Applying Spectral Normalisation and Efficient Envelope Estimation and Statistical Transformation for the Voice Conversion Challenge 2016

Fernando Villavicencio; Junichi Yamagishi; Jordi  Bonada; Felipe Espic

doi:10.21437/Interspeech.2016-305

Applying Spectral Normalisation and Efficient Envelope Estimation and Statistical Transformation for the Voice Conversion Challenge 2016

Fernando Villavicencio, Junichi Yamagishi, Jordi Bonada, Felipe Espic

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

In this work we present our entry for the Voice Conversion Challenge 2016, denoting new features to previous work on GMM-based voice conversion. We incorporate frequency warping and pitch transposition strategies to perform a normalisation of the spectral conditions, with benefits confirmed by objective and perceptual means. Moreover, the results of the challenge showed our entry among the highest performing systems in terms of perceived naturalness while maintaining the target similarity performance of GMM-based conversion.

Original language	English
Title of host publication	Interspeech 2016
Publisher	International Speech Communication Association
Pages	1661
Number of pages	5
DOIs	https://doi.org/10.21437/Interspeech.2016-305
Publication status	Published - 12 Sep 2016
Event	Interspeech 2016 - San Francisco, United States Duration: 8 Sep 2016 → 12 Sep 2016 http://www.interspeech2016.org/

Publication series

Name
Publisher	International Speech Communication Association
ISSN (Print)	1990-9772

Conference

Conference	Interspeech 2016
Country/Territory	United States
City	San Francisco
Period	8/09/16 → 12/09/16
Internet address	http://www.interspeech2016.org/

Access to Document

10.21437/Interspeech.2016-305

0305Final published version, 274 KB

http://www.isca-speech.org/archive/Interspeech_2016/pdfs/0305.PDF

Cite this

@inproceedings{3c948eae972740dc81140cc995be0315,

title = "Applying Spectral Normalisation and Efficient Envelope Estimation and Statistical Transformation for the Voice Conversion Challenge 2016",

abstract = "In this work we present our entry for the Voice Conversion Challenge 2016, denoting new features to previous work on GMM-based voice conversion. We incorporate frequency warping and pitch transposition strategies to perform a normalisation of the spectral conditions, with benefits confirmed by objective and perceptual means. Moreover, the results of the challenge showed our entry among the highest performing systems in terms of perceived naturalness while maintaining the target similarity performance of GMM-based conversion.",

author = "Fernando Villavicencio and Junichi Yamagishi and Jordi Bonada and Felipe Espic",

year = "2016",

month = sep,

day = "12",

doi = "10.21437/Interspeech.2016-305",

language = "English",

publisher = "International Speech Communication Association",

pages = "1661",

booktitle = "Interspeech 2016",

note = "Interspeech 2016 ; Conference date: 08-09-2016 Through 12-09-2016",

url = "http://www.interspeech2016.org/",

}

Villavicencio, F, Yamagishi, J, Bonada, J & Espic, F 2016, Applying Spectral Normalisation and Efficient Envelope Estimation and Statistical Transformation for the Voice Conversion Challenge 2016. in Interspeech 2016. International Speech Communication Association, pp. 1661, Interspeech 2016, San Francisco, United States, 8/09/16. https://doi.org/10.21437/Interspeech.2016-305

Applying Spectral Normalisation and Efficient Envelope Estimation and Statistical Transformation for the Voice Conversion Challenge 2016. / Villavicencio, Fernando; Yamagishi, Junichi; Bonada, Jordi et al.

Interspeech 2016. International Speech Communication Association, 2016. p. 1661.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Applying Spectral Normalisation and Efficient Envelope Estimation and Statistical Transformation for the Voice Conversion Challenge 2016

AU - Villavicencio, Fernando

AU - Yamagishi, Junichi

AU - Bonada, Jordi

AU - Espic, Felipe

PY - 2016/9/12

Y1 - 2016/9/12

N2 - In this work we present our entry for the Voice Conversion Challenge 2016, denoting new features to previous work on GMM-based voice conversion. We incorporate frequency warping and pitch transposition strategies to perform a normalisation of the spectral conditions, with benefits confirmed by objective and perceptual means. Moreover, the results of the challenge showed our entry among the highest performing systems in terms of perceived naturalness while maintaining the target similarity performance of GMM-based conversion.

AB - In this work we present our entry for the Voice Conversion Challenge 2016, denoting new features to previous work on GMM-based voice conversion. We incorporate frequency warping and pitch transposition strategies to perform a normalisation of the spectral conditions, with benefits confirmed by objective and perceptual means. Moreover, the results of the challenge showed our entry among the highest performing systems in terms of perceived naturalness while maintaining the target similarity performance of GMM-based conversion.

U2 - 10.21437/Interspeech.2016-305

DO - 10.21437/Interspeech.2016-305

M3 - Conference contribution

SP - 1661

BT - Interspeech 2016

PB - International Speech Communication Association

T2 - Interspeech 2016

Y2 - 8 September 2016 through 12 September 2016

ER -