{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/129827"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/129827","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Implicit neural representations for time-frequency signal processing","abstract":"Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2025-10-20 without embargo terms","abstract_html":"Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2025-10-20 without embargo terms","abstract_has_math":false,"creators":["Subramani, Krishna"],"institution":"University of Illinois Urbana-Champaign","degree_name":"Ph.D.","degree_level":"Dissertation","degree_discipline":"Electrical & Computer Engr","degree_department":null,"school":null,"contributors":["Smaragdis, Paris","Kim, Minje","Hasegawa-Johnson, Mark","Choudhury, Romit Roy"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2025,"date_issued":"2025-06-24","date_published":"2025-06-24","updated_at":"2026-07-22T22:25:05Z","subjects":["Time-frequency Representations","Point Clouds","Implicit Neural Representations","Multichannel Filtering","Machine Learning","Signal Processing"],"languages":["en","eng"],"rights":["Copyright 2025 Krishna Subramani"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/2142/129827","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Smaragdis, Paris","Kim, Minje","Hasegawa-Johnson, Mark","Choudhury, Romit Roy"]},{"key":"dc:creator","label":"Author","values":["Subramani, Krishna"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2025-06-24","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":["Time-frequency Representations","Point Clouds","Implicit Neural Representations","Multichannel Filtering","Machine Learning","Signal Processing"]}]},{"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 Krishna Subramani"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://hdl.handle.net/2142/129827"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2025-10-20 without embargo terms","The student, Krishna Subramani, accepted the attached license on 2025-06-23 at 09:27.","The student, Krishna Subramani, submitted this Dissertation for approval on 2025-06-23 at 11:57.","This Dissertation was approved for publication on 2025-06-24 at 11:29.","DSpace SAF Submission Ingestion Package generated from Vireo submission #22348 on 2025-10-20 at 16:57:13","This dissertation presents a departure from conventional audio signal processing approaches that rely on fixed-dimensional vector representations and regularly sampled time-frequency grids. We introduce a flexible framework that models audio time-frequency representations using continuous, adaptive structures, enabling greater robustness and efficiency in modern applications. First, we propose a differentiable proxy for automatically optimizing Short-Time Fourier Transform parameters, aligning time-frequency resolution with task-specific objectives. We then reformulate time-frequency representations as Point Clouds, allowing for resolution-invariant processing and effective subsampling without sacrificing performance. Building on this foundation, we employ Implicit Neural Representations to model vectors and filters as continuous functions, thereby decoupling classical algorithms like multichannel filtering and matrix factorization from fixed parameters and sampling constraints. These contributions collectively propose a unified, parameter-agnostic view of signal processing that seamlessly integrates traditional methods with modern learning-based paradigms."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Implicit neural representations for time-frequency signal processing"]}]}],"canonical_facts":{"dc:contributor":["Smaragdis, Paris","Kim, Minje","Hasegawa-Johnson, Mark","Choudhury, Romit Roy"],"dc:creator":["Subramani, Krishna"],"dc:date":["2025-06-24","2025-08"],"dc:description":["Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2025-10-20 without embargo terms","The student, Krishna Subramani, accepted the attached license on 2025-06-23 at 09:27.","The student, Krishna Subramani, submitted this Dissertation for approval on 2025-06-23 at 11:57.","This Dissertation was approved for publication on 2025-06-24 at 11:29.","DSpace SAF Submission Ingestion Package generated from Vireo submission #22348 on 2025-10-20 at 16:57:13","This dissertation presents a departure from conventional audio signal processing approaches that rely on fixed-dimensional vector representations and regularly sampled time-frequency grids. We introduce a flexible framework that models audio time-frequency representations using continuous, adaptive structures, enabling greater robustness and efficiency in modern applications. First, we propose a differentiable proxy for automatically optimizing Short-Time Fourier Transform parameters, aligning time-frequency resolution with task-specific objectives. We then reformulate time-frequency representations as Point Clouds, allowing for resolution-invariant processing and effective subsampling without sacrificing performance. Building on this foundation, we employ Implicit Neural Representations to model vectors and filters as continuous functions, thereby decoupling classical algorithms like multichannel filtering and matrix factorization from fixed parameters and sampling constraints. These contributions collectively propose a unified, parameter-agnostic view of signal processing that seamlessly integrates traditional methods with modern learning-based paradigms."],"dc:format":["application/pdf"],"dc:identifier":["https://hdl.handle.net/2142/129827"],"dc:language":["en","eng"],"dc:rights":["Copyright 2025 Krishna Subramani"],"dc:subject":["Time-frequency Representations","Point Clouds","Implicit Neural Representations","Multichannel Filtering","Machine Learning","Signal Processing"],"dc:title":["Implicit neural representations for time-frequency signal 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":"2026-07-22T22:25:05Z"}