@inproceedings{gupta-boulianne-2020-speech,
title = "Speech Transcription Challenges for Resource Constrained Indigenous Language {C}ree",
author = "Gupta, Vishwa and
Boulianne, Gilles",
editor = "Beermann, Dorothee and
Besacier, Laurent and
Sakti, Sakriani and
Soria, Claudia",
booktitle = "Proceedings of the 1st Joint Workshop on Spoken Language Technologies for Under-resourced languages (SLTU) and Collaboration and Computing for Under-Resourced Languages (CCURL)",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources association",
url = "https://aclanthology.org/2020.sltu-1.51",
pages = "362--367",
abstract = "Cree is one of the most spoken Indigenous languages in Canada. From a speech recognition perspective, it is a low-resource language, since very little data is available for either acoustic or language modeling. This has prevented development of speech technology that could help revitalize the language. We describe our experiments with available Cree data to improve automatic transcription both in speaker- independent and dependent scenarios. While it was difficult to get low speaker-independent word error rates with only six speakers, we were able to get low word and phoneme error rates in the speaker-dependent scenario. We compare our phoneme recognition with two state-of-the-art open-source phoneme recognition toolkits, which use end-to-end training and sequence-to-sequence modeling. Our phoneme error rate (8.7{\%}) is significantly lower than that achieved by the best of these systems (15.1{\%}). With these systems and varying amounts of transcribed and text data, we show that pre-training on other languages is important for speaker-independent recognition, and even small amounts of additional text-only documents are useful. These results can guide practical language documentation work, when deciding how much transcribed and text data is needed to achieve useful phoneme accuracies.",
language = "English",
ISBN = "979-10-95546-35-1",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gupta-boulianne-2020-speech">
<titleInfo>
<title>Speech Transcription Challenges for Resource Constrained Indigenous Language Cree</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 1st Joint Workshop on Spoken Language Technologies for Under-resourced languages (SLTU) and Collaboration and Computing for Under-Resourced Languages (CCURL)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dorothee</namePart>
<namePart type="family">Beermann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Laurent</namePart>
<namePart type="family">Besacier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Claudia</namePart>
<namePart type="family">Soria</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">979-10-95546-35-1</identifier>
</relatedItem>
<abstract>Cree is one of the most spoken Indigenous languages in Canada. From a speech recognition perspective, it is a low-resource language, since very little data is available for either acoustic or language modeling. This has prevented development of speech technology that could help revitalize the language. We describe our experiments with available Cree data to improve automatic transcription both in speaker- independent and dependent scenarios. While it was difficult to get low speaker-independent word error rates with only six speakers, we were able to get low word and phoneme error rates in the speaker-dependent scenario. We compare our phoneme recognition with two state-of-the-art open-source phoneme recognition toolkits, which use end-to-end training and sequence-to-sequence modeling. Our phoneme error rate (8.7%) is significantly lower than that achieved by the best of these systems (15.1%). With these systems and varying amounts of transcribed and text data, we show that pre-training on other languages is important for speaker-independent recognition, and even small amounts of additional text-only documents are useful. These results can guide practical language documentation work, when deciding how much transcribed and text data is needed to achieve useful phoneme accuracies.</abstract>
<identifier type="citekey">gupta-boulianne-2020-speech</identifier>
<location>
<url>https://aclanthology.org/2020.sltu-1.51</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>362</start>
<end>367</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Speech Transcription Challenges for Resource Constrained Indigenous Language Cree
%A Gupta, Vishwa
%A Boulianne, Gilles
%Y Beermann, Dorothee
%Y Besacier, Laurent
%Y Sakti, Sakriani
%Y Soria, Claudia
%S Proceedings of the 1st Joint Workshop on Spoken Language Technologies for Under-resourced languages (SLTU) and Collaboration and Computing for Under-Resourced Languages (CCURL)
%D 2020
%8 May
%I European Language Resources association
%C Marseille, France
%@ 979-10-95546-35-1
%G English
%F gupta-boulianne-2020-speech
%X Cree is one of the most spoken Indigenous languages in Canada. From a speech recognition perspective, it is a low-resource language, since very little data is available for either acoustic or language modeling. This has prevented development of speech technology that could help revitalize the language. We describe our experiments with available Cree data to improve automatic transcription both in speaker- independent and dependent scenarios. While it was difficult to get low speaker-independent word error rates with only six speakers, we were able to get low word and phoneme error rates in the speaker-dependent scenario. We compare our phoneme recognition with two state-of-the-art open-source phoneme recognition toolkits, which use end-to-end training and sequence-to-sequence modeling. Our phoneme error rate (8.7%) is significantly lower than that achieved by the best of these systems (15.1%). With these systems and varying amounts of transcribed and text data, we show that pre-training on other languages is important for speaker-independent recognition, and even small amounts of additional text-only documents are useful. These results can guide practical language documentation work, when deciding how much transcribed and text data is needed to achieve useful phoneme accuracies.
%U https://aclanthology.org/2020.sltu-1.51
%P 362-367
Markdown (Informal)
[Speech Transcription Challenges for Resource Constrained Indigenous Language Cree](https://aclanthology.org/2020.sltu-1.51) (Gupta & Boulianne, SLTU 2020)
ACL