2026-09-20T11:55:18Zhttps://dspace.mit.edu/server/oai/requestoai:dspace.mit.edu:1721.1/1399532022-02-08T03:06:09Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023
Glass, James R.
Belinkov, Yonatan
Manna, Rami
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
2022-02-07T15:15:18Z
2022-02-07T15:15:18Z
2021-09
2021-11-03T19:25:26.781Z
https://hdl.handle.net/1721.1/139953
This thesis explores novel approaches to the Arabic-English speech-to-text translation task. First, we construct a novel Modern Standard Arabic speech and English text parallel dataset. Second, we propose a novel framework for leveraging unsupervised machine translation to improve speech-to-text translation, and apply this framework to the task of Arabic-English speech-to-text translation. In particular, we propose a 3-step cascade approach to speech-to-text translation. In step 1, we use a speech recognition model to transcribe the Arabic speech into Arabic text. In step 2, we leverage unsupervised machine translation to learn a mapping between the output of the speech recognition model (transcribed Arabic) and Modern Standard Arabic (formal written Arabic). In step 3, we use an Arabic-English machine translation model to translate the output of the unsupervised model to English. Our third contribution is an exploration of approaches to low-resource end-to-end speech-to-text translation. We present and compare two approaches for synthesizing parallel training data. Finally, we compare the end-to-end approach with the cascaded approach. We found that the 3-step cascaded speech-to-text did not perform as well as the 2-step cascaded speech-to-text baseline. We show that with the end-to-end approach trained with synthetic English text, we are able to achieve similar performance to the 2-step cascaded speech-to-text baseline.
M.Eng.
Massachusetts Institute of Technology
In Copyright - Educational Use Permitted
Copyright MIT
http://rightsstatements.org/page/InC-EDU/1.0/
Constructing Low Resource Approaches to Improve Speech-to-text Translation from Modern Standard Arabic to English
Thesis
application/pdf
Master
Master of Engineering in Electrical Engineering and Computer Science
Publication
unknown
unknown
<Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="dddc505c-0527-4e4b-a3c1-317e912eed9b">
<Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843</Type>
<Title>Constructing Low Resource Approaches to Improve Speech-to-text Translation from Modern Standard Arabic to English</Title>
<PublishedIn>
<Publication>
</Publication>
</PublishedIn>
<PublicationDate>2021-09</PublicationDate>
<Authors>
<Author>
<DisplayName>Manna, Rami</DisplayName>
<Affiliation>
<OrgUnit>
</OrgUnit>
</Affiliation>
</Author>
</Authors>
<Editors>
</Editors>
<Publishers>
<Publisher>
<DisplayName>Massachusetts Institute of Technology</DisplayName>
<OrgUnit />
</Publisher>
</Publishers>
<License>http://rightsstatements.org/page/InC-EDU/1.0/</License>
<Abstract>This thesis explores novel approaches to the Arabic-English speech-to-text translation task. First, we construct a novel Modern Standard Arabic speech and English text parallel dataset. Second, we propose a novel framework for leveraging unsupervised machine translation to improve speech-to-text translation, and apply this framework to the task of Arabic-English speech-to-text translation. In particular, we propose a 3-step cascade approach to speech-to-text translation. In step 1, we use a speech recognition model to transcribe the Arabic speech into Arabic text. In step 2, we leverage unsupervised machine translation to learn a mapping between the output of the speech recognition model (transcribed Arabic) and Modern Standard Arabic (formal written Arabic). In step 3, we use an Arabic-English machine translation model to translate the output of the unsupervised model to English. Our third contribution is an exploration of approaches to low-resource end-to-end speech-to-text translation. We present and compare two approaches for synthesizing parallel training data. Finally, we compare the end-to-end approach with the cascaded approach. We found that the 3-step cascaded speech-to-text did not perform as well as the 2-step cascaded speech-to-text baseline. We show that with the end-to-end approach trained with synthetic English text, we are able to achieve similar performance to the 2-step cascaded speech-to-text baseline.</Abstract>
<Access xmlns="http://purl.org/coar/access_right"
>
</Access>
</Publication>