@inproceedings{sigurgeirsson-etal-2020-manual,
title = "Manual Speech Synthesis Data Acquisition - From Script Design to Recording Speech",
author = {Sigurgeirsson, Atli and
{\"O}rn{\'o}lfsson, Gunnar and
Gu{\dh}nason, J{\'o}n},
editor = "Beermann, Dorothee and
Besacier, Laurent and
Sakti, Sakriani and
Soria, Claudia",
booktitle = "Proceedings of the 1st Joint Workshop on Spoken Language Technologies for Under-resourced languages (SLTU) and Collaboration and Computing for Under-Resourced Languages (CCURL)",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources association",
url = "https://aclanthology.org/2020.sltu-1.44/",
pages = "316--320",
language = "eng",
ISBN = "979-10-95546-35-1",
abstract = {Atli {\TH}{\'o}r Sigurgeirsson, atlithors@ru.is, Reykjavik University Gunnar Thor {\"O}rn{\'o}lfsson, gunnarthor@hi.is, {\'A}rni Magn{\'u}sson institute of Icelandic studies Dr. J{\'o}n Gu{\dh}nason, jg@ru.is In this paper we present the work of collecting a large amount of high quality speech synthesis data for Icelandic. 8 speakers will be recorded for 20 hours each. A script design strategy is proposed and three scripts have been generated to maximize diphone coverage, varying in length. The largest reading script contains 14,400 prompts and includes 87.3{\%} of all Icelandic diphones at least once and 81{\%} of all Icelandic diphones at least twenty times. A recording client was developed to facilitate recording sessions. The client supports easily importing scripts and maintaining multiple collections in parallel. The recorded data can be downloaded straight from the client. Recording sessions are carried out in a professional studio under supervision and started October of 2019. As of writing, 58.7 hours of high quality speech data has been collected. The scripts, the recording software and the speech data will later be released under a CC-BY 4.0 license.}
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sigurgeirsson-etal-2020-manual">
<titleInfo>
<title>Manual Speech Synthesis Data Acquisition - From Script Design to Recording Speech</title>
</titleInfo>
<name type="personal">
<namePart type="given">Atli</namePart>
<namePart type="family">Sigurgeirsson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gunnar</namePart>
<namePart type="family">Örnólfsson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jón</namePart>
<namePart type="family">Gu\dhnason</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 1st Joint Workshop on Spoken Language Technologies for Under-resourced languages (SLTU) and Collaboration and Computing for Under-Resourced Languages (CCURL)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dorothee</namePart>
<namePart type="family">Beermann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Laurent</namePart>
<namePart type="family">Besacier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Claudia</namePart>
<namePart type="family">Soria</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-35-1</identifier>
</relatedItem>
<abstract>Atli \THór Sigurgeirsson, atlithors@ru.is, Reykjavik University Gunnar Thor Örnólfsson, gunnarthor@hi.is, Árni Magnússon institute of Icelandic studies Dr. Jón Gu\dhnason, jg@ru.is In this paper we present the work of collecting a large amount of high quality speech synthesis data for Icelandic. 8 speakers will be recorded for 20 hours each. A script design strategy is proposed and three scripts have been generated to maximize diphone coverage, varying in length. The largest reading script contains 14,400 prompts and includes 87.3% of all Icelandic diphones at least once and 81% of all Icelandic diphones at least twenty times. A recording client was developed to facilitate recording sessions. The client supports easily importing scripts and maintaining multiple collections in parallel. The recorded data can be downloaded straight from the client. Recording sessions are carried out in a professional studio under supervision and started October of 2019. As of writing, 58.7 hours of high quality speech data has been collected. The scripts, the recording software and the speech data will later be released under a CC-BY 4.0 license.</abstract>
<identifier type="citekey">sigurgeirsson-etal-2020-manual</identifier>
<location>
<url>https://aclanthology.org/2020.sltu-1.44/</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>316</start>
<end>320</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Manual Speech Synthesis Data Acquisition - From Script Design to Recording Speech
%A Sigurgeirsson, Atli
%A Örnólfsson, Gunnar
%A Gu\dhnason, Jón
%Y Beermann, Dorothee
%Y Besacier, Laurent
%Y Sakti, Sakriani
%Y Soria, Claudia
%S Proceedings of the 1st Joint Workshop on Spoken Language Technologies for Under-resourced languages (SLTU) and Collaboration and Computing for Under-Resourced Languages (CCURL)
%D 2020
%8 May
%I European Language Resources association
%C Marseille, France
%@ 979-10-95546-35-1
%G eng
%F sigurgeirsson-etal-2020-manual
%X Atli \THór Sigurgeirsson, atlithors@ru.is, Reykjavik University Gunnar Thor Örnólfsson, gunnarthor@hi.is, Árni Magnússon institute of Icelandic studies Dr. Jón Gu\dhnason, jg@ru.is In this paper we present the work of collecting a large amount of high quality speech synthesis data for Icelandic. 8 speakers will be recorded for 20 hours each. A script design strategy is proposed and three scripts have been generated to maximize diphone coverage, varying in length. The largest reading script contains 14,400 prompts and includes 87.3% of all Icelandic diphones at least once and 81% of all Icelandic diphones at least twenty times. A recording client was developed to facilitate recording sessions. The client supports easily importing scripts and maintaining multiple collections in parallel. The recorded data can be downloaded straight from the client. Recording sessions are carried out in a professional studio under supervision and started October of 2019. As of writing, 58.7 hours of high quality speech data has been collected. The scripts, the recording software and the speech data will later be released under a CC-BY 4.0 license.
%U https://aclanthology.org/2020.sltu-1.44/
%P 316-320
Markdown (Informal)
[Manual Speech Synthesis Data Acquisition - From Script Design to Recording Speech](https://aclanthology.org/2020.sltu-1.44/) (Sigurgeirsson et al., SLTU 2020)
ACL