@inproceedings{tachbelie-etal-2020-dnn,
title = "{DNN}-Based Multilingual Automatic Speech Recognition for {W}olaytta using {O}romo Speech",
author = "Tachbelie, Martha Yifiru and
Abate, Solomon Teferra and
Schultz, Tanja",
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-1.37",
pages = "265--270",
abstract = "It is known that Automatic Speech Recognition (ASR) is very useful for human-computer interaction in all the human languages. However, due to its requirement for a big speech corpus, which is very expensive, it has not been developed for most of the languages. Multilingual ASR (MLASR) has been suggested to share existing speech corpora among related languages to develop an ASR for languages which do not have the required speech corpora. Literature shows that phonetic relatedness goes across language families. We have, therefore, conducted experiments on MLASR taking two language families: one as source (Oromo from Cushitic) and the other as target (Wolaytta from Omotic). Using Oromo Deep Neural Network (DNN) based acoustic model, Wolaytta pronunciation dictionary and language model we have achieved Word Error Rate (WER) of 48.34{\%} for Wolaytta. Moreover, our experiments show that adding only 30 minutes of speech data from the target language (Wolaytta) to the whole training data (22.8 hours) of the source language (Oromo) results in a relative WER reduction of 32.77{\%}. Our results show the possibility of developing ASR system for a language, if we have pronunciation dictionary and language model, using an existing speech corpus of another language irrespective of their language family.",
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="tachbelie-etal-2020-dnn">
<titleInfo>
<title>DNN-Based Multilingual Automatic Speech Recognition for Wolaytta using Oromo Speech</title>
</titleInfo>
<name type="personal">
<namePart type="given">Martha</namePart>
<namePart type="given">Yifiru</namePart>
<namePart type="family">Tachbelie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Solomon</namePart>
<namePart type="given">Teferra</namePart>
<namePart type="family">Abate</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanja</namePart>
<namePart type="family">Schultz</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>It is known that Automatic Speech Recognition (ASR) is very useful for human-computer interaction in all the human languages. However, due to its requirement for a big speech corpus, which is very expensive, it has not been developed for most of the languages. Multilingual ASR (MLASR) has been suggested to share existing speech corpora among related languages to develop an ASR for languages which do not have the required speech corpora. Literature shows that phonetic relatedness goes across language families. We have, therefore, conducted experiments on MLASR taking two language families: one as source (Oromo from Cushitic) and the other as target (Wolaytta from Omotic). Using Oromo Deep Neural Network (DNN) based acoustic model, Wolaytta pronunciation dictionary and language model we have achieved Word Error Rate (WER) of 48.34% for Wolaytta. Moreover, our experiments show that adding only 30 minutes of speech data from the target language (Wolaytta) to the whole training data (22.8 hours) of the source language (Oromo) results in a relative WER reduction of 32.77%. Our results show the possibility of developing ASR system for a language, if we have pronunciation dictionary and language model, using an existing speech corpus of another language irrespective of their language family.</abstract>
<identifier type="citekey">tachbelie-etal-2020-dnn</identifier>
<location>
<url>https://aclanthology.org/2020.sltu-1.37</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>265</start>
<end>270</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DNN-Based Multilingual Automatic Speech Recognition for Wolaytta using Oromo Speech
%A Tachbelie, Martha Yifiru
%A Abate, Solomon Teferra
%A Schultz, Tanja
%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 tachbelie-etal-2020-dnn
%X It is known that Automatic Speech Recognition (ASR) is very useful for human-computer interaction in all the human languages. However, due to its requirement for a big speech corpus, which is very expensive, it has not been developed for most of the languages. Multilingual ASR (MLASR) has been suggested to share existing speech corpora among related languages to develop an ASR for languages which do not have the required speech corpora. Literature shows that phonetic relatedness goes across language families. We have, therefore, conducted experiments on MLASR taking two language families: one as source (Oromo from Cushitic) and the other as target (Wolaytta from Omotic). Using Oromo Deep Neural Network (DNN) based acoustic model, Wolaytta pronunciation dictionary and language model we have achieved Word Error Rate (WER) of 48.34% for Wolaytta. Moreover, our experiments show that adding only 30 minutes of speech data from the target language (Wolaytta) to the whole training data (22.8 hours) of the source language (Oromo) results in a relative WER reduction of 32.77%. Our results show the possibility of developing ASR system for a language, if we have pronunciation dictionary and language model, using an existing speech corpus of another language irrespective of their language family.
%U https://aclanthology.org/2020.sltu-1.37
%P 265-270
Markdown (Informal)
[DNN-Based Multilingual Automatic Speech Recognition for Wolaytta using Oromo Speech](https://aclanthology.org/2020.sltu-1.37) (Tachbelie et al., SLTU 2020)
ACL