@inproceedings{mcgraw-etal-2010-collecting,
title = "Collecting Voices from the Cloud",
author = "McGraw, Ian and
Lee, Chia-ying and
Hetherington, Lee and
Seneff, Stephanie and
Glass, Jim",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Rosner, Mike and
Tapias, Daniel",
booktitle = "Proceedings of the Seventh International Conference on Language Resources and Evaluation ({LREC}'10)",
month = may,
year = "2010",
address = "Valletta, Malta",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2010/pdf/822_Paper.pdf",
abstract = "The collection and transcription of speech data is typically an expensive and time-consuming task. Voice over IP and cloud computing are poised to greatly reduce this impediment to research on spoken language interfaces in many domains. This paper documents our efforts to deploy speech-enabled web interfaces to large audiences over the Internet via Amazon Mechanical Turk, an online marketplace for work. Using the open source WAMI Toolkit, we collected corpora in two different domains which collectively constitute over 113 hours of speech. The first corpus contains 100,000 utterances of read speech, and was collected by asking workers to record street addresses in the United States. For the second task, we collected conversations with FlightBrowser, a multimodal spoken dialogue system. The FlightBrowser corpus obtained contains 10,651 utterances composing 1,113 individual dialogue sessions from 101 distinct users. The aggregate time spent collecting the data for both corpora was just under two weeks. At times, our servers were logging audio from workers at rates faster than real-time. We describe the process of collection and transcription of these corpora while providing an analysis of the advantages and limitations to this data collection method.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mcgraw-etal-2010-collecting">
<titleInfo>
<title>Collecting Voices from the Cloud</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ian</namePart>
<namePart type="family">McGraw</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chia-ying</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lee</namePart>
<namePart type="family">Hetherington</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stephanie</namePart>
<namePart type="family">Seneff</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jim</namePart>
<namePart type="family">Glass</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2010-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)</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">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">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>
<name type="personal">
<namePart type="given">Mike</namePart>
<namePart type="family">Rosner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Tapias</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Valletta, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The collection and transcription of speech data is typically an expensive and time-consuming task. Voice over IP and cloud computing are poised to greatly reduce this impediment to research on spoken language interfaces in many domains. This paper documents our efforts to deploy speech-enabled web interfaces to large audiences over the Internet via Amazon Mechanical Turk, an online marketplace for work. Using the open source WAMI Toolkit, we collected corpora in two different domains which collectively constitute over 113 hours of speech. The first corpus contains 100,000 utterances of read speech, and was collected by asking workers to record street addresses in the United States. For the second task, we collected conversations with FlightBrowser, a multimodal spoken dialogue system. The FlightBrowser corpus obtained contains 10,651 utterances composing 1,113 individual dialogue sessions from 101 distinct users. The aggregate time spent collecting the data for both corpora was just under two weeks. At times, our servers were logging audio from workers at rates faster than real-time. We describe the process of collection and transcription of these corpora while providing an analysis of the advantages and limitations to this data collection method.</abstract>
<identifier type="citekey">mcgraw-etal-2010-collecting</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/822_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Collecting Voices from the Cloud
%A McGraw, Ian
%A Lee, Chia-ying
%A Hetherington, Lee
%A Seneff, Stephanie
%A Glass, Jim
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Rosner, Mike
%Y Tapias, Daniel
%S Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)
%D 2010
%8 May
%I European Language Resources Association (ELRA)
%C Valletta, Malta
%F mcgraw-etal-2010-collecting
%X The collection and transcription of speech data is typically an expensive and time-consuming task. Voice over IP and cloud computing are poised to greatly reduce this impediment to research on spoken language interfaces in many domains. This paper documents our efforts to deploy speech-enabled web interfaces to large audiences over the Internet via Amazon Mechanical Turk, an online marketplace for work. Using the open source WAMI Toolkit, we collected corpora in two different domains which collectively constitute over 113 hours of speech. The first corpus contains 100,000 utterances of read speech, and was collected by asking workers to record street addresses in the United States. For the second task, we collected conversations with FlightBrowser, a multimodal spoken dialogue system. The FlightBrowser corpus obtained contains 10,651 utterances composing 1,113 individual dialogue sessions from 101 distinct users. The aggregate time spent collecting the data for both corpora was just under two weeks. At times, our servers were logging audio from workers at rates faster than real-time. We describe the process of collection and transcription of these corpora while providing an analysis of the advantages and limitations to this data collection method.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/822_Paper.pdf
Markdown (Informal)
[Collecting Voices from the Cloud](http://www.lrec-conf.org/proceedings/lrec2010/pdf/822_Paper.pdf) (McGraw et al., LREC 2010)
ACL
- Ian McGraw, Chia-ying Lee, Lee Hetherington, Stephanie Seneff, and Jim Glass. 2010. Collecting Voices from the Cloud. In Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC'10), Valletta, Malta. European Language Resources Association (ELRA).