Evaluation of speaker mimic technology for personalizing SGD voices

Esther Klabbers; Alexander Kain; Jan P.H. Van Santen

Evaluation of speaker mimic technology for personalizing SGD voices

Esther Klabbers, Alexander Kain, Jan P.H. Van Santen

Institute on Development & Disability

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

3 Scopus citations

Abstract

In this paper, we demonstrate the use of state-of-the-art speech technology to transform speech from a source speaker to mimic a particular target speaker with the intention of providng personalized voices to users of Speech Generating Devices (SGDs). This speaker mimicry (SM) capability allows us to use high-quality acoustic inventories from professional speakers and transform them to a different target speaker using a very limited set of sentences from that speaker. This technology targets future SGD users who still have a limited vocabulary or available previous recordings. The results of a perceptual study show that listeners can identify which SM voices most resemble their respective target voices. ¹

Original language	English (US)
Pages	2154-2157
Number of pages	4
State	Published - 2010
Event	11th Annual Conference of the International Speech Communication Association: Spoken Language Processing for All, INTERSPEECH 2010 - Makuhari, Chiba, Japan Duration: Sep 26 2010 → Sep 30 2010

Other

Other	11th Annual Conference of the International Speech Communication Association: Spoken Language Processing for All, INTERSPEECH 2010
Country	Japan
City	Makuhari, Chiba
Period	9/26/10 → 9/30/10

Keywords

Perceptual evaluation
Prosody modeling
Speech synthesis
Voice transformation

ASJC Scopus subject areas

Language and Linguistics
Speech and Hearing

Access to Document

Fingerprint Dive into the research topics of 'Evaluation of speaker mimic technology for personalizing SGD voices'. Together they form a unique fingerprint.

Cite this

Evaluation of speaker mimic technology for personalizing SGD voices. / Klabbers, Esther; Kain, Alexander; Van Santen, Jan P.H.

2010. 2154-2157 Paper presented at 11th Annual Conference of the International Speech Communication Association: Spoken Language Processing for All, INTERSPEECH 2010, Makuhari, Chiba, Japan.

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

@conference{42344b9ec6574f0796879c01f4cf98fe,

title = "Evaluation of speaker mimic technology for personalizing SGD voices",

abstract = "In this paper, we demonstrate the use of state-of-the-art speech technology to transform speech from a source speaker to mimic a particular target speaker with the intention of providng personalized voices to users of Speech Generating Devices (SGDs). This speaker mimicry (SM) capability allows us to use high-quality acoustic inventories from professional speakers and transform them to a different target speaker using a very limited set of sentences from that speaker. This technology targets future SGD users who still have a limited vocabulary or available previous recordings. The results of a perceptual study show that listeners can identify which SM voices most resemble their respective target voices. 1",

keywords = "Perceptual evaluation, Prosody modeling, Speech synthesis, Voice transformation",

author = "Esther Klabbers and Alexander Kain and {Van Santen}, {Jan P.H.}",

year = "2010",

language = "English (US)",

pages = "2154--2157",

note = "11th Annual Conference of the International Speech Communication Association: Spoken Language Processing for All, INTERSPEECH 2010 ; Conference date: 26-09-2010 Through 30-09-2010",

}

TY - CONF

T1 - Evaluation of speaker mimic technology for personalizing SGD voices

AU - Klabbers, Esther

AU - Kain, Alexander

AU - Van Santen, Jan P.H.

PY - 2010

Y1 - 2010

N2 - In this paper, we demonstrate the use of state-of-the-art speech technology to transform speech from a source speaker to mimic a particular target speaker with the intention of providng personalized voices to users of Speech Generating Devices (SGDs). This speaker mimicry (SM) capability allows us to use high-quality acoustic inventories from professional speakers and transform them to a different target speaker using a very limited set of sentences from that speaker. This technology targets future SGD users who still have a limited vocabulary or available previous recordings. The results of a perceptual study show that listeners can identify which SM voices most resemble their respective target voices. 1

AB - In this paper, we demonstrate the use of state-of-the-art speech technology to transform speech from a source speaker to mimic a particular target speaker with the intention of providng personalized voices to users of Speech Generating Devices (SGDs). This speaker mimicry (SM) capability allows us to use high-quality acoustic inventories from professional speakers and transform them to a different target speaker using a very limited set of sentences from that speaker. This technology targets future SGD users who still have a limited vocabulary or available previous recordings. The results of a perceptual study show that listeners can identify which SM voices most resemble their respective target voices. 1

KW - Perceptual evaluation

KW - Prosody modeling

KW - Speech synthesis

KW - Voice transformation

UR - http://www.scopus.com/inward/record.url?scp=79959840813&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79959840813&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:79959840813

SP - 2154

EP - 2157

T2 - 11th Annual Conference of the International Speech Communication Association: Spoken Language Processing for All, INTERSPEECH 2010

Y2 - 26 September 2010 through 30 September 2010

ER -