@inproceedings{woldemariam-2020-transfer,
title = "Transfer Learning for Less-Resourced {S}emitic Languages Speech Recognition: the Case of {A}mharic",
author = "Woldemariam, Yonas",
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-1.9",
pages = "61--69",
abstract = "While building automatic speech recognition (ASR) requires a large amount of speech and text data, the problem gets worse for less-resourced languages. In this paper, we investigate a model adaptation method, namely transfer learning for a less-resourced Semitic language i.e., Amharic, to solve resource scarcity problems in speech recognition development and improve the Amharic ASR model. In our experiments, we transfer acoustic models trained on two different source languages (English and Mandarin) to Amharic using very limited resources. The experimental results show that a significant WER (Word Error Rate) reduction has been achieved by transferring the hidden layers of the trained source languages neural networks. In the best case scenario, the Amharic ASR model adapted from English yields the best WER reduction from 38.72{\%} to 24.50{\%} (an improvement of 14.22{\%} absolute). Adapting the Mandarin model improves the baseline Amharic model with a WER reduction of 10.25{\%} (absolute). Our analysis also reveals that, the speech recognition performance of the adapted acoustic model is highly influenced by the relatedness (in a relative sense) between the source and the target languages than other considered factors (e.g. the quality of source models). Furthermore, other Semitic as well as Afro-Asiatic languages could benefit from the methodology presented in this study.",
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="woldemariam-2020-transfer">
<titleInfo>
<title>Transfer Learning for Less-Resourced Semitic Languages Speech Recognition: the Case of Amharic</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yonas</namePart>
<namePart type="family">Woldemariam</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>While building automatic speech recognition (ASR) requires a large amount of speech and text data, the problem gets worse for less-resourced languages. In this paper, we investigate a model adaptation method, namely transfer learning for a less-resourced Semitic language i.e., Amharic, to solve resource scarcity problems in speech recognition development and improve the Amharic ASR model. In our experiments, we transfer acoustic models trained on two different source languages (English and Mandarin) to Amharic using very limited resources. The experimental results show that a significant WER (Word Error Rate) reduction has been achieved by transferring the hidden layers of the trained source languages neural networks. In the best case scenario, the Amharic ASR model adapted from English yields the best WER reduction from 38.72% to 24.50% (an improvement of 14.22% absolute). Adapting the Mandarin model improves the baseline Amharic model with a WER reduction of 10.25% (absolute). Our analysis also reveals that, the speech recognition performance of the adapted acoustic model is highly influenced by the relatedness (in a relative sense) between the source and the target languages than other considered factors (e.g. the quality of source models). Furthermore, other Semitic as well as Afro-Asiatic languages could benefit from the methodology presented in this study.</abstract>
<identifier type="citekey">woldemariam-2020-transfer</identifier>
<location>
<url>https://aclanthology.org/2020.sltu-1.9</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>61</start>
<end>69</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Transfer Learning for Less-Resourced Semitic Languages Speech Recognition: the Case of Amharic
%A Woldemariam, Yonas
%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 woldemariam-2020-transfer
%X While building automatic speech recognition (ASR) requires a large amount of speech and text data, the problem gets worse for less-resourced languages. In this paper, we investigate a model adaptation method, namely transfer learning for a less-resourced Semitic language i.e., Amharic, to solve resource scarcity problems in speech recognition development and improve the Amharic ASR model. In our experiments, we transfer acoustic models trained on two different source languages (English and Mandarin) to Amharic using very limited resources. The experimental results show that a significant WER (Word Error Rate) reduction has been achieved by transferring the hidden layers of the trained source languages neural networks. In the best case scenario, the Amharic ASR model adapted from English yields the best WER reduction from 38.72% to 24.50% (an improvement of 14.22% absolute). Adapting the Mandarin model improves the baseline Amharic model with a WER reduction of 10.25% (absolute). Our analysis also reveals that, the speech recognition performance of the adapted acoustic model is highly influenced by the relatedness (in a relative sense) between the source and the target languages than other considered factors (e.g. the quality of source models). Furthermore, other Semitic as well as Afro-Asiatic languages could benefit from the methodology presented in this study.
%U https://aclanthology.org/2020.sltu-1.9
%P 61-69
Markdown (Informal)
[Transfer Learning for Less-Resourced Semitic Languages Speech Recognition: the Case of Amharic](https://aclanthology.org/2020.sltu-1.9) (Woldemariam, SLTU 2020)
ACL