@inproceedings{weiner-etal-2016-towards,
title = "Towards Automatic Transcription of {ILSE} {\textemdash} an Interdisciplinary Longitudinal Study of Adult Development and Aging",
author = {Weiner, Jochen and
Frankenberg, Claudia and
Telaar, Dominic and
Wendelstein, Britta and
Schr{\"o}der, Johannes and
Schultz, Tanja},
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/L16-1114/",
pages = "718--725",
abstract = "The Interdisciplinary Longitudinal Study on Adult Development and Aging (ILSE) was created to facilitate the study of challenges posed by rapidly aging societies in developed countries such as Germany. ILSE contains over 8,000 hours of biographic interviews recorded from more than 1,000 participants over the course of 20 years. Investigations on various aspects of aging, such as cognitive decline, often rely on the analysis of linguistic features which can be derived from spoken content like these interviews. However, transcribing speech is a time and cost consuming manual process and so far only 380 hours of ILSE interviews have been transcribed. Thus, it is the aim of our work to establish technical systems to fully automatically transcribe the ILSE interview data. The joint occurrence of poor recording quality, long audio segments, erroneous transcriptions, varying speaking styles {\&} crosstalk, and emotional {\&} dialectal speech in these interviews presents challenges for automatic speech recognition (ASR). We describe our ongoing work towards the fully automatic transcription of all ILSE interviews and the steps we implemented in preparing the transcriptions to meet the interviews' challenges. Using a recursive long audio alignment procedure 96 hours of the transcribed data have been made accessible for ASR training."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="weiner-etal-2016-towards">
<titleInfo>
<title>Towards Automatic Transcription of ILSE — an Interdisciplinary Longitudinal Study of Adult Development and Aging</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jochen</namePart>
<namePart type="family">Weiner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Claudia</namePart>
<namePart type="family">Frankenberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dominic</namePart>
<namePart type="family">Telaar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Britta</namePart>
<namePart type="family">Wendelstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Johannes</namePart>
<namePart type="family">Schröder</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanja</namePart>
<namePart type="family">Schultz</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>The Interdisciplinary Longitudinal Study on Adult Development and Aging (ILSE) was created to facilitate the study of challenges posed by rapidly aging societies in developed countries such as Germany. ILSE contains over 8,000 hours of biographic interviews recorded from more than 1,000 participants over the course of 20 years. Investigations on various aspects of aging, such as cognitive decline, often rely on the analysis of linguistic features which can be derived from spoken content like these interviews. However, transcribing speech is a time and cost consuming manual process and so far only 380 hours of ILSE interviews have been transcribed. Thus, it is the aim of our work to establish technical systems to fully automatically transcribe the ILSE interview data. The joint occurrence of poor recording quality, long audio segments, erroneous transcriptions, varying speaking styles & crosstalk, and emotional & dialectal speech in these interviews presents challenges for automatic speech recognition (ASR). We describe our ongoing work towards the fully automatic transcription of all ILSE interviews and the steps we implemented in preparing the transcriptions to meet the interviews’ challenges. Using a recursive long audio alignment procedure 96 hours of the transcribed data have been made accessible for ASR training.</abstract>
<identifier type="citekey">weiner-etal-2016-towards</identifier>
<location>
<url>https://aclanthology.org/L16-1114/</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>718</start>
<end>725</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Towards Automatic Transcription of ILSE — an Interdisciplinary Longitudinal Study of Adult Development and Aging
%A Weiner, Jochen
%A Frankenberg, Claudia
%A Telaar, Dominic
%A Wendelstein, Britta
%A Schröder, Johannes
%A Schultz, Tanja
%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 weiner-etal-2016-towards
%X The Interdisciplinary Longitudinal Study on Adult Development and Aging (ILSE) was created to facilitate the study of challenges posed by rapidly aging societies in developed countries such as Germany. ILSE contains over 8,000 hours of biographic interviews recorded from more than 1,000 participants over the course of 20 years. Investigations on various aspects of aging, such as cognitive decline, often rely on the analysis of linguistic features which can be derived from spoken content like these interviews. However, transcribing speech is a time and cost consuming manual process and so far only 380 hours of ILSE interviews have been transcribed. Thus, it is the aim of our work to establish technical systems to fully automatically transcribe the ILSE interview data. The joint occurrence of poor recording quality, long audio segments, erroneous transcriptions, varying speaking styles & crosstalk, and emotional & dialectal speech in these interviews presents challenges for automatic speech recognition (ASR). We describe our ongoing work towards the fully automatic transcription of all ILSE interviews and the steps we implemented in preparing the transcriptions to meet the interviews’ challenges. Using a recursive long audio alignment procedure 96 hours of the transcribed data have been made accessible for ASR training.
%U https://aclanthology.org/L16-1114/
%P 718-725
Markdown (Informal)
[Towards Automatic Transcription of ILSE ― an Interdisciplinary Longitudinal Study of Adult Development and Aging](https://aclanthology.org/L16-1114/) (Weiner et al., LREC 2016)
ACL