Speaker identification based on the frame linear predictive coding spectrum technique

Jian Da Wu, Bing Fu Lin

Research output: Contribution to journalArticle

18 Citations (Scopus)

Abstract

In this paper, a frame linear predictive coding spectrum (FLPCS) technique for speaker identification is presented. Traditionally, linear predictive coding (LPC) was applied in many speech recognition applications, nevertheless, the modification of LPC termed FLPCS is proposed in this study for speaker identification. The analysis procedure consists of feature extraction and voice classification. In the stage of feature extraction, the representative characteristics were extracted using the FLPCS technique. Through the approach, the size of the feature vector of a speaker can be reduced within an acceptable recognition rate. In the stage of classification, general regression neural network (GRNN) and Gaussian mixture model (GMM) were applied because of their rapid response and simplicity in implementation. In the experimental investigation, performances of different order FLPCS coefficients which were induced from the LPC spectrum were compared with one another. Further, the capability analysis on GRNN and GMM was also described. The experimental results showed GMM can achieve a better recognition rate with feature extraction using the FLPCS method. It is also suggested the GMM can complete training and identification in a very short time.

Original languageEnglish
Pages (from-to)8056-8063
Number of pages8
JournalExpert Systems with Applications
Volume36
Issue number4
DOIs
Publication statusPublished - 2009 May 1

Fingerprint

Feature extraction
Neural networks
Speech recognition
Identification (control systems)

All Science Journal Classification (ASJC) codes

  • Engineering(all)
  • Computer Science Applications
  • Artificial Intelligence

Cite this

@article{28105864009e4315a2686c4c9c3a3114,
title = "Speaker identification based on the frame linear predictive coding spectrum technique",
abstract = "In this paper, a frame linear predictive coding spectrum (FLPCS) technique for speaker identification is presented. Traditionally, linear predictive coding (LPC) was applied in many speech recognition applications, nevertheless, the modification of LPC termed FLPCS is proposed in this study for speaker identification. The analysis procedure consists of feature extraction and voice classification. In the stage of feature extraction, the representative characteristics were extracted using the FLPCS technique. Through the approach, the size of the feature vector of a speaker can be reduced within an acceptable recognition rate. In the stage of classification, general regression neural network (GRNN) and Gaussian mixture model (GMM) were applied because of their rapid response and simplicity in implementation. In the experimental investigation, performances of different order FLPCS coefficients which were induced from the LPC spectrum were compared with one another. Further, the capability analysis on GRNN and GMM was also described. The experimental results showed GMM can achieve a better recognition rate with feature extraction using the FLPCS method. It is also suggested the GMM can complete training and identification in a very short time.",
author = "Wu, {Jian Da} and Lin, {Bing Fu}",
year = "2009",
month = "5",
day = "1",
doi = "10.1016/j.eswa.2008.10.051",
language = "English",
volume = "36",
pages = "8056--8063",
journal = "Expert Systems with Applications",
issn = "0957-4174",
publisher = "Elsevier Limited",
number = "4",

}

Speaker identification based on the frame linear predictive coding spectrum technique. / Wu, Jian Da; Lin, Bing Fu.

In: Expert Systems with Applications, Vol. 36, No. 4, 01.05.2009, p. 8056-8063.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Speaker identification based on the frame linear predictive coding spectrum technique

AU - Wu, Jian Da

AU - Lin, Bing Fu

PY - 2009/5/1

Y1 - 2009/5/1

N2 - In this paper, a frame linear predictive coding spectrum (FLPCS) technique for speaker identification is presented. Traditionally, linear predictive coding (LPC) was applied in many speech recognition applications, nevertheless, the modification of LPC termed FLPCS is proposed in this study for speaker identification. The analysis procedure consists of feature extraction and voice classification. In the stage of feature extraction, the representative characteristics were extracted using the FLPCS technique. Through the approach, the size of the feature vector of a speaker can be reduced within an acceptable recognition rate. In the stage of classification, general regression neural network (GRNN) and Gaussian mixture model (GMM) were applied because of their rapid response and simplicity in implementation. In the experimental investigation, performances of different order FLPCS coefficients which were induced from the LPC spectrum were compared with one another. Further, the capability analysis on GRNN and GMM was also described. The experimental results showed GMM can achieve a better recognition rate with feature extraction using the FLPCS method. It is also suggested the GMM can complete training and identification in a very short time.

AB - In this paper, a frame linear predictive coding spectrum (FLPCS) technique for speaker identification is presented. Traditionally, linear predictive coding (LPC) was applied in many speech recognition applications, nevertheless, the modification of LPC termed FLPCS is proposed in this study for speaker identification. The analysis procedure consists of feature extraction and voice classification. In the stage of feature extraction, the representative characteristics were extracted using the FLPCS technique. Through the approach, the size of the feature vector of a speaker can be reduced within an acceptable recognition rate. In the stage of classification, general regression neural network (GRNN) and Gaussian mixture model (GMM) were applied because of their rapid response and simplicity in implementation. In the experimental investigation, performances of different order FLPCS coefficients which were induced from the LPC spectrum were compared with one another. Further, the capability analysis on GRNN and GMM was also described. The experimental results showed GMM can achieve a better recognition rate with feature extraction using the FLPCS method. It is also suggested the GMM can complete training and identification in a very short time.

UR - http://www.scopus.com/inward/record.url?scp=60249103352&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=60249103352&partnerID=8YFLogxK

U2 - 10.1016/j.eswa.2008.10.051

DO - 10.1016/j.eswa.2008.10.051

M3 - Article

AN - SCOPUS:60249103352

VL - 36

SP - 8056

EP - 8063

JO - Expert Systems with Applications

JF - Expert Systems with Applications

SN - 0957-4174

IS - 4

ER -