Adaptation in the Pronunciation Space for Non-Native Speech Recognition

Steidl S, Stemmer G, Hacker C, Nöth E (2004)

Publication Type: Conference contribution, Conference Contribution

Publication year: 2004

Original Authors: Steidl Stefan, Stemmer Georg, Hacker Christian, Nöth Elmar

Pages Range: 318-321

Conference Proceedings Title: Interspeech 2004 ICSLP, 8th International Conference on Spoken Language Processing, Jeju Island, Korea, Proceedings

Event location: Jeju Island KR

URI: http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2004/Steidl04-AIT.pdf

Abstract

We introduce a new technique to improve the recognition of non-native speech. The underlying assumption is that for each non-native pronunciation of a speech sound, there is at least one sound in the target language that has a similar native pronunciation. The adaptation is performed by HMM interpolation between adequate native acoustic models. The interpolation partners are determined automatically in a data-driven manner. Our experiments show that this technique is suitable for both the offline adaptation to a whole group of speakers as well as for the unsupervised online adaptation to a single speaker. Results are given both for spontaneous non-native English speech as well as for a set of read non-native German utterances.

Authors with CRIS profile

Stefan Steidl Lehrstuhl für Informatik 14 (Bild- und Sprachverarbeitung) Elmar Nöth Professur für Informatik (Mustererkennung)

How to cite

APA:

Steidl, S., Stemmer, G., Hacker, C., & Nöth, E. (2004). Adaptation in the Pronunciation Space for Non-Native Speech Recognition. In Kim S. H., Youn D. H. (Eds.), Interspeech 2004 ICSLP, 8th International Conference on Spoken Language Processing, Jeju Island, Korea, Proceedings (pp. 318-321). Jeju Island, KR.

MLA:

Steidl, Stefan, et al. "Adaptation in the Pronunciation Space for Non-Native Speech Recognition." Proceedings of the Interspeech 2004, Jeju Island Ed. Kim S. H., Youn D. H., 2004. 318-321.

BibTeX: Download