@inproceedings{stein-usabaev-2012-automatic,
title = "Automatic Speech Recognition on a Firefighter {TETRA} Broadcast Channel",
author = "Stein, Daniel and
Usabaev, Bela",
booktitle = "Proceedings of the Eighth International Conference on Language Resources and Evaluation ({LREC}'12)",
month = may,
year = "2012",
address = "Istanbul, Turkey",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2012/pdf/113_Paper.pdf",
pages = "119--124",
abstract = "For a reliable keyword extraction on firefighter radio communication, a strong automatic speech recognition system is needed. However, real-life data poses several challenges like a distorted voice signal, background noise and several different speakers. Moreover, the domain is out-of-scope for common language models, and the available data is scarce. In this paper, we introduce the PRONTO corpus, which consists of German firefighter exercise transcriptions. We show that by standard adaption techniques the recognition rate already rises from virtually zero to up to 51.7{\%} and can be further improved by domain-specific rules to 47.9{\%}. Extending the acoustic material by semi-automatic transcription and crawled in-domain written material, we arrive at a WER of 45.2{\%}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="stein-usabaev-2012-automatic">
<titleInfo>
<title>Automatic Speech Recognition on a Firefighter TETRA Broadcast Channel</title>
</titleInfo>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Stein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bela</namePart>
<namePart type="family">Usabaev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2012-may</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)</title>
</titleInfo>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Istanbul, Turkey</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>For a reliable keyword extraction on firefighter radio communication, a strong automatic speech recognition system is needed. However, real-life data poses several challenges like a distorted voice signal, background noise and several different speakers. Moreover, the domain is out-of-scope for common language models, and the available data is scarce. In this paper, we introduce the PRONTO corpus, which consists of German firefighter exercise transcriptions. We show that by standard adaption techniques the recognition rate already rises from virtually zero to up to 51.7% and can be further improved by domain-specific rules to 47.9%. Extending the acoustic material by semi-automatic transcription and crawled in-domain written material, we arrive at a WER of 45.2%.</abstract>
<identifier type="citekey">stein-usabaev-2012-automatic</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/113_Paper.pdf</url>
</location>
<part>
<date>2012-may</date>
<extent unit="page">
<start>119</start>
<end>124</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Automatic Speech Recognition on a Firefighter TETRA Broadcast Channel
%A Stein, Daniel
%A Usabaev, Bela
%S Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)
%D 2012
%8 may
%I European Language Resources Association (ELRA)
%C Istanbul, Turkey
%F stein-usabaev-2012-automatic
%X For a reliable keyword extraction on firefighter radio communication, a strong automatic speech recognition system is needed. However, real-life data poses several challenges like a distorted voice signal, background noise and several different speakers. Moreover, the domain is out-of-scope for common language models, and the available data is scarce. In this paper, we introduce the PRONTO corpus, which consists of German firefighter exercise transcriptions. We show that by standard adaption techniques the recognition rate already rises from virtually zero to up to 51.7% and can be further improved by domain-specific rules to 47.9%. Extending the acoustic material by semi-automatic transcription and crawled in-domain written material, we arrive at a WER of 45.2%.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/113_Paper.pdf
%P 119-124
Markdown (Informal)
[Automatic Speech Recognition on a Firefighter TETRA Broadcast Channel](http://www.lrec-conf.org/proceedings/lrec2012/pdf/113_Paper.pdf) (Stein & Usabaev, LREC 2012)
ACL