Incorporation of time varying AR modeling in speech recognition system based on dynamic programming

Author

Babin, Zafrir ; Flomen, Felix A. ; Shallom, Ilan D.

Author_Institution

Dept. of Electr. & Comput. Eng., Ben-Gurion Univ., Beer-Sheva, Israel

fYear

1991

fDate

5-7 Mar 1991

Firstpage

289

Lastpage

292

Abstract

Two isolated-word speaker-independent recognition systems are based on non-stationary representations of the speech signal. The first system is based on a time-varying linear prediction model. This recognition system is distinguishable by incorporation of the model and appropriate extension of the log likelihood ratio (LLR) distortion measure. The second system is based on the lattice model represented by time-varying reflection coefficients In this System, the distortion measure used is the Euclidean distance. In order to support this system properly, the extension of the LLR was modified

Keywords

dynamic programming; filtering and prediction theory; speech recognition; time-varying systems; Euclidean distance; dynamic programming; isolated word recognition; lattice model; log likelihood ratio; speaker-independent recognition systems; speech recognition; time-varying autoregressive modelling; time-varying linear prediction model; time-varying reflection coefficients; Distortion measurement; Dynamic programming; Equations; Filters; Lattices; Linear predictive coding; Reflection; Speech recognition; Testing; Time varying systems;

fLanguage

English

Publisher

ieee

Conference_Titel

Electrical and Electronics Engineers in Israel, 1991. Proceedings., 17th Convention of

Conference_Location

Tel Aviv

Print_ISBN

0-87942-678-0

Type

conf

DOI

10.1109/EEIS.1991.217640

Filename

217640