@inproceedings{sitaram-black-2016-speech,
title = "Speech Synthesis of Code-Mixed Text",
author = "Sitaram, Sunayana and
Black, Alan W",
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/L16-1546",
pages = "3422--3428",
abstract = "Most Text to Speech (TTS) systems today assume that the input text is in a single language and is written in the same language that the text needs to be synthesized in. However, in bilingual and multilingual communities, code mixing or code switching occurs in speech, in which speakers switch between languages in the same utterance. Due to the popularity of social media, we now see code-mixing even in text in these multilingual communities. TTS systems capable of synthesizing such text need to be able to handle text that is written in multiple languages and scripts. Code-mixed text poses many challenges to TTS systems, such as language identification, spelling normalization and pronunciation modeling. In this work, we describe a preliminary framework for synthesizing code-mixed text. We carry out experiments on synthesizing code-mixed Hindi and English text. We find that there is a significant user preference for TTS systems that can correctly identify and pronounce words in different languages.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sitaram-black-2016-speech">
<titleInfo>
<title>Speech Synthesis of Code-Mixed Text</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sunayana</namePart>
<namePart type="family">Sitaram</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="given">W</namePart>
<namePart type="family">Black</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>Most Text to Speech (TTS) systems today assume that the input text is in a single language and is written in the same language that the text needs to be synthesized in. However, in bilingual and multilingual communities, code mixing or code switching occurs in speech, in which speakers switch between languages in the same utterance. Due to the popularity of social media, we now see code-mixing even in text in these multilingual communities. TTS systems capable of synthesizing such text need to be able to handle text that is written in multiple languages and scripts. Code-mixed text poses many challenges to TTS systems, such as language identification, spelling normalization and pronunciation modeling. In this work, we describe a preliminary framework for synthesizing code-mixed text. We carry out experiments on synthesizing code-mixed Hindi and English text. We find that there is a significant user preference for TTS systems that can correctly identify and pronounce words in different languages.</abstract>
<identifier type="citekey">sitaram-black-2016-speech</identifier>
<location>
<url>https://aclanthology.org/L16-1546</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>3422</start>
<end>3428</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Speech Synthesis of Code-Mixed Text
%A Sitaram, Sunayana
%A Black, Alan W.
%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 sitaram-black-2016-speech
%X Most Text to Speech (TTS) systems today assume that the input text is in a single language and is written in the same language that the text needs to be synthesized in. However, in bilingual and multilingual communities, code mixing or code switching occurs in speech, in which speakers switch between languages in the same utterance. Due to the popularity of social media, we now see code-mixing even in text in these multilingual communities. TTS systems capable of synthesizing such text need to be able to handle text that is written in multiple languages and scripts. Code-mixed text poses many challenges to TTS systems, such as language identification, spelling normalization and pronunciation modeling. In this work, we describe a preliminary framework for synthesizing code-mixed text. We carry out experiments on synthesizing code-mixed Hindi and English text. We find that there is a significant user preference for TTS systems that can correctly identify and pronounce words in different languages.
%U https://aclanthology.org/L16-1546
%P 3422-3428
Markdown (Informal)
[Speech Synthesis of Code-Mixed Text](https://aclanthology.org/L16-1546) (Sitaram & Black, LREC 2016)
ACL
- Sunayana Sitaram and Alan W Black. 2016. Speech Synthesis of Code-Mixed Text. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16), pages 3422–3428, Portorož, Slovenia. European Language Resources Association (ELRA).