Relevancy of time-frequency features for phonetic classification measured by mutual information

Author

Yang, Hongming ; Van Vuuren, Sarel ; Hermansky, Hynek

Author_Institution

Dept. of Comput. Sci. & Eng., Oregon Graduate Inst. of Sci. & Technol., Beaverton, OR, USA

Volume

1

fYear

1999

fDate

15-19 Mar 1999

Firstpage

225

Abstract

In this paper we use mutual information to study the distribution in time and frequency of information relevant for phonetic classification. A large database of hand-labeled fluent speech is used to (a) compute the mutual information between phoneme labels and a point of logarithmic energy in the time-frequency plane and (b) compute the joint mutual information between phoneme labels and two points of logarithmic energy in the time-frequency plane

Keywords

feature extraction; information theory; signal classification; speech processing; speech recognition; statistical analysis; time-frequency analysis; automatic speech recognition; frequency distribution; hand-labeled fluent speech database; logarithmic energy; mutual information; phoneme labels; phonetic classification; speech signal analysis; time distribution; time-frequency features; time-frequency plane; Automatic speech recognition; Computer science; Databases; Electric variables measurement; Frequency measurement; Mutual information; Signal analysis; Speech analysis; Time frequency analysis; Time measurement;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 1999. Proceedings., 1999 IEEE International Conference on

Conference_Location

Phoenix, AZ

ISSN

1520-6149

Print_ISBN

0-7803-5041-3

Type

conf

DOI

10.1109/ICASSP.1999.758103

Filename

758103