Statistical methods for voice quality transformation

Yannis Stylianou; Olivier Cappé; Eric Moulines

Statistical methods for voice quality transformation

Yannis Stylianou
, Olivier Cappé
, Eric Moulines

Department Signal
Telecom Paris

Research output: Contribution to conference › Paper › peer-review

78 Citations (Scopus)

Abstract

This paper presents a new method for the statistical learning of the correspondence between spectral parameters measured from two different speakers uttering the same text. This method is based on the use of a gaussian mixture model of the speaker's spectral parameters. It is shown to be more efficient and robust than previously known techniques based on the use of vector quantization. The results obtained on large speech database demonstrate effective high-quality transformations of the voice characteristics.

Original language	English
Pages	447-450
Number of pages	4
Publication status	Published - 1 Jan 1995
Event	4th European Conference on Speech Communication and Technology, EUROSPEECH 1995 - Madrid, Spain Duration: 18 Sept 1995 → 21 Sept 1995

Conference

Conference	4th European Conference on Speech Communication and Technology, EUROSPEECH 1995
Country/Territory	Spain
City	Madrid
Period	18/09/95 → 21/09/95

Cite this

@conference{f54b88f68c2e471eb5de41b53cd7e294,

title = "Statistical methods for voice quality transformation",

abstract = "This paper presents a new method for the statistical learning of the correspondence between spectral parameters measured from two different speakers uttering the same text. This method is based on the use of a gaussian mixture model of the speaker's spectral parameters. It is shown to be more efficient and robust than previously known techniques based on the use of vector quantization. The results obtained on large speech database demonstrate effective high-quality transformations of the voice characteristics.",

author = "Yannis Stylianou and Olivier Capp{\'e} and Eric Moulines",

note = "Publisher Copyright: {\textcopyright} 1995 4th European Conference on Speech Communication and Technology, EUROSPEECH 1995. All rights reserved.; 4th European Conference on Speech Communication and Technology, EUROSPEECH 1995 ; Conference date: 18-09-1995 Through 21-09-1995",

year = "1995",

month = jan,

day = "1",

language = "English",

pages = "447--450",

}

TY - CONF

T1 - Statistical methods for voice quality transformation

AU - Stylianou, Yannis

AU - Cappé, Olivier

AU - Moulines, Eric

PY - 1995/1/1

Y1 - 1995/1/1

N2 - This paper presents a new method for the statistical learning of the correspondence between spectral parameters measured from two different speakers uttering the same text. This method is based on the use of a gaussian mixture model of the speaker's spectral parameters. It is shown to be more efficient and robust than previously known techniques based on the use of vector quantization. The results obtained on large speech database demonstrate effective high-quality transformations of the voice characteristics.

AB - This paper presents a new method for the statistical learning of the correspondence between spectral parameters measured from two different speakers uttering the same text. This method is based on the use of a gaussian mixture model of the speaker's spectral parameters. It is shown to be more efficient and robust than previously known techniques based on the use of vector quantization. The results obtained on large speech database demonstrate effective high-quality transformations of the voice characteristics.

M3 - Paper

AN - SCOPUS:85135175982

SP - 447

EP - 450

T2 - 4th European Conference on Speech Communication and Technology, EUROSPEECH 1995

Y2 - 18 September 1995 through 21 September 1995

ER -

Statistical methods for voice quality transformation

Abstract

Conference

Fingerprint

Cite this