@inproceedings{liu-etal-2010-large,
title = "A Very Large Scale {M}andarin {C}hinese Broadcast Corpus for {GALE} Project",
author = "Liu, Yi and
Fung, Pascale and
Yang, Yongsheng and
DiPersio, Denise and
Glenn, Meghan and
Strassel, Stephanie and
Cieri, Christopher",
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/664_Paper.pdf",
abstract = "In this paper, we present the design, collection, transcription and analysis of a Mandarin Chinese Broadcast Collection of over 3000 hours. The data was collected by Hong Kong University of Science and Technology (HKUST) in China on a cable TV and satellite transmission platform established in support of the DARPA Global Autonomous Language Exploitation (GALE) program. The collection includes broadcast news (BN) and broadcast conversation (BC) including talk shows, roundtable discussions, call-in shows, editorials and other conversational programs that focus on news and current events. HKUST also collects detailed information about all recorded programs. A subset of BC and BN recordings are manually transcribed with standard Chinese characters in UTF-8 encoding, using specific mark-ups for a small set of spontaneous and conversational speech phenomena. The collection is among the largest and first of its kind for Mandarin Chinese Broadcast speech, providing abundant and diverse samples for Mandarin speech recognition and other application-dependent tasks, such as spontaneous speech processing and recognition, topic detection, information retrieval, and speaker recognition. HKUST{\^a}s acoustic analysis of 500 hours of the speech and transcripts demonstrates the positive impact this data could have on system performance.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2010-large">
<titleInfo>
<title>A Very Large Scale Mandarin Chinese Broadcast Corpus for GALE Project</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yi</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pascale</namePart>
<namePart type="family">Fung</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yongsheng</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Denise</namePart>
<namePart type="family">DiPersio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Meghan</namePart>
<namePart type="family">Glenn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stephanie</namePart>
<namePart type="family">Strassel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</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>In this paper, we present the design, collection, transcription and analysis of a Mandarin Chinese Broadcast Collection of over 3000 hours. The data was collected by Hong Kong University of Science and Technology (HKUST) in China on a cable TV and satellite transmission platform established in support of the DARPA Global Autonomous Language Exploitation (GALE) program. The collection includes broadcast news (BN) and broadcast conversation (BC) including talk shows, roundtable discussions, call-in shows, editorials and other conversational programs that focus on news and current events. HKUST also collects detailed information about all recorded programs. A subset of BC and BN recordings are manually transcribed with standard Chinese characters in UTF-8 encoding, using specific mark-ups for a small set of spontaneous and conversational speech phenomena. The collection is among the largest and first of its kind for Mandarin Chinese Broadcast speech, providing abundant and diverse samples for Mandarin speech recognition and other application-dependent tasks, such as spontaneous speech processing and recognition, topic detection, information retrieval, and speaker recognition. HKUSTâs acoustic analysis of 500 hours of the speech and transcripts demonstrates the positive impact this data could have on system performance.</abstract>
<identifier type="citekey">liu-etal-2010-large</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/664_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Very Large Scale Mandarin Chinese Broadcast Corpus for GALE Project
%A Liu, Yi
%A Fung, Pascale
%A Yang, Yongsheng
%A DiPersio, Denise
%A Glenn, Meghan
%A Strassel, Stephanie
%A Cieri, Christopher
%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 liu-etal-2010-large
%X In this paper, we present the design, collection, transcription and analysis of a Mandarin Chinese Broadcast Collection of over 3000 hours. The data was collected by Hong Kong University of Science and Technology (HKUST) in China on a cable TV and satellite transmission platform established in support of the DARPA Global Autonomous Language Exploitation (GALE) program. The collection includes broadcast news (BN) and broadcast conversation (BC) including talk shows, roundtable discussions, call-in shows, editorials and other conversational programs that focus on news and current events. HKUST also collects detailed information about all recorded programs. A subset of BC and BN recordings are manually transcribed with standard Chinese characters in UTF-8 encoding, using specific mark-ups for a small set of spontaneous and conversational speech phenomena. The collection is among the largest and first of its kind for Mandarin Chinese Broadcast speech, providing abundant and diverse samples for Mandarin speech recognition and other application-dependent tasks, such as spontaneous speech processing and recognition, topic detection, information retrieval, and speaker recognition. HKUSTâs acoustic analysis of 500 hours of the speech and transcripts demonstrates the positive impact this data could have on system performance.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/664_Paper.pdf
Markdown (Informal)
[A Very Large Scale Mandarin Chinese Broadcast Corpus for GALE Project](http://www.lrec-conf.org/proceedings/lrec2010/pdf/664_Paper.pdf) (Liu et al., LREC 2010)
ACL
- Yi Liu, Pascale Fung, Yongsheng Yang, Denise DiPersio, Meghan Glenn, Stephanie Strassel, and Christopher Cieri. 2010. A Very Large Scale Mandarin Chinese Broadcast Corpus for GALE Project. In Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC'10), Valletta, Malta. European Language Resources Association (ELRA).