@inproceedings{georgila-etal-2012-practical,
title = "Practical Evaluation of Human and Synthesized Speech for Virtual Human Dialogue Systems",
author = "Georgila, Kallirroi and
Black, Alan and
Sagae, Kenji and
Traum, David",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Do{\u{g}}an, Mehmet U{\u{g}}ur and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Eighth International Conference on Language Resources and Evaluation ({LREC}'12)",
month = may,
year = "2012",
address = "Istanbul, Turkey",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2012/pdf/562_Paper.pdf",
pages = "3519--3526",
abstract = "The current practice in virtual human dialogue systems is to use professional human recordings or limited-domain speech synthesis. Both approaches lead to good performance but at a high cost. To determine the best trade-off between performance and cost, we perform a systematic evaluation of human and synthesized voices with regard to naturalness, conversational aspect, and likability. We vary the type (in-domain vs. out-of-domain), length, and content of utterances, and take into account the age and native language of raters as well as their familiarity with speech synthesis. We present detailed results from two studies, a pilot one and one run on Amazon's Mechanical Turk. Our results suggest that a professional human voice can supersede both an amateur human voice and synthesized voices. Also, a high-quality general-purpose voice or a good limited-domain voice can perform better than amateur human recordings. We do not find any significant differences between the performance of a high-quality general-purpose voice and a limited-domain voice, both trained with speech recorded by actors. As expected, the high-quality general-purpose voice is rated higher than the limited-domain voice for out-of-domain sentences and lower for in-domain sentences. There is also a trend for long or negative-content utterances to receive lower ratings.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="georgila-etal-2012-practical">
<titleInfo>
<title>Practical Evaluation of Human and Synthesized Speech for Virtual Human Dialogue Systems</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kallirroi</namePart>
<namePart type="family">Georgila</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Black</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kenji</namePart>
<namePart type="family">Sagae</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Traum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2012-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mehmet</namePart>
<namePart type="given">Uğur</namePart>
<namePart type="family">Doğan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Istanbul, Turkey</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The current practice in virtual human dialogue systems is to use professional human recordings or limited-domain speech synthesis. Both approaches lead to good performance but at a high cost. To determine the best trade-off between performance and cost, we perform a systematic evaluation of human and synthesized voices with regard to naturalness, conversational aspect, and likability. We vary the type (in-domain vs. out-of-domain), length, and content of utterances, and take into account the age and native language of raters as well as their familiarity with speech synthesis. We present detailed results from two studies, a pilot one and one run on Amazon’s Mechanical Turk. Our results suggest that a professional human voice can supersede both an amateur human voice and synthesized voices. Also, a high-quality general-purpose voice or a good limited-domain voice can perform better than amateur human recordings. We do not find any significant differences between the performance of a high-quality general-purpose voice and a limited-domain voice, both trained with speech recorded by actors. As expected, the high-quality general-purpose voice is rated higher than the limited-domain voice for out-of-domain sentences and lower for in-domain sentences. There is also a trend for long or negative-content utterances to receive lower ratings.</abstract>
<identifier type="citekey">georgila-etal-2012-practical</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/562_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>3519</start>
<end>3526</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Practical Evaluation of Human and Synthesized Speech for Virtual Human Dialogue Systems
%A Georgila, Kallirroi
%A Black, Alan
%A Sagae, Kenji
%A Traum, David
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Doğan, Mehmet Uğur
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)
%D 2012
%8 May
%I European Language Resources Association (ELRA)
%C Istanbul, Turkey
%F georgila-etal-2012-practical
%X The current practice in virtual human dialogue systems is to use professional human recordings or limited-domain speech synthesis. Both approaches lead to good performance but at a high cost. To determine the best trade-off between performance and cost, we perform a systematic evaluation of human and synthesized voices with regard to naturalness, conversational aspect, and likability. We vary the type (in-domain vs. out-of-domain), length, and content of utterances, and take into account the age and native language of raters as well as their familiarity with speech synthesis. We present detailed results from two studies, a pilot one and one run on Amazon’s Mechanical Turk. Our results suggest that a professional human voice can supersede both an amateur human voice and synthesized voices. Also, a high-quality general-purpose voice or a good limited-domain voice can perform better than amateur human recordings. We do not find any significant differences between the performance of a high-quality general-purpose voice and a limited-domain voice, both trained with speech recorded by actors. As expected, the high-quality general-purpose voice is rated higher than the limited-domain voice for out-of-domain sentences and lower for in-domain sentences. There is also a trend for long or negative-content utterances to receive lower ratings.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/562_Paper.pdf
%P 3519-3526
Markdown (Informal)
[Practical Evaluation of Human and Synthesized Speech for Virtual Human Dialogue Systems](http://www.lrec-conf.org/proceedings/lrec2012/pdf/562_Paper.pdf) (Georgila et al., LREC 2012)
ACL