A study on the robust speaker recognition algorithm in noise surroundings

Jung Jong Soon

Journal of The Korea Society of Computer and Information

Abbr : JKSCI
2005, 10(6), pp.47-54
Publisher : The Korean Society Of Computer And Information
Research Area : Computer Science

Jung Jong Soon ¹

¹상지영서대학교

ABSTRACT

In the most of speaker recognition system, speaker's characteristics is extracted from acoustic parameter by speech analysis and we make speaker's reference pattern. Parameters used in speaker recognition system are desirable expressing speaker's characteristics fully and being a few difference whenever it is spoken. Therefore we suggest following to solve this problem. This paper is proposed to use strong spectrum characteristic in non-noise circumstance and prosodic information in noise circumstance. In a stage of making code book, we make the number of data we need to combine spectrum characteristic and prosodic information. We decide acceptance or rejection comparing test pattern and each model distance. As a result, we obtained more improved recognition rate than we use spectrum and prosodic information especially we obtained stational recognition rate in noise circumstance.
KEYWORDS

prosodic information, code book, pitch ratio
REFERENCES (10)

[journal] / 199309 / “A Speech Prosody Conversion System with a high Quality Speech Analysis-Synthesis Method” : 995~

[journal] / 1983 / “Changing Pitch and Duration in LPC Synthesised Speech using Multipulse Excitation

[journal] / 1997 / Palm “A New codebook Training algorithm for VQ-base speaker recognition” : 1091~

[journal] / “Automatic Speaker Recognition based on Pitch Con-tours ” Journal of the Acoustical Society of America : 1687~

[journal] / 1991 / Advance in Speech Coding / Kluwer Academic Publisher

[journal] / 1996 / “Robust Prosodic Features for Speaker Identification”

[journal] / 1997 / “A New Codebook Training algorithm for VQ-based speaker recognition” : 1091~

[journal] / 1995 / “A study on the performance improvement of speaker recognition using average pattern and weighted cepstrum” : 179~

[journal] / 2002 / “음성인식 시스템에서의 잡음 제거 개선에 관한 연구” : 2~

[journal] / 2000 / “음성을 이용한 화자 검증기 설계 및 구현” : 92~
KCI Citation (0)

KJC Korea
Journal Central

Statistics

Tools