Intelligibility is more than a single word: Quantification of speech intelligibility by ASR and prosody

Maier A, Haderlein T, Schuster M, Nkenke E, Nöth E (2007)


Publication Type: Conference contribution, Conference Contribution

Publication year: 2007

Original Authors: Maier Andreas, Haderlein Tino, Schuster Maria, Nkenke Emeka, Nöth Elmar

Publisher: Springer

City/Town: Berlin

Pages Range: 278-285

Conference Proceedings Title: Text, Speech and Dialogue

Event location: Pilsen CZ

URI: http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2007/Maier07-IIM.pdf

Abstract

In this paper we examine the quality of the prediction of intelligibility scores of human experts. Furthermore, we investigate the differences between subjective expert raters who evaluated speech disorders of laryngectomees and children with cleft lip and palate. We use the recognition rate of a word recognizer and prosodic features to predict the intelligibility score of each individual expert. For each expert and the mean opinion of all experts we present the best features to model their scoring behavior according to the mean rank obtained during a 10-fold cross-validation. In this manner all individual speech experts were modeled with a correlation coefficient of at least r >.75. The mean opinion of all raters is predicted with a correlation of r =.90 for the laryngectomees and r =.86 for the children.

Authors with CRIS profile

How to cite

APA:

Maier, A., Haderlein, T., Schuster, M., Nkenke, E., & Nöth, E. (2007). Intelligibility is more than a single word: Quantification of speech intelligibility by ASR and prosody. In Matousek Vaclav, Mautner Pavel (Eds.), Text, Speech and Dialogue (pp. 278-285). Pilsen, CZ: Berlin: Springer.

MLA:

Maier, Andreas, et al. "Intelligibility is more than a single word: Quantification of speech intelligibility by ASR and prosody." Proceedings of the 10th International Conference, TSD 2007, Pilsen Ed. Matousek Vaclav, Mautner Pavel, Berlin: Springer, 2007. 278-285.

BibTeX: Download