@inproceedings{aichinger-etal-2016-database,
title = "A Database of Laryngeal High-Speed Videos with Simultaneous High-Quality Audio Recordings of Pathological and Non-Pathological Voices",
author = "Aichinger, Philipp and
Roesner, Immer and
Leonhard, Matthias and
Denk-Linnert, Doris-Maria and
Bigenzahn, Wolfgang and
Schneider-Stickler, Berit",
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/L16-1122",
pages = "767--770",
abstract = "Auditory voice quality judgements are used intensively for the clinical assessment of pathological voice. Voice quality concepts are fuzzily defined and poorly standardized however, which hinders scientific and clinical communication. The described database documents a wide variety of pathologies and is used to investigate auditory voice quality concepts with regard to phonation mechanisms. The database contains 375 laryngeal high-speed videos and simultaneous high-quality audio recordings of sustained phonations of 80 pathological and 40 non-pathological subjects. Interval wise annotations regarding video and audio quality, as well as voice quality ratings are provided. Video quality is annotated for the visibility of anatomical structures and artefacts such as blurring or reduced contrast. Voice quality annotations include ratings on the presence of dysphonia and diplophonia. The purpose of the database is to aid the formulation of observationally well-founded models of phonation and the development of model-based automatic detectors for distinct types of phonation, especially for clinically relevant nonmodal voice phenomena. Another application is the training of audio-based fundamental frequency extractors on video-based reference fundamental frequencies.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="aichinger-etal-2016-database">
<titleInfo>
<title>A Database of Laryngeal High-Speed Videos with Simultaneous High-Quality Audio Recordings of Pathological and Non-Pathological Voices</title>
</titleInfo>
<name type="personal">
<namePart type="given">Philipp</namePart>
<namePart type="family">Aichinger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Immer</namePart>
<namePart type="family">Roesner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthias</namePart>
<namePart type="family">Leonhard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Doris-Maria</namePart>
<namePart type="family">Denk-Linnert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wolfgang</namePart>
<namePart type="family">Bigenzahn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Berit</namePart>
<namePart type="family">Schneider-Stickler</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>Auditory voice quality judgements are used intensively for the clinical assessment of pathological voice. Voice quality concepts are fuzzily defined and poorly standardized however, which hinders scientific and clinical communication. The described database documents a wide variety of pathologies and is used to investigate auditory voice quality concepts with regard to phonation mechanisms. The database contains 375 laryngeal high-speed videos and simultaneous high-quality audio recordings of sustained phonations of 80 pathological and 40 non-pathological subjects. Interval wise annotations regarding video and audio quality, as well as voice quality ratings are provided. Video quality is annotated for the visibility of anatomical structures and artefacts such as blurring or reduced contrast. Voice quality annotations include ratings on the presence of dysphonia and diplophonia. The purpose of the database is to aid the formulation of observationally well-founded models of phonation and the development of model-based automatic detectors for distinct types of phonation, especially for clinically relevant nonmodal voice phenomena. Another application is the training of audio-based fundamental frequency extractors on video-based reference fundamental frequencies.</abstract>
<identifier type="citekey">aichinger-etal-2016-database</identifier>
<location>
<url>https://aclanthology.org/L16-1122</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>767</start>
<end>770</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Database of Laryngeal High-Speed Videos with Simultaneous High-Quality Audio Recordings of Pathological and Non-Pathological Voices
%A Aichinger, Philipp
%A Roesner, Immer
%A Leonhard, Matthias
%A Denk-Linnert, Doris-Maria
%A Bigenzahn, Wolfgang
%A Schneider-Stickler, Berit
%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 aichinger-etal-2016-database
%X Auditory voice quality judgements are used intensively for the clinical assessment of pathological voice. Voice quality concepts are fuzzily defined and poorly standardized however, which hinders scientific and clinical communication. The described database documents a wide variety of pathologies and is used to investigate auditory voice quality concepts with regard to phonation mechanisms. The database contains 375 laryngeal high-speed videos and simultaneous high-quality audio recordings of sustained phonations of 80 pathological and 40 non-pathological subjects. Interval wise annotations regarding video and audio quality, as well as voice quality ratings are provided. Video quality is annotated for the visibility of anatomical structures and artefacts such as blurring or reduced contrast. Voice quality annotations include ratings on the presence of dysphonia and diplophonia. The purpose of the database is to aid the formulation of observationally well-founded models of phonation and the development of model-based automatic detectors for distinct types of phonation, especially for clinically relevant nonmodal voice phenomena. Another application is the training of audio-based fundamental frequency extractors on video-based reference fundamental frequencies.
%U https://aclanthology.org/L16-1122
%P 767-770
Markdown (Informal)
[A Database of Laryngeal High-Speed Videos with Simultaneous High-Quality Audio Recordings of Pathological and Non-Pathological Voices](https://aclanthology.org/L16-1122) (Aichinger et al., LREC 2016)
ACL