Abstract
In this paper we present an HMM “phonetic” training system and its performance both in recognition and label alignment tasks. Results on recognition using DARPA RM database and on label alignment using EUROM-0 SAM- ESPRIT database will be presented. Detailed description of the different systems is also presented. This work has been developed within the framework of the POLYGLOT-ESPRIT project no. 2104.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Esprit Project 2598 (SAM). Interim Report. Year Two. 1-III-90 to 28-11-91. Ref: SAM-UCL-G003.
Paul Dalsgaard, O. Andersen and W. Barry, “Multi lingual label alignment using acoustic phonetic features derived by neural network technique”, ICASSP 91.
Frank K. Soong, “On the automatic segmentation of speech signals”, ICASSP 87.
Kai Fu Lee, “Large Vocabulary Speaker Independent Continuous Speech Recognition: The SPHINX System”, CMU 1988.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1995 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Ferreiros, J., de Córdoba, R., Savoji, M.H., Pardo, J.M. (1995). Continuous Speech HMM Training System: Applications to Speech Recognition and Phonetic Label Alignment. In: Ayuso, A.J.R., Soler, J.M.L. (eds) Speech Recognition and Coding. NATO ASI Series, vol 147. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-57745-1_8
Download citation
DOI: https://doi.org/10.1007/978-3-642-57745-1_8
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-63344-7
Online ISBN: 978-3-642-57745-1
eBook Packages: Springer Book Archive