Dynamic features for segmental speech recognition

Author

Harte, Naomi ; Vaseghi, Saeed ; Milner, Ben

Author_Institution

Sch. of Electr. Eng. & Comput. Sci., Queen´´s Univ., Belfast, UK

Volume

2

fYear

1996

fDate

3-6 Oct 1996

Firstpage

933

Abstract

Speech models and features that emphasise the dynamic aspects of speech can provide improved speech recognition. The cepstral time matrix has been established as a successful method of encoding dynamics. The paper extends this set of dynamic features, considering cepstral time features on both a segmental and subsegmental level. This offers the potential of using a conditional PDF for the state observation within a HMM and incorporating this into the training stage. Methods of linear discriminative analysis are applied to the new feature set to identify the subset of features making the greatest contribution to the task of recognition

Keywords

cepstral analysis; hidden Markov models; speech coding; speech recognition; cepstral time features; cepstral time matrix; conditional PDF; dynamic features; dynamics encoding; hidden Markov model; linear discriminative analysis; segmental speech recognition; speech features; speech models; state observation; subsegmental level; training stage; Band pass filters; Cepstral analysis; Computer science; Covariance matrix; Discrete cosine transforms; Hidden Markov models; Laboratories; Speech analysis; Speech recognition; Telecommunications;

fLanguage

English

Publisher

ieee

Conference_Titel

Spoken Language, 1996. ICSLP 96. Proceedings., Fourth International Conference on

Conference_Location

Philadelphia, PA

Print_ISBN

0-7803-3555-4

Type

conf

DOI

10.1109/ICSLP.1996.607755

Filename

607755