An investigation of modelling aspects for rate-dependent speech recognition

Wrede B, Fink GA, Sagerer G (2001)
In: Proc. European Conf. on Speech Communication and Technology. 4. Aalborg: 2527-2530.

Conference Paper | Published | English

No fulltext has been uploaded

Author
Abstract
For the modelling of speech rate variation in speech recognition many approaches have been suggested. However, the training of speech-rate dependent models has by far received most of the attention. In order to investigate problematic aspects related with the classification of the speech data which represents one of the major problems of these approaches extensive experiments were carried out on a German corpus of read speech. The results indicate that while the kind of the model-driven speech-rate measure is only of minor importance a data-driven classification of the speech data significantly improves the performance of rate-dependent models. Further results suggest a detailed modelling of speech rate based on more general models. This means that it might be possible to model speech rate adaptation by means of a transformation based on a continuous measure.
Publishing Year
PUB-ID

Cite this

Wrede B, Fink GA, Sagerer G. An investigation of modelling aspects for rate-dependent speech recognition. In: Proc. European Conf. on Speech Communication and Technology. Vol 4. Aalborg; 2001: 2527-2530.
Wrede, B., Fink, G. A., & Sagerer, G. (2001). An investigation of modelling aspects for rate-dependent speech recognition. Proc. European Conf. on Speech Communication and Technology, 4, 2527-2530.
Wrede, B., Fink, G. A., and Sagerer, G. (2001). “An investigation of modelling aspects for rate-dependent speech recognition” in Proc. European Conf. on Speech Communication and Technology, vol. 4, (Aalborg), 2527-2530.
Wrede, B., Fink, G.A., & Sagerer, G., 2001. An investigation of modelling aspects for rate-dependent speech recognition. In Proc. European Conf. on Speech Communication and Technology. no.4 Aalborg, pp. 2527-2530.
B. Wrede, G.A. Fink, and G. Sagerer, “An investigation of modelling aspects for rate-dependent speech recognition”, Proc. European Conf. on Speech Communication and Technology, vol. 4, Aalborg: 2001, pp.2527-2530.
Wrede, B., Fink, G.A., Sagerer, G.: An investigation of modelling aspects for rate-dependent speech recognition. Proc. European Conf. on Speech Communication and Technology. 4, p. 2527-2530. Aalborg (2001).
Wrede, Britta, Fink, Gernot A., and Sagerer, Gerhard. “An investigation of modelling aspects for rate-dependent speech recognition”. Proc. European Conf. on Speech Communication and Technology. Aalborg, 2001.Vol. 4. 2527-2530.
This data publication is cited in the following publications:
This publication cites the following data publications:

Export

0 Marked Publications

Open Data PUB

Search this title in

Google Scholar