VOICE CONVERSION THROUGH VECTOR QUANTIZATION.

Masanobu Abe, Satoshi Nakamura, Kiyohiro Shikano, Hisao Kuwabara

Research output: Chapter in Book/Report/Conference proceedingConference contribution

326 Citations (Scopus)

Abstract

A voice conversion technique using vector quantization and spectrum mapping is proposed. The basic idea is to create mapping codebooks which represent the correspondence between different speakers' codebooks. The mapping codebooks for spectrum parameters, power values, and pitch frequencies are separately generated using training utterances. This technique makes it possible to precisely control voice individuality. To evaluate the performance of this technique, hearing tests were carried out on two kinds of voice conversions. One is a conversion between male and female speakers, the other is a conversion between male speakers. In the male-to-female conversion experiment, all converted utterances were judged as female, and in the male-to-male conversion, 65% of them were identified as the target speaker.

Original languageEnglish
Title of host publicationICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
PublisherIEEE
Pages655-658
Number of pages4
Publication statusPublished - 1988
Externally publishedYes

Fingerprint

vector quantization
Vector quantization
Audition
voice control
hearing
education
Experiments

ASJC Scopus subject areas

  • Signal Processing
  • Electrical and Electronic Engineering
  • Acoustics and Ultrasonics

Cite this

Abe, M., Nakamura, S., Shikano, K., & Kuwabara, H. (1988). VOICE CONVERSION THROUGH VECTOR QUANTIZATION. In ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings (pp. 655-658). IEEE.

VOICE CONVERSION THROUGH VECTOR QUANTIZATION. / Abe, Masanobu; Nakamura, Satoshi; Shikano, Kiyohiro; Kuwabara, Hisao.

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. IEEE, 1988. p. 655-658.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abe, M, Nakamura, S, Shikano, K & Kuwabara, H 1988, VOICE CONVERSION THROUGH VECTOR QUANTIZATION. in ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. IEEE, pp. 655-658.
Abe M, Nakamura S, Shikano K, Kuwabara H. VOICE CONVERSION THROUGH VECTOR QUANTIZATION. In ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. IEEE. 1988. p. 655-658
Abe, Masanobu ; Nakamura, Satoshi ; Shikano, Kiyohiro ; Kuwabara, Hisao. / VOICE CONVERSION THROUGH VECTOR QUANTIZATION. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. IEEE, 1988. pp. 655-658
@inproceedings{12a83159175b41df84c139a283510ec5,
title = "VOICE CONVERSION THROUGH VECTOR QUANTIZATION.",
abstract = "A voice conversion technique using vector quantization and spectrum mapping is proposed. The basic idea is to create mapping codebooks which represent the correspondence between different speakers' codebooks. The mapping codebooks for spectrum parameters, power values, and pitch frequencies are separately generated using training utterances. This technique makes it possible to precisely control voice individuality. To evaluate the performance of this technique, hearing tests were carried out on two kinds of voice conversions. One is a conversion between male and female speakers, the other is a conversion between male speakers. In the male-to-female conversion experiment, all converted utterances were judged as female, and in the male-to-male conversion, 65{\%} of them were identified as the target speaker.",
author = "Masanobu Abe and Satoshi Nakamura and Kiyohiro Shikano and Hisao Kuwabara",
year = "1988",
language = "English",
pages = "655--658",
booktitle = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",
publisher = "IEEE",

}

TY - GEN

T1 - VOICE CONVERSION THROUGH VECTOR QUANTIZATION.

AU - Abe, Masanobu

AU - Nakamura, Satoshi

AU - Shikano, Kiyohiro

AU - Kuwabara, Hisao

PY - 1988

Y1 - 1988

N2 - A voice conversion technique using vector quantization and spectrum mapping is proposed. The basic idea is to create mapping codebooks which represent the correspondence between different speakers' codebooks. The mapping codebooks for spectrum parameters, power values, and pitch frequencies are separately generated using training utterances. This technique makes it possible to precisely control voice individuality. To evaluate the performance of this technique, hearing tests were carried out on two kinds of voice conversions. One is a conversion between male and female speakers, the other is a conversion between male speakers. In the male-to-female conversion experiment, all converted utterances were judged as female, and in the male-to-male conversion, 65% of them were identified as the target speaker.

AB - A voice conversion technique using vector quantization and spectrum mapping is proposed. The basic idea is to create mapping codebooks which represent the correspondence between different speakers' codebooks. The mapping codebooks for spectrum parameters, power values, and pitch frequencies are separately generated using training utterances. This technique makes it possible to precisely control voice individuality. To evaluate the performance of this technique, hearing tests were carried out on two kinds of voice conversions. One is a conversion between male and female speakers, the other is a conversion between male speakers. In the male-to-female conversion experiment, all converted utterances were judged as female, and in the male-to-male conversion, 65% of them were identified as the target speaker.

UR - http://www.scopus.com/inward/record.url?scp=0023739214&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0023739214&partnerID=8YFLogxK

M3 - Conference contribution

SP - 655

EP - 658

BT - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

PB - IEEE

ER -