Wideband Parametric Speech Synthesis Using Warped Linear Prediction

Tuomo Raitio; Antti Suni; Martti Vainio; Paavo Alku

Wideband Parametric Speech Synthesis Using Warped Linear Prediction

Tuomo Raitio, Antti Suni, Martti Vainio, Paavo Alku

Institute of Language, Cognition and Computation

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

Abstract

This paper studies the use of warped linear prediction (WLP) for wideband parametric speech synthesis. As the sampling frequency is increased from the usual 16 kHz, linear frequency resolution of conventional linear prediction (LP) cannot efficiently model the speech spectrum. By using frequency warping that weights perceptually the most important formant information, spectral models with better accuracy and lower model orders can be utilized. In this work, WLP is embedded in a parametric speech synthesizer to efficiently create wideband synthetic speech. Experiments show thatWLP-based wideband synthetic speech is rated better compared to narrowband speech and wideband LP-based speech.

Original language	English
Title of host publication	INTERSPEECH 2012, 13th Annual Conference of the International Speech Communication Association
Subtitle of host publication	Portland, Oregon, USA September 9-13, 2012
Publisher	ISCA-INST SPEECH COMMUNICATION ASSOC
Number of pages	4
Publication status	Published - 2012

Access to Document

Raitio Suni 2012 Wideband parametric synthesis using warped linear predictionAccepted author manuscript, 66.6 KB

http://interspeech2012.org/accepted-abstract.html?id=188

Fingerprint Dive into the research topics of 'Wideband Parametric Speech Synthesis Using Warped Linear Prediction'. Together they form a unique fingerprint.

1 Finished

HELP4MOOD:A computational distributed system to support the treatment of patients with major depression
Matheson, C. & Wolters, M.
EU government bodies
1/01/11 → 30/06/14
Project: Research

Cite this

@inproceedings{55ef954b44c64129b67d9ec4f10ad9b0,

title = "Wideband Parametric Speech Synthesis Using Warped Linear Prediction",

abstract = "This paper studies the use of warped linear prediction (WLP) for wideband parametric speech synthesis. As the sampling frequency is increased from the usual 16 kHz, linear frequency resolution of conventional linear prediction (LP) cannot efficiently model the speech spectrum. By using frequency warping that weights perceptually the most important formant information, spectral models with better accuracy and lower model orders can be utilized. In this work, WLP is embedded in a parametric speech synthesizer to efficiently create wideband synthetic speech. Experiments show thatWLP-based wideband synthetic speech is rated better compared to narrowband speech and wideband LP-based speech.",

author = "Tuomo Raitio and Antti Suni and Martti Vainio and Paavo Alku",

year = "2012",

language = "English",

booktitle = "INTERSPEECH 2012, 13th Annual Conference of the International Speech Communication Association",

publisher = "ISCA-INST SPEECH COMMUNICATION ASSOC",

}

Wideband Parametric Speech Synthesis Using Warped Linear Prediction. / Raitio, Tuomo; Suni, Antti; Vainio, Martti; Alku, Paavo.

INTERSPEECH 2012, 13th Annual Conference of the International Speech Communication Association: Portland, Oregon, USA September 9-13, 2012. ISCA-INST SPEECH COMMUNICATION ASSOC, 2012.

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

TY - GEN

T1 - Wideband Parametric Speech Synthesis Using Warped Linear Prediction

AU - Raitio, Tuomo

AU - Suni, Antti

AU - Vainio, Martti

AU - Alku, Paavo

PY - 2012

Y1 - 2012

N2 - This paper studies the use of warped linear prediction (WLP) for wideband parametric speech synthesis. As the sampling frequency is increased from the usual 16 kHz, linear frequency resolution of conventional linear prediction (LP) cannot efficiently model the speech spectrum. By using frequency warping that weights perceptually the most important formant information, spectral models with better accuracy and lower model orders can be utilized. In this work, WLP is embedded in a parametric speech synthesizer to efficiently create wideband synthetic speech. Experiments show thatWLP-based wideband synthetic speech is rated better compared to narrowband speech and wideband LP-based speech.

AB - This paper studies the use of warped linear prediction (WLP) for wideband parametric speech synthesis. As the sampling frequency is increased from the usual 16 kHz, linear frequency resolution of conventional linear prediction (LP) cannot efficiently model the speech spectrum. By using frequency warping that weights perceptually the most important formant information, spectral models with better accuracy and lower model orders can be utilized. In this work, WLP is embedded in a parametric speech synthesizer to efficiently create wideband synthetic speech. Experiments show thatWLP-based wideband synthetic speech is rated better compared to narrowband speech and wideband LP-based speech.

M3 - Conference contribution

BT - INTERSPEECH 2012, 13th Annual Conference of the International Speech Communication Association

PB - ISCA-INST SPEECH COMMUNICATION ASSOC

ER -

Wideband Parametric Speech Synthesis Using Warped Linear Prediction

Abstract

Access to Document

HELP4MOOD:A computational distributed system to support the treatment of patients with major depression

Cite this