5th European Conference on Speech Communication and Technology

Rhodes, Greece
September 22-25, 1997

Optimal State Dependent Spectral Representation for HMM Modeling : A New Theoretical Framework

C. Mokbel (1), G. Gravier (2), Gérard Chollet (2)

(1) France Telecom - CNET - DIH/RCP, Lannion, France
(2) ENST, dept Signal, Paris , France

In this paper we propose a theoretical framework to extend classical continuous density HMM in order to consider different spectral representations depending on the state. We stress the need for a reference space and for spectral transformations between the model spectral representation spaces and the reference space. We show that this framework permits to obtain more precise pdfs in the reference space. Preliminary speech recognition experiments for two spectral representations MFCC and linear frequency scale cepstral coefficients show no improvements ; however they identify that the choice of the spectral representations is crucial and the determination of the spaces transformations is a complex problem.

Full Paper

Bibliographic reference.  Mokbel, C. / Gravier, G. / Chollet, Gérard (1997): "Optimal state dependent spectral representation for HMM modeling : a new theoretical framework", In EUROSPEECH-1997, 1351-1354.