@inproceedings{rusko-etal-2014-alert,
title = "Alert!... Calm Down, There is Nothing to Worry About. Warning and Soothing Speech Synthesis.",
author = "Rusko, Milan and
Darjaa, Sakhia and
Trnka, Mari{\'a}n and
Ritomsk{\'y}, Mari{\'a}n and
Sabo, R{\'o}bert",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Loftsson, Hrafn and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Ninth International Conference on Language Resources and Evaluation ({LREC}'14)",
month = may,
year = "2014",
address = "Reykjavik, Iceland",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2014/pdf/722_Paper.pdf",
pages = "1182--1187",
abstract = "Presence of appropriate acoustic cues of affective features in the synthesized speech can be a prerequisite for the proper evaluation of the semantic content by the message recipient. In the recent work the authors have focused on the research of expressive speech synthesis capable of generating naturally sounding synthetic speech at various levels of arousal. The synthesizer should be able to produce speech in Slovak in different styles from extremely urgent warnings, insisting messages, alerts, through comments, and neutral style speech to soothing messages and very calm speech. A three-step method was used for recording both - the high-activation and low-activation expressive speech databases. The acoustic properties of the obtained databases are discussed. Several synthesizers with different levels of arousal were designed using these databases and their outputs are compared to the original voice of the voice talent. A possible ambiguity of acoustic cues is pointed out and the relevance of the semantic meaning of the sentences both in the sentence set for the speech database recording and in the set for subjective synthesizer testing is discussed.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rusko-etal-2014-alert">
<titleInfo>
<title>Alert!... Calm Down, There is Nothing to Worry About. Warning and Soothing Speech Synthesis.</title>
</titleInfo>
<name type="personal">
<namePart type="given">Milan</namePart>
<namePart type="family">Rusko</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakhia</namePart>
<namePart type="family">Darjaa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marián</namePart>
<namePart type="family">Trnka</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marián</namePart>
<namePart type="family">Ritomský</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Róbert</namePart>
<namePart type="family">Sabo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2014-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)</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">Hrafn</namePart>
<namePart type="family">Loftsson</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">Reykjavik, Iceland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Presence of appropriate acoustic cues of affective features in the synthesized speech can be a prerequisite for the proper evaluation of the semantic content by the message recipient. In the recent work the authors have focused on the research of expressive speech synthesis capable of generating naturally sounding synthetic speech at various levels of arousal. The synthesizer should be able to produce speech in Slovak in different styles from extremely urgent warnings, insisting messages, alerts, through comments, and neutral style speech to soothing messages and very calm speech. A three-step method was used for recording both - the high-activation and low-activation expressive speech databases. The acoustic properties of the obtained databases are discussed. Several synthesizers with different levels of arousal were designed using these databases and their outputs are compared to the original voice of the voice talent. A possible ambiguity of acoustic cues is pointed out and the relevance of the semantic meaning of the sentences both in the sentence set for the speech database recording and in the set for subjective synthesizer testing is discussed.</abstract>
<identifier type="citekey">rusko-etal-2014-alert</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/722_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>1182</start>
<end>1187</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Alert!... Calm Down, There is Nothing to Worry About. Warning and Soothing Speech Synthesis.
%A Rusko, Milan
%A Darjaa, Sakhia
%A Trnka, Marián
%A Ritomský, Marián
%A Sabo, Róbert
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Loftsson, Hrafn
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)
%D 2014
%8 May
%I European Language Resources Association (ELRA)
%C Reykjavik, Iceland
%F rusko-etal-2014-alert
%X Presence of appropriate acoustic cues of affective features in the synthesized speech can be a prerequisite for the proper evaluation of the semantic content by the message recipient. In the recent work the authors have focused on the research of expressive speech synthesis capable of generating naturally sounding synthetic speech at various levels of arousal. The synthesizer should be able to produce speech in Slovak in different styles from extremely urgent warnings, insisting messages, alerts, through comments, and neutral style speech to soothing messages and very calm speech. A three-step method was used for recording both - the high-activation and low-activation expressive speech databases. The acoustic properties of the obtained databases are discussed. Several synthesizers with different levels of arousal were designed using these databases and their outputs are compared to the original voice of the voice talent. A possible ambiguity of acoustic cues is pointed out and the relevance of the semantic meaning of the sentences both in the sentence set for the speech database recording and in the set for subjective synthesizer testing is discussed.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/722_Paper.pdf
%P 1182-1187
Markdown (Informal)
[Alert!... Calm Down, There is Nothing to Worry About. Warning and Soothing Speech Synthesis.](http://www.lrec-conf.org/proceedings/lrec2014/pdf/722_Paper.pdf) (Rusko et al., LREC 2014)
ACL