@inproceedings{salesky-etal-2016-operational,
title = "Operational Assessment of Keyword Search on Oral History",
author = "Salesky, Elizabeth and
Ray, Jessica and
Shen, Wade",
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/L16-1049",
pages = "317--321",
abstract = "This project assesses the resources necessary to make oral history searchable by means of automatic speech recognition (ASR). There are many inherent challenges in applying ASR to conversational speech: smaller training set sizes and varying demographics, among others. We assess the impact of dataset size, word error rate and term-weighted value on human search capability through an information retrieval task on Mechanical Turk. We use English oral history data collected by StoryCorps, a national organization that provides all people with the opportunity to record, share and preserve their stories, and control for a variety of demographics including age, gender, birthplace, and dialect on four different training set sizes. We show comparable search performance using a standard speech recognition system as with hand-transcribed data, which is promising for increased accessibility of conversational speech and oral history archives.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="salesky-etal-2016-operational">
<titleInfo>
<title>Operational Assessment of Keyword Search on Oral History</title>
</titleInfo>
<name type="personal">
<namePart type="given">Elizabeth</namePart>
<namePart type="family">Salesky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessica</namePart>
<namePart type="family">Ray</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wade</namePart>
<namePart type="family">Shen</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>This project assesses the resources necessary to make oral history searchable by means of automatic speech recognition (ASR). There are many inherent challenges in applying ASR to conversational speech: smaller training set sizes and varying demographics, among others. We assess the impact of dataset size, word error rate and term-weighted value on human search capability through an information retrieval task on Mechanical Turk. We use English oral history data collected by StoryCorps, a national organization that provides all people with the opportunity to record, share and preserve their stories, and control for a variety of demographics including age, gender, birthplace, and dialect on four different training set sizes. We show comparable search performance using a standard speech recognition system as with hand-transcribed data, which is promising for increased accessibility of conversational speech and oral history archives.</abstract>
<identifier type="citekey">salesky-etal-2016-operational</identifier>
<location>
<url>https://aclanthology.org/L16-1049</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>317</start>
<end>321</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Operational Assessment of Keyword Search on Oral History
%A Salesky, Elizabeth
%A Ray, Jessica
%A Shen, Wade
%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 salesky-etal-2016-operational
%X This project assesses the resources necessary to make oral history searchable by means of automatic speech recognition (ASR). There are many inherent challenges in applying ASR to conversational speech: smaller training set sizes and varying demographics, among others. We assess the impact of dataset size, word error rate and term-weighted value on human search capability through an information retrieval task on Mechanical Turk. We use English oral history data collected by StoryCorps, a national organization that provides all people with the opportunity to record, share and preserve their stories, and control for a variety of demographics including age, gender, birthplace, and dialect on four different training set sizes. We show comparable search performance using a standard speech recognition system as with hand-transcribed data, which is promising for increased accessibility of conversational speech and oral history archives.
%U https://aclanthology.org/L16-1049
%P 317-321
Markdown (Informal)
[Operational Assessment of Keyword Search on Oral History](https://aclanthology.org/L16-1049) (Salesky et al., LREC 2016)
ACL
- Elizabeth Salesky, Jessica Ray, and Wade Shen. 2016. Operational Assessment of Keyword Search on Oral History. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16), pages 317–321, Portorož, Slovenia. European Language Resources Association (ELRA).