{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/130021"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/130021","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Direct exposure of linguistic principles in model architectures for downstream processing","abstract":"Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2027-08-01","abstract_html":"Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2027-08-01","abstract_has_math":false,"creators":["Morshed, Mahir Abrar"],"institution":"University of Illinois Urbana-Champaign","degree_name":"Ph.D.","degree_level":"Dissertation","degree_discipline":"Electrical & Computer Engr","degree_department":null,"school":null,"contributors":["Hasegawa-Johnson, Mark A.","Hasegawa-Johnson, Mark A","Smaragdis, Paris","Tang, Yan","Singer, Andrew C","Varshney, Lav R."],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2025,"date_issued":"2025-07-17","date_published":"2025-07-17","updated_at":"2026-07-22T22:25:06Z","subjects":["Low-resource Speech Recognition","Articulatory Feature Detection","Over-regularized Speech","Structured Text Generation"],"languages":["en","eng"],"rights":["Copyright 2025 Mahir Morshed"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/2142/130021","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Hasegawa-Johnson, Mark A.","Hasegawa-Johnson, Mark A","Smaragdis, Paris","Tang, Yan","Singer, Andrew C","Varshney, Lav R."]},{"key":"dc:creator","label":"Author","values":["Morshed, Mahir Abrar"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2025-07-17","2025-08"]},{"key":"dc:type","label":"Dc Type","values":["text"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Electrical & Computer Engr"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Dissertation"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Ph.D."]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Illinois Urbana-Champaign"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Low-resource Speech Recognition","Articulatory Feature Detection","Over-regularized Speech","Structured Text Generation"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en","eng"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright 2025 Mahir Morshed"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://hdl.handle.net/2142/130021"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2027-08-01","The student, Mahir Morshed, accepted the attached license on 2025-07-07 at 10:14.","The student, Mahir Morshed, submitted this Dissertation for approval on 2025-07-07 at 10:21.","This Dissertation was approved for publication on 2025-07-17 at 15:17.","DSpace SAF Submission Ingestion Package generated from Vireo submission #22405 on 2025-10-21 at 10:05:38","Extensive work on models processing text and speech has led to massively multilingual tools targeting often lower-resourced languages. Examining those tools’ architectures, however, has often revealed little use of specific linguistic principles in a directly explainable fashion, whether in model setup, training, or evaluation. This work seeks to further the inclusion of linguistic information within the structure of systems that process language, whether for text generation or speech recognition. Systems demonstrating differing levels of system restructuring to expose such information include, at one end, a novel text generation system using discrete semantic and syntactic units, built on an open knowledge base and community contributions of code and data. A foundation speech recognizer fine-tuned using morphemic units to handle over-regularized children’s speech serves as the other end of the restructuring spectrum. Following these are improvements to multilingual phone recognition systems through the use and transfer of articulatory information, as a means of imparting some explainability to those systems. Reductions in phone error rates have originated in diversified training corpora to improve language and phone coverage, the introduction of self-supervised waveform input processing, and adjustments to universal phone and feature sets for consistency and brevity. Such efforts highlight the importance of introducing explicit linguistic decompositions, whether phonological, morphological, or syntactic, to models that process language, and the need for continual improvements to sources providing those decompositions."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Direct exposure of linguistic principles in model architectures for downstream processing"]}]}],"canonical_facts":{"dc:contributor":["Hasegawa-Johnson, Mark A.","Hasegawa-Johnson, Mark A","Smaragdis, Paris","Tang, Yan","Singer, Andrew C","Varshney, Lav R."],"dc:creator":["Morshed, Mahir Abrar"],"dc:date":["2025-07-17","2025-08"],"dc:description":["Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2027-08-01","The student, Mahir Morshed, accepted the attached license on 2025-07-07 at 10:14.","The student, Mahir Morshed, submitted this Dissertation for approval on 2025-07-07 at 10:21.","This Dissertation was approved for publication on 2025-07-17 at 15:17.","DSpace SAF Submission Ingestion Package generated from Vireo submission #22405 on 2025-10-21 at 10:05:38","Extensive work on models processing text and speech has led to massively multilingual tools targeting often lower-resourced languages. Examining those tools’ architectures, however, has often revealed little use of specific linguistic principles in a directly explainable fashion, whether in model setup, training, or evaluation. This work seeks to further the inclusion of linguistic information within the structure of systems that process language, whether for text generation or speech recognition. Systems demonstrating differing levels of system restructuring to expose such information include, at one end, a novel text generation system using discrete semantic and syntactic units, built on an open knowledge base and community contributions of code and data. A foundation speech recognizer fine-tuned using morphemic units to handle over-regularized children’s speech serves as the other end of the restructuring spectrum. Following these are improvements to multilingual phone recognition systems through the use and transfer of articulatory information, as a means of imparting some explainability to those systems. Reductions in phone error rates have originated in diversified training corpora to improve language and phone coverage, the introduction of self-supervised waveform input processing, and adjustments to universal phone and feature sets for consistency and brevity. Such efforts highlight the importance of introducing explicit linguistic decompositions, whether phonological, morphological, or syntactic, to models that process language, and the need for continual improvements to sources providing those decompositions."],"dc:format":["application/pdf"],"dc:identifier":["https://hdl.handle.net/2142/130021"],"dc:language":["en","eng"],"dc:rights":["Copyright 2025 Mahir Morshed"],"dc:subject":["Low-resource Speech Recognition","Articulatory Feature Detection","Over-regularized Speech","Structured Text Generation"],"dc:title":["Direct exposure of linguistic principles in model architectures for downstream processing"],"dc:type":["text"],"thesis:degree_discipline":["Electrical & Computer Engr"],"thesis:degree_level":["Dissertation"],"thesis:degree_name":["Ph.D."],"thesis:institution_name":["University of Illinois Urbana-Champaign"]},"updated_at":"2026-07-22T22:25:06Z"}