@inproceedings{gupta-boulianne-2020-automatic,
title = "Automatic Transcription Challenges for {I}nuktitut, a Low-Resource Polysynthetic Language",
author = "Gupta, Vishwa and
Boulianne, Gilles",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.307",
pages = "2521--2527",
abstract = "We introduce the first attempt at automatic speech recognition (ASR) in Inuktitut, as a representative for polysynthetic, low-resource languages, like many of the 900 Indigenous languages spoken in the Americas. As most previous work on Inuktitut, we use texts from parliament proceedings, but in addition we have access to 23 hours of transcribed oral stories. With this corpus, we show that Inuktitut displays a much higher degree of polysynthesis than other agglutinative languages usually considered in ASR, such as Finnish or Turkish. Even with a vocabulary of 1.3 million words derived from proceedings and stories, held-out stories have more than 60{\%} of words out-of-vocabulary. We train bi-directional LSTM acoustic models, then investigate word and subword units, morphemes and syllables, and a deep neural network that finds word boundaries in subword sequences. We show that acoustic decoding using syllables decorated with word boundary markers results in the lowest word error rate.",
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gupta-boulianne-2020-automatic">
<titleInfo>
<title>Automatic Transcription Challenges for Inuktitut, a Low-Resource Polysynthetic Language</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vishwa</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gilles</namePart>
<namePart type="family">Boulianne</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Twelfth Language Resources and Evaluation Conference</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">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</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">Christopher</namePart>
<namePart type="family">Cieri</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">Hitoshi</namePart>
<namePart type="family">Isahara</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">Hélène</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</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>We introduce the first attempt at automatic speech recognition (ASR) in Inuktitut, as a representative for polysynthetic, low-resource languages, like many of the 900 Indigenous languages spoken in the Americas. As most previous work on Inuktitut, we use texts from parliament proceedings, but in addition we have access to 23 hours of transcribed oral stories. With this corpus, we show that Inuktitut displays a much higher degree of polysynthesis than other agglutinative languages usually considered in ASR, such as Finnish or Turkish. Even with a vocabulary of 1.3 million words derived from proceedings and stories, held-out stories have more than 60% of words out-of-vocabulary. We train bi-directional LSTM acoustic models, then investigate word and subword units, morphemes and syllables, and a deep neural network that finds word boundaries in subword sequences. We show that acoustic decoding using syllables decorated with word boundary markers results in the lowest word error rate.</abstract>
<identifier type="citekey">gupta-boulianne-2020-automatic</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.307</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>2521</start>
<end>2527</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Automatic Transcription Challenges for Inuktitut, a Low-Resource Polysynthetic Language
%A Gupta, Vishwa
%A Boulianne, Gilles
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Twelfth Language Resources and Evaluation Conference
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G English
%F gupta-boulianne-2020-automatic
%X We introduce the first attempt at automatic speech recognition (ASR) in Inuktitut, as a representative for polysynthetic, low-resource languages, like many of the 900 Indigenous languages spoken in the Americas. As most previous work on Inuktitut, we use texts from parliament proceedings, but in addition we have access to 23 hours of transcribed oral stories. With this corpus, we show that Inuktitut displays a much higher degree of polysynthesis than other agglutinative languages usually considered in ASR, such as Finnish or Turkish. Even with a vocabulary of 1.3 million words derived from proceedings and stories, held-out stories have more than 60% of words out-of-vocabulary. We train bi-directional LSTM acoustic models, then investigate word and subword units, morphemes and syllables, and a deep neural network that finds word boundaries in subword sequences. We show that acoustic decoding using syllables decorated with word boundary markers results in the lowest word error rate.
%U https://aclanthology.org/2020.lrec-1.307
%P 2521-2527
Markdown (Informal)
[Automatic Transcription Challenges for Inuktitut, a Low-Resource Polysynthetic Language](https://aclanthology.org/2020.lrec-1.307) (Gupta & Boulianne, LREC 2020)
ACL