Abstract
It is well known that speech signals constitute highly structured objects which are composed of different kinds of subobjects such as words, phonemes, etc. This fact has motivated several researchers to propose different models which more or less explicitly assume the structural nature of speech. Notable examples of these models are Markov models /Bak 75/, /Jel 76/; the famous Harpy /Low 76/; Scriber and Lafs /Kla 80/; and many others works in which the convenience of some structural model of the speech objects considered is explicitly claimed /Gup 82/, /Lev 83/, /Cra 84/, /Sca 85/, /Kam 85/, /Sau 85/, /Rab 85/, /Kop 85/, /Sch 85/, /Der 86/, /Tan 86/.
Work partially suported by grant N. PA85-0086 of the Spanish CAICYT.
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
Angluin D. “On the complexity of minimun inference of regular sets”. Information and Control (39), 1978.
Baker J. “Stochastic modeling for automatic speech understanding”. Speech recognition, R. Reddy Ed. Ac. Press, 1975.
Cravero M. et al. “Syntax driven recognition of connected words by Markov models”. ICASSP 1984.
Derouault A., Merialdo B. “Natural modeling for phoneme-to-text transcription”. PAMI-8 (6), 1986.
English T., Boggess L. “A grammatical approach to reducing the statistical sparsity of languages models in natural domains”. ICASSP, 1986.
Fu K.S., Booth T. L. “Grammatical Inference: Introduction and Survey”. Parts 1 and 2. IEEE Trans. Syst. Man Cybern. SMC-5, 1975.
Gupta V., Mermelstein P. “Effects of speaker accent on the performance of a speaker-independent IWR”. Ac. Soc. or America (71, 6), 1982.
Jelinek F. “Continuous speech rec. by statistical methods”. IEEE (64,4), 1976
Kamp Y. “State reduction in Hidden Markov chains used for speech recognition”. IEEE, ASSP-33, (4), 1985.
KLatt D. “Scriber and Lafs: Two new approach to speech analysis”. W.A. Lee, Ed. Trends in speech recgg. Prentice-Hall, 1980.
Kohonen T. “Dinamically expanding context, with application…”. 8 th. ICFR, 1986.
Kopec G., Bush M. “Network-Based isolated digit recognition using vector quantization”. IEEE Trans. ASSP-33 (4), 1985.
Lee K. “Incremental network generation in word recognition”. ICASSP, 1986.
Levinson S. “Some experiments with a linguistic processor for continuous speech rec.”. IEEE, ASSP-31 (6), 1983.
Lowerre B. T. “The Harpy speech recognition system”. Intern report, Carnegie- Mellon University, 1976.
Rabiner L., Levinson S. “A speaker-indep., syntax-directed, CWR system based on HMM and level building”. IEEE Trans. ASSP-33 (3), 1985.
Rulot H., Vidal E. “Modelling (sub) string-length-based constraints through a Grammatical Inference method”. Devijver, Kittler eds. Springer, 1987.
Sauter L. “Isolated word rec. using a segmental approach”. ICASSP, 1985.
Scagliola C. “Language models and search algorithms for real-time speech recognition”. Int. J. Man-machine studies, (22) 1985.
Schwartz R. et al. “Context dependent modeling for acoustic-phonetic recognition of continuous speech”. ICASSP, 1985.
Smith A.R. et al. “Application of sequential pattern learning system to connected speech recognition”. ICASSP, 1985.
Tanaka K. et al. “A demiphoneme network representation of speech…”. ICASSP, 1986.
Thomason M. et al. “Experiments in dynamic programming inference of Markov networks with string representing speech data”. Patt. rec. (19, 5). 1986.
Venta O., Kohonen T. “A non-stochastic method for the correction of sentences”. 8 th. ICFR, 1986.
Vidal E. et al. “On the use of the Morphic Generator Grammatical Inference (MGGI) methodology in ASR”. Also in this book, 1987.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1988 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Vidal, E., Prieto, N., Sanchis, E., Rulot, H. (1988). Application of the Error Correcting Grammatical Inference Method (ECGI) to Multi-Speaker Isolated Word Recognition. In: Niemann, H., Lang, M., Sagerer, G. (eds) Recent Advances in Speech Understanding and Dialog Systems. NATO ASI Series, vol 46. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-83476-9_32
Download citation
DOI: https://doi.org/10.1007/978-3-642-83476-9_32
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-83478-3
Online ISBN: 978-3-642-83476-9
eBook Packages: Springer Book Archive