Speech morphing by gradually changing spectrum parameter and fundamental frequency

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

9 Citations (Scopus)

Abstract

This paper proposes a new application of speech modification called `speech morphing'. In image processing, morphing is a well known technique that gradually changes one person's face to that of someone else. Speech morphing produces similar results for speech; i.e., one person's speech is gradually changed to that of someone else. Speech morphing makes it possible to create movies or multi-media entertainment together with image morphing. The proposed algorithm pitch-synchronously modifies fundamental frequency(F0) and DFT spectrum and outputs high quality speech. To clarify the balance of F0 modification and spectrum modification, listening tests were carried out using 20 male speakers. The results yielded the relationship between the amount of modification and speaker identity. In terms of overall performance, listening tests show that the proposed algorithm successfully generates smooth, high quality voice changes.

Original languageEnglish
Title of host publicationInternational Conference on Spoken Language Processing, ICSLP, Proceedings
Editors Anon
PublisherIEEE
Pages2235-2238
Number of pages4
Volume4
Publication statusPublished - 1996
Externally publishedYes
EventProceedings of the 1996 International Conference on Spoken Language Processing, ICSLP. Part 1 (of 4) - Philadelphia, PA, USA
Duration: Oct 3 1996Oct 6 1996

Other

OtherProceedings of the 1996 International Conference on Spoken Language Processing, ICSLP. Part 1 (of 4)
CityPhiladelphia, PA, USA
Period10/3/9610/6/96

Fingerprint

Discrete Fourier transforms
Image processing

ASJC Scopus subject areas

  • Computer Science(all)

Cite this

Abe, M. (1996). Speech morphing by gradually changing spectrum parameter and fundamental frequency. In Anon (Ed.), International Conference on Spoken Language Processing, ICSLP, Proceedings (Vol. 4, pp. 2235-2238). IEEE.

Speech morphing by gradually changing spectrum parameter and fundamental frequency. / Abe, Masanobu.

International Conference on Spoken Language Processing, ICSLP, Proceedings. ed. / Anon. Vol. 4 IEEE, 1996. p. 2235-2238.

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

Abe, M 1996, Speech morphing by gradually changing spectrum parameter and fundamental frequency. in Anon (ed.), International Conference on Spoken Language Processing, ICSLP, Proceedings. vol. 4, IEEE, pp. 2235-2238, Proceedings of the 1996 International Conference on Spoken Language Processing, ICSLP. Part 1 (of 4), Philadelphia, PA, USA, 10/3/96.
Abe M. Speech morphing by gradually changing spectrum parameter and fundamental frequency. In Anon, editor, International Conference on Spoken Language Processing, ICSLP, Proceedings. Vol. 4. IEEE. 1996. p. 2235-2238
Abe, Masanobu. / Speech morphing by gradually changing spectrum parameter and fundamental frequency. International Conference on Spoken Language Processing, ICSLP, Proceedings. editor / Anon. Vol. 4 IEEE, 1996. pp. 2235-2238
@inproceedings{6a2c8ccee4b24983b492ed1a08b1bd90,
title = "Speech morphing by gradually changing spectrum parameter and fundamental frequency",
abstract = "This paper proposes a new application of speech modification called `speech morphing'. In image processing, morphing is a well known technique that gradually changes one person's face to that of someone else. Speech morphing produces similar results for speech; i.e., one person's speech is gradually changed to that of someone else. Speech morphing makes it possible to create movies or multi-media entertainment together with image morphing. The proposed algorithm pitch-synchronously modifies fundamental frequency(F0) and DFT spectrum and outputs high quality speech. To clarify the balance of F0 modification and spectrum modification, listening tests were carried out using 20 male speakers. The results yielded the relationship between the amount of modification and speaker identity. In terms of overall performance, listening tests show that the proposed algorithm successfully generates smooth, high quality voice changes.",
author = "Masanobu Abe",
year = "1996",
language = "English",
volume = "4",
pages = "2235--2238",
editor = "Anon",
booktitle = "International Conference on Spoken Language Processing, ICSLP, Proceedings",
publisher = "IEEE",

}

TY - GEN

T1 - Speech morphing by gradually changing spectrum parameter and fundamental frequency

AU - Abe, Masanobu

PY - 1996

Y1 - 1996

N2 - This paper proposes a new application of speech modification called `speech morphing'. In image processing, morphing is a well known technique that gradually changes one person's face to that of someone else. Speech morphing produces similar results for speech; i.e., one person's speech is gradually changed to that of someone else. Speech morphing makes it possible to create movies or multi-media entertainment together with image morphing. The proposed algorithm pitch-synchronously modifies fundamental frequency(F0) and DFT spectrum and outputs high quality speech. To clarify the balance of F0 modification and spectrum modification, listening tests were carried out using 20 male speakers. The results yielded the relationship between the amount of modification and speaker identity. In terms of overall performance, listening tests show that the proposed algorithm successfully generates smooth, high quality voice changes.

AB - This paper proposes a new application of speech modification called `speech morphing'. In image processing, morphing is a well known technique that gradually changes one person's face to that of someone else. Speech morphing produces similar results for speech; i.e., one person's speech is gradually changed to that of someone else. Speech morphing makes it possible to create movies or multi-media entertainment together with image morphing. The proposed algorithm pitch-synchronously modifies fundamental frequency(F0) and DFT spectrum and outputs high quality speech. To clarify the balance of F0 modification and spectrum modification, listening tests were carried out using 20 male speakers. The results yielded the relationship between the amount of modification and speaker identity. In terms of overall performance, listening tests show that the proposed algorithm successfully generates smooth, high quality voice changes.

UR - http://www.scopus.com/inward/record.url?scp=0030374940&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0030374940&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0030374940

VL - 4

SP - 2235

EP - 2238

BT - International Conference on Spoken Language Processing, ICSLP, Proceedings

A2 - Anon, null

PB - IEEE

ER -