@inproceedings{shah-etal-2019-cossat,
title = "{C}o{SSAT}: Code-Switched Speech Annotation Tool",
author = "Shah, Sanket and
Joshi, Pratik and
Santy, Sebastin and
Sitaram, Sunayana",
editor = "Paun, Silviu and
Hovy, Dirk",
booktitle = "Proceedings of the First Workshop on Aggregating and Analysing Crowdsourced Annotations for NLP",
month = nov,
year = "2019",
address = "Hong Kong",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D19-5907/",
doi = "10.18653/v1/D19-5907",
pages = "48--52",
abstract = "Code-switching refers to the alternation of two or more languages in a conversation or utterance and is common in multilingual communities across the world. Building code-switched speech and natural language processing systems are challenging due to the lack of annotated speech and text data. We present a speech annotation interface CoSSAT, which helps annotators transcribe code-switched speech faster, more easily and more accurately than a traditional interface, by displaying candidate words from monolingual speech recognizers. We conduct a user study on the transcription of Hindi-English code-switched speech with 10 annotators and describe quantitative and qualitative results."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shah-etal-2019-cossat">
<titleInfo>
<title>CoSSAT: Code-Switched Speech Annotation Tool</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sanket</namePart>
<namePart type="family">Shah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pratik</namePart>
<namePart type="family">Joshi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastin</namePart>
<namePart type="family">Santy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunayana</namePart>
<namePart type="family">Sitaram</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the First Workshop on Aggregating and Analysing Crowdsourced Annotations for NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Silviu</namePart>
<namePart type="family">Paun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dirk</namePart>
<namePart type="family">Hovy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hong Kong</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Code-switching refers to the alternation of two or more languages in a conversation or utterance and is common in multilingual communities across the world. Building code-switched speech and natural language processing systems are challenging due to the lack of annotated speech and text data. We present a speech annotation interface CoSSAT, which helps annotators transcribe code-switched speech faster, more easily and more accurately than a traditional interface, by displaying candidate words from monolingual speech recognizers. We conduct a user study on the transcription of Hindi-English code-switched speech with 10 annotators and describe quantitative and qualitative results.</abstract>
<identifier type="citekey">shah-etal-2019-cossat</identifier>
<identifier type="doi">10.18653/v1/D19-5907</identifier>
<location>
<url>https://aclanthology.org/D19-5907/</url>
</location>
<part>
<date>2019-11</date>
<extent unit="page">
<start>48</start>
<end>52</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CoSSAT: Code-Switched Speech Annotation Tool
%A Shah, Sanket
%A Joshi, Pratik
%A Santy, Sebastin
%A Sitaram, Sunayana
%Y Paun, Silviu
%Y Hovy, Dirk
%S Proceedings of the First Workshop on Aggregating and Analysing Crowdsourced Annotations for NLP
%D 2019
%8 November
%I Association for Computational Linguistics
%C Hong Kong
%F shah-etal-2019-cossat
%X Code-switching refers to the alternation of two or more languages in a conversation or utterance and is common in multilingual communities across the world. Building code-switched speech and natural language processing systems are challenging due to the lack of annotated speech and text data. We present a speech annotation interface CoSSAT, which helps annotators transcribe code-switched speech faster, more easily and more accurately than a traditional interface, by displaying candidate words from monolingual speech recognizers. We conduct a user study on the transcription of Hindi-English code-switched speech with 10 annotators and describe quantitative and qualitative results.
%R 10.18653/v1/D19-5907
%U https://aclanthology.org/D19-5907/
%U https://doi.org/10.18653/v1/D19-5907
%P 48-52
Markdown (Informal)
[CoSSAT: Code-Switched Speech Annotation Tool](https://aclanthology.org/D19-5907/) (Shah et al., 2019)
ACL
- Sanket Shah, Pratik Joshi, Sebastin Santy, and Sunayana Sitaram. 2019. CoSSAT: Code-Switched Speech Annotation Tool. In Proceedings of the First Workshop on Aggregating and Analysing Crowdsourced Annotations for NLP, pages 48–52, Hong Kong. Association for Computational Linguistics.