{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/129612"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/129612","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Text recaptioning for audio diffusion models","abstract":"Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2027-05-01","abstract_html":"Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2027-05-01","abstract_has_math":false,"creators":["Matthews, Evan Michael"],"institution":"University of Illinois Urbana-Champaign","degree_name":"M.S.","degree_level":"Thesis","degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":["Smaragdis, Paris"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2025,"date_issued":"2025-05-05","date_published":"2025-05-05","updated_at":"2026-07-22T22:25:05Z","subjects":["diffusion","audio","generative models","generative audio","sound","text recaptioning","recaptioning","text prompts"],"languages":["en","eng"],"rights":["Copyright 2025 Evan M. Matthews"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/2142/129612","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Smaragdis, Paris"]},{"key":"dc:creator","label":"Author","values":["Matthews, Evan Michael"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2025-05-05","2025-05"]},{"key":"dc:type","label":"Dc Type","values":["text","Thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["M.S."]},{"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":["diffusion","audio","generative models","generative audio","sound","text recaptioning","recaptioning","text prompts"]}]},{"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 Evan M. Matthews"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://hdl.handle.net/2142/129612"]}]},{"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 2027-05-01","The student, Evan Matthews, accepted the attached license on 2025-04-29 at 17:07.","The student, Evan Matthews, submitted this Thesis for approval on 2025-04-29 at 17:15.","This Thesis was approved for publication on 2025-05-05 at 10:05.","DSpace SAF Submission Ingestion Package generated from Vireo submission #22099 on 2025-10-19 at 19:16:50","Textual Inversion (TI) is one of the most recent discoveries in generative audio models that allows for prompt recaptioning of a pretrained model’s concept understanding. In this thesis, we explore a rudimentary method and TI for audio sample outputs, specifically focusing on a custom-trained TI model that embeds new concepts into pretrained image models. The TI recaptioned samples are compared with baseline samples, and we find a significant difference in variation between baseline samples. We believe that this comparison will provide a strong foundation and inspiration to future works related to prompt recaptions and analysis on generative audio models."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Text recaptioning for audio diffusion models"]}]}],"canonical_facts":{"dc:contributor":["Smaragdis, Paris"],"dc:creator":["Matthews, Evan Michael"],"dc:date":["2025-05-05","2025-05"],"dc:description":["Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2027-05-01","The student, Evan Matthews, accepted the attached license on 2025-04-29 at 17:07.","The student, Evan Matthews, submitted this Thesis for approval on 2025-04-29 at 17:15.","This Thesis was approved for publication on 2025-05-05 at 10:05.","DSpace SAF Submission Ingestion Package generated from Vireo submission #22099 on 2025-10-19 at 19:16:50","Textual Inversion (TI) is one of the most recent discoveries in generative audio models that allows for prompt recaptioning of a pretrained model’s concept understanding. In this thesis, we explore a rudimentary method and TI for audio sample outputs, specifically focusing on a custom-trained TI model that embeds new concepts into pretrained image models. The TI recaptioned samples are compared with baseline samples, and we find a significant difference in variation between baseline samples. We believe that this comparison will provide a strong foundation and inspiration to future works related to prompt recaptions and analysis on generative audio models."],"dc:format":["application/pdf"],"dc:identifier":["https://hdl.handle.net/2142/129612"],"dc:language":["en","eng"],"dc:rights":["Copyright 2025 Evan M. Matthews"],"dc:subject":["diffusion","audio","generative models","generative audio","sound","text recaptioning","recaptioning","text prompts"],"dc:title":["Text recaptioning for audio diffusion models"],"dc:type":["text","Thesis"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["M.S."],"thesis:institution_name":["University of Illinois Urbana-Champaign"]},"updated_at":"2026-07-22T22:25:05Z"}