Abstract
The incorporation of context modelling to a Spanish Inferred Stochastic Regular Grammar -based continuous acoustic phonetic decoder, lead to a Speaker-Independent recognition phone accuracy of 75% and 72% for the Vocabulary Dependent and the Vocabulary Independent tests, respectively. The major novelty of this work is the modelling approach chosen in order to tackle the general problem of context-modelling: stochastic regular grammars inferred automatically from speech samples via the Semi-Continuous Morphic Generator Grammatical Inference methodology.
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
H.W. Hon, K.F. Lee: “On vocabulary-independent Speech Modelling”, Proc. IEEE Int. Conf. Acoust., Speech, Signal Processing, pp.725–728, 1990.
I. Galiano, E. Sanchis, I. Torres, F. Casacuberta: “Acoustic-Phonetic Decoding of Spanish Continuous Speech”, International Journal on Pattern Recognition and Artificial Intelligence. To be published in January, 1994.
I. Galiano and F. Casacuberta: “Experiments on Spanish Phone Recognition using automatically derived phonemic baseforms”, Proce. EUROSPEECH-93, Berlin, 1993.
M.I. Torres: “Selección de unidades subléxicas para la decodificación acústico-fonética del hablaen Castellano”, Internal Report, D.S I.C. Univ. Politécnica de Valencia, 1992.
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
Galiano, I., Casacuberta, F., Sanchis, E. (1995). Modelling Phone-Context in Spanish by Using SCMGGI Models. 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_38
Download citation
DOI: https://doi.org/10.1007/978-3-642-57745-1_38
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-63344-7
Online ISBN: 978-3-642-57745-1
eBook Packages: Springer Book Archive