{"id":{"repo_id":"mit","oai_identifier":"oai:dspace.mit.edu:1721.1/139953"},"canonical_url":"https://search.dev.ndltd.org/etd/mit/oai:dspace.mit.edu:1721.1/139953","repository":{"repo_id":"mit","name":"MIT","base_url":"https://dspace.mit.edu/oai/request"},"display":{"title":"Constructing Low Resource Approaches to Improve Speech-to-text Translation from Modern Standard Arabic to English","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_html":"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_has_math":false,"creators":["Manna, Rami"],"institution":"Massachusetts Institute of Technology","degree_name":"Master","degree_level":null,"degree_discipline":null,"degree_department":"Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science","school":null,"contributors":[],"advisors":["Glass, James R.","Belinkov, Yonatan"],"committee_chairs":[],"committee_members":[],"year":2021,"date_issued":"2021-09","date_published":"2021-09","updated_at":"2026-07-22T22:22:18Z","subjects":[],"languages":[],"rights":["In Copyright - Educational Use Permitted","Copyright MIT"],"rights_urls":["http://rightsstatements.org/page/InC-EDU/1.0/"],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/1721.1/139953","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Glass, James R.","Belinkov, Yonatan"]},{"key":"dc:contributor.department","label":"Department","values":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science"]},{"key":"dc:creator","label":"Author","values":["Manna, Rami"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2022-02-07T15:15:18Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2022-02-07T15:15:18Z"]},{"key":"dc:date.issued","label":"Date","values":["2021-09"]},{"key":"dc:publisher","label":"Institution","values":["Massachusetts Institute of Technology"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master","Master of Engineering in Electrical Engineering and Computer Science"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:rights","label":"Dc Rights","values":["In Copyright - Educational Use Permitted","Copyright MIT"]},{"key":"dc:rights.uri","label":"Rights URI","values":["http://rightsstatements.org/page/InC-EDU/1.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/1721.1/139953"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["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."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["M.Eng."]},{"key":"dc:title","label":"Title","values":["Constructing Low Resource Approaches to Improve Speech-to-text Translation from Modern Standard Arabic to English"]}]}],"canonical_facts":{"dc:contributor.advisor":["Glass, James R.","Belinkov, Yonatan"],"dc:contributor.department":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science"],"dc:creator":["Manna, Rami"],"dc:date.accessioned":["2022-02-07T15:15:18Z"],"dc:date.available":["2022-02-07T15:15:18Z"],"dc:date.issued":["2021-09"],"dc:description.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."],"dc:description.degree":["M.Eng."],"dc:identifier.uri":["https://hdl.handle.net/1721.1/139953"],"dc:publisher":["Massachusetts Institute of Technology"],"dc:rights":["In Copyright - Educational Use Permitted","Copyright MIT"],"dc:rights.uri":["http://rightsstatements.org/page/InC-EDU/1.0/"],"dc:title":["Constructing Low Resource Approaches to Improve Speech-to-text Translation from Modern Standard Arabic to English"],"dc:type":["Thesis"],"thesis:degree_name":["Master","Master of Engineering in Electrical Engineering and Computer Science"]},"updated_at":"2026-07-22T22:22:18Z"}