paul J. Govaerts},
  title={{Language-universal speech audiometry with automated scoring}},
  year=2013,
  booktitle={Proc. Interspeech 2013},
  pages={3608--3612},
  doi={10.21437/Interspeech.2013-317}
}