@inproceedings{pessentheiner-etal-2016-amisco,
title = "{AMISCO}: The {A}ustrian {G}erman Multi-Sensor Corpus",
author = {Pessentheiner, Hannes and
Pichler, Thomas and
Hagm{\"u}ller, Martin},
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Goggi, Sara and
Grobelnik, Marko and
Maegaard, Bente and
Mariani, Joseph and
Mazo, Helene and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Tenth International Conference on Language Resources and Evaluation ({LREC}'16)",
month = may,
year = "2016",
address = "Portoro{\v{z}}, Slovenia",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/L16-1121",
pages = "760--766",
abstract = "We introduce a unique, comprehensive Austrian German multi-sensor corpus with moving and non-moving speakers to facilitate the evaluation of estimators and detectors that jointly detect a speaker{'}s spatial and temporal parameters. The corpus is suitable for various machine learning and signal processing tasks, linguistic studies, and studies related to a speaker{'}s fundamental frequency (due to recorded glottograms). Available corpora are limited to (synthetically generated/spatialized) speech data or recordings of musical instruments that lack moving speakers, glottograms, and/or multi-channel distant speech recordings. That is why we recorded 24 spatially non-moving and moving speakers, balanced male and female, to set up a two-room and 43-channel Austrian German multi-sensor speech corpus. It contains 8.2 hours of read speech based on phonetically balanced sentences, commands, and digits. The orthographic transcriptions include around 53,000 word tokens and 2,070 word types. Special features of this corpus are the laryngograph recordings (representing glottograms required to detect a speaker{'}s instantaneous fundamental frequency and pitch), corresponding clean-speech recordings, and spatial information and video data provided by four Kinects and a camera.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pessentheiner-etal-2016-amisco">
<titleInfo>
<title>AMISCO: The Austrian German Multi-Sensor Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hannes</namePart>
<namePart type="family">Pessentheiner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thomas</namePart>
<namePart type="family">Pichler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Martin</namePart>
<namePart type="family">Hagmüller</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)</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">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marko</namePart>
<namePart type="family">Grobelnik</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">Helene</namePart>
<namePart type="family">Mazo</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">Portorož, Slovenia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We introduce a unique, comprehensive Austrian German multi-sensor corpus with moving and non-moving speakers to facilitate the evaluation of estimators and detectors that jointly detect a speaker’s spatial and temporal parameters. The corpus is suitable for various machine learning and signal processing tasks, linguistic studies, and studies related to a speaker’s fundamental frequency (due to recorded glottograms). Available corpora are limited to (synthetically generated/spatialized) speech data or recordings of musical instruments that lack moving speakers, glottograms, and/or multi-channel distant speech recordings. That is why we recorded 24 spatially non-moving and moving speakers, balanced male and female, to set up a two-room and 43-channel Austrian German multi-sensor speech corpus. It contains 8.2 hours of read speech based on phonetically balanced sentences, commands, and digits. The orthographic transcriptions include around 53,000 word tokens and 2,070 word types. Special features of this corpus are the laryngograph recordings (representing glottograms required to detect a speaker’s instantaneous fundamental frequency and pitch), corresponding clean-speech recordings, and spatial information and video data provided by four Kinects and a camera.</abstract>
<identifier type="citekey">pessentheiner-etal-2016-amisco</identifier>
<location>
<url>https://aclanthology.org/L16-1121</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>760</start>
<end>766</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T AMISCO: The Austrian German Multi-Sensor Corpus
%A Pessentheiner, Hannes
%A Pichler, Thomas
%A Hagmüller, Martin
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Grobelnik, Marko
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Helene
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)
%D 2016
%8 May
%I European Language Resources Association (ELRA)
%C Portorož, Slovenia
%F pessentheiner-etal-2016-amisco
%X We introduce a unique, comprehensive Austrian German multi-sensor corpus with moving and non-moving speakers to facilitate the evaluation of estimators and detectors that jointly detect a speaker’s spatial and temporal parameters. The corpus is suitable for various machine learning and signal processing tasks, linguistic studies, and studies related to a speaker’s fundamental frequency (due to recorded glottograms). Available corpora are limited to (synthetically generated/spatialized) speech data or recordings of musical instruments that lack moving speakers, glottograms, and/or multi-channel distant speech recordings. That is why we recorded 24 spatially non-moving and moving speakers, balanced male and female, to set up a two-room and 43-channel Austrian German multi-sensor speech corpus. It contains 8.2 hours of read speech based on phonetically balanced sentences, commands, and digits. The orthographic transcriptions include around 53,000 word tokens and 2,070 word types. Special features of this corpus are the laryngograph recordings (representing glottograms required to detect a speaker’s instantaneous fundamental frequency and pitch), corresponding clean-speech recordings, and spatial information and video data provided by four Kinects and a camera.
%U https://aclanthology.org/L16-1121
%P 760-766
Markdown (Informal)
[AMISCO: The Austrian German Multi-Sensor Corpus](https://aclanthology.org/L16-1121) (Pessentheiner et al., LREC 2016)
ACL
- Hannes Pessentheiner, Thomas Pichler, and Martin Hagmüller. 2016. AMISCO: The Austrian German Multi-Sensor Corpus. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16), pages 760–766, Portorož, Slovenia. European Language Resources Association (ELRA).