Enhancing automatic speaker identification using phoneme clustering and frame based parameter and frame size selection

Author

Pelecanos, J. ; Slomka, S. ; Sridharan, S.

Author_Institution

Sch. of Electr. & Electron. Syst. Eng., Queensland Univ. of Technol., Brisbane, Qld., Australia

Volume

2

fYear

1999

fDate

1999

Firstpage

633

Abstract

The aim of this study is to investigate variations in speaker Identification performance for the various American English phonemes for different speech parameterisation types and frame sizes. Results on KING wideband data indicate that various phonemes have different optimal parameterisation types and frame sizes. A system able to utilise these alternatives is proposed. The system is shown to improve SI system performance when optimal parameterisation schemes are substituted for each phoneme

Keywords

pattern clustering; speaker recognition; American English phonemes; KING wideband data; SI system performance; automatic speaker identification; frame based parameter selection; frame size selection; phoneme clustering; speech parameterisation; Acoustic signal processing; Australia; Cepstral analysis; Hidden Markov models; Laboratories; Speech enhancement; Speech recognition; System performance; Systems engineering and theory; Wideband;

fLanguage

English

Publisher

ieee

Conference_Titel

Signal Processing and Its Applications, 1999. ISSPA '99. Proceedings of the Fifth International Symposium on

Conference_Location

Brisbane, Qld.

Print_ISBN

1-86435-451-8

Type

conf

DOI

10.1109/ISSPA.1999.815752

Filename

815752