SPEAKER IDENTIFICATION BASED ON FREQUENCY DISTRIBUTION OF VECTOR-QUANTIZED SPECTRA.

Katsuhiko Shirai, Kazunori Mano, Shunichi Ishige

Research output: Contribution to journalArticle

Abstract

At present, one of the most important problems in speech recognition and speaker recognition is the extraction of individual information from the speech waveform. This paper describes the extraction of individual information by the vector-quantization and the text-independent speaker information based on that method. A feature vector is proposed which is the quantized distribution by the frequency of the vector-quantization code to represent the individual features of the speaker. The properties of the feature vector are investigated, and effectiveness is verified by an actual speaker-identification experiment. The quantization distribution is a feature representing the distribution density in the space for the acoustic features, e. g. , the spectrum uttered by the individual. As the acoustic feature parameters, the cepstrum for stationary part, and the change of the cepstrum, are used to construct the quantization distribution. The identification rates are compared.

Original languageEnglish
Pages (from-to)63-72
Number of pages10
JournalSystems and Computers in Japan
Volume19
Issue number6
Publication statusPublished - 1988 Jun
Externally publishedYes

Fingerprint

Vector quantization
Acoustics
Speech recognition
Experiments

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Hardware and Architecture
  • Information Systems
  • Theoretical Computer Science

Cite this

SPEAKER IDENTIFICATION BASED ON FREQUENCY DISTRIBUTION OF VECTOR-QUANTIZED SPECTRA. / Shirai, Katsuhiko; Mano, Kazunori; Ishige, Shunichi.

In: Systems and Computers in Japan, Vol. 19, No. 6, 06.1988, p. 63-72.

Research output: Contribution to journalArticle

@article{8520ae3bd2134c94a8cb66d011403269,
title = "SPEAKER IDENTIFICATION BASED ON FREQUENCY DISTRIBUTION OF VECTOR-QUANTIZED SPECTRA.",
abstract = "At present, one of the most important problems in speech recognition and speaker recognition is the extraction of individual information from the speech waveform. This paper describes the extraction of individual information by the vector-quantization and the text-independent speaker information based on that method. A feature vector is proposed which is the quantized distribution by the frequency of the vector-quantization code to represent the individual features of the speaker. The properties of the feature vector are investigated, and effectiveness is verified by an actual speaker-identification experiment. The quantization distribution is a feature representing the distribution density in the space for the acoustic features, e. g. , the spectrum uttered by the individual. As the acoustic feature parameters, the cepstrum for stationary part, and the change of the cepstrum, are used to construct the quantization distribution. The identification rates are compared.",
author = "Katsuhiko Shirai and Kazunori Mano and Shunichi Ishige",
year = "1988",
month = "6",
language = "English",
volume = "19",
pages = "63--72",
journal = "Systems and Computers in Japan",
issn = "0882-1666",
publisher = "John Wiley and Sons Inc.",
number = "6",

}

TY - JOUR

T1 - SPEAKER IDENTIFICATION BASED ON FREQUENCY DISTRIBUTION OF VECTOR-QUANTIZED SPECTRA.

AU - Shirai, Katsuhiko

AU - Mano, Kazunori

AU - Ishige, Shunichi

PY - 1988/6

Y1 - 1988/6

N2 - At present, one of the most important problems in speech recognition and speaker recognition is the extraction of individual information from the speech waveform. This paper describes the extraction of individual information by the vector-quantization and the text-independent speaker information based on that method. A feature vector is proposed which is the quantized distribution by the frequency of the vector-quantization code to represent the individual features of the speaker. The properties of the feature vector are investigated, and effectiveness is verified by an actual speaker-identification experiment. The quantization distribution is a feature representing the distribution density in the space for the acoustic features, e. g. , the spectrum uttered by the individual. As the acoustic feature parameters, the cepstrum for stationary part, and the change of the cepstrum, are used to construct the quantization distribution. The identification rates are compared.

AB - At present, one of the most important problems in speech recognition and speaker recognition is the extraction of individual information from the speech waveform. This paper describes the extraction of individual information by the vector-quantization and the text-independent speaker information based on that method. A feature vector is proposed which is the quantized distribution by the frequency of the vector-quantization code to represent the individual features of the speaker. The properties of the feature vector are investigated, and effectiveness is verified by an actual speaker-identification experiment. The quantization distribution is a feature representing the distribution density in the space for the acoustic features, e. g. , the spectrum uttered by the individual. As the acoustic feature parameters, the cepstrum for stationary part, and the change of the cepstrum, are used to construct the quantization distribution. The identification rates are compared.

UR - http://www.scopus.com/inward/record.url?scp=0024032634&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0024032634&partnerID=8YFLogxK

M3 - Article

VL - 19

SP - 63

EP - 72

JO - Systems and Computers in Japan

JF - Systems and Computers in Japan

SN - 0882-1666

IS - 6

ER -