Abstract
An information based, two-stage DP procedure is proposed for phonemic HMM structure inference. It operates on the phonetic description of speech provided by means of an ergodic HMM. The resulting HMM, while comprising a quite large number of states, share the observation densities originated by the EHMM.
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
— P.Pierucci, A.Falaschi, M.Giustiniani, “Phonetic Units and Phonological Constraints representation by EHMM”, this volume
— A.Falaschi, “Continuosly variable Transition Probability HMM for speech recognition”, this volume
— A.Falaschi, P.Pierucci, “Some experiments on HMH Structure Inference”, Proc. EUSIPCO 90, Barcellona, SPAIN
— D.Jouvet,J.Monné,P.Dobois, “A new network-based speaker-independent connected word recognition system”, Proc. ICASSP-86, Tokyo
— L.R.Rabiner,C.M.Lee,B.H.Juang,J.G.Wilpon, “HMM Clustering for Connected Word Recognition”, Proc. Of ICASSP 1989, Glascom, UK
— F.Casacuberta,E.Vidal,B.Mas,H.Rulot, “Learning the Structure of HMM’s through Grammatical Inference Techniques”, Proc. of ICASSP 1990, Albuquerque, MN, USA
— A.Falaschi, “A Word-like Phonetic Sequence Statistical Source Model for Large Lexicon Automatic Speech Recognition Systems”, 1st ECST, Sept.1987, Edinburgh, UK
— X.D.Huang,M.A.Jack, “Unified techniques for Vector Quantization and Hidden Markov Modeling using Semi-Continuous Models”, proc. of ICASSP 1989, Glascom, UK
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1992 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Falaschi, A. (1992). Phonetic Structure Inference of Phonemic HMM. In: Laface, P., De Mori, R. (eds) Speech Recognition and Understanding. NATO ASI Series, vol 75. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-76626-8_5
Download citation
DOI: https://doi.org/10.1007/978-3-642-76626-8_5
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-76628-2
Online ISBN: 978-3-642-76626-8
eBook Packages: Springer Book Archive