{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/121935"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/121935","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Data-efficient approaches for audio classification and separation","abstract":"Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2024-03-01 without embargo terms","abstract_html":"Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2024-03-01 without embargo terms","abstract_has_math":false,"creators":["Wang, Zhepei"],"institution":"University of Illinois at Urbana-Champaign","degree_name":"Ph.D.","degree_level":"Dissertation","degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":["Smaragdis, Paris","Lazebnik, Svetlana","Hasegawa-Johnson, Mark","Kim, Minje"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2023,"date_issued":"2023-12","date_published":"2023-12","updated_at":"2026-07-22T22:25:00Z","subjects":["Deep Learning","Sound Classification","Source Separation","Self-supervised Learning","Semi-supervised Learning","Continual Learning"],"languages":["en","eng"],"rights":["Copyright 2023 Zhepei Wang"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/2142/121935","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Smaragdis, Paris","Lazebnik, Svetlana","Hasegawa-Johnson, Mark","Kim, Minje"]},{"key":"dc:creator","label":"Author","values":["Wang, Zhepei"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2023-12","2023-08-22"]},{"key":"dc:type","label":"Dc Type","values":["text"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"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 at Urbana-Champaign"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Deep Learning","Sound Classification","Source Separation","Self-supervised Learning","Semi-supervised Learning","Continual Learning"]}]},{"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 2023 Zhepei Wang"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://hdl.handle.net/2142/121935"]}]},{"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 2024-03-01 without embargo terms","The student, Zhepei Wang, accepted the attached license on 2023-08-18 at 12:51.","The student, Zhepei Wang, submitted this Dissertation for approval on 2023-08-18 at 13:01.","This Dissertation was approved for publication on 2023-08-22 at 11:17.","DSpace SAF Submission Ingestion Package generated from Vireo submission #19808 on 2024-03-01 at 13:13:14","Recent advances in deep learning for computational audio processing are established upon sufficient annotated audio data. However, obtaining a substantial volume of high-quality annotations from in-the-wild audio remains a significant challenge. In this thesis, we propose and analyze data-efficient approaches for modeling audio signals to perform sound classification and separation. First, we present neural network architectures based on multi-dimensional unrolling of recurrent neural networks that allow the model to perform sound event detection with efficient usage of training data. Equipped with adaptive computation, the model further learns to intelligently adjust the amount of computation and enables processing when only partial information is available. Next, we propose approaches for recognizing sound classes under a time-varying distribution. We investigate continual learning techniques to train a classifier that can efficiently learn new sound classes without forgetting the past using generative replay. We further extend our approach to an unsupervised learning setup, where the model progressively learns representations for an indefinite number of sound classes with few labels presented. Last but not least, we investigate learning with limited annotated data using semi-supervised learning. We demonstrate the effectiveness of the proposed teacher-student framework on tasks including cross-modal audio-text representation learning, singing voice separation, and personalized speech enhancement. To this end, our proposed data-efficient algorithms for audio classification and source separation show high potential for reducing the labor cost for collecting high-quality annotated data, improving computational and storage efficiency, and enabling processing on memory-limited edge devices."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Data-efficient approaches for audio classification and separation"]}]}],"canonical_facts":{"dc:contributor":["Smaragdis, Paris","Lazebnik, Svetlana","Hasegawa-Johnson, Mark","Kim, Minje"],"dc:creator":["Wang, Zhepei"],"dc:date":["2023-12","2023-08-22"],"dc:description":["Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2024-03-01 without embargo terms","The student, Zhepei Wang, accepted the attached license on 2023-08-18 at 12:51.","The student, Zhepei Wang, submitted this Dissertation for approval on 2023-08-18 at 13:01.","This Dissertation was approved for publication on 2023-08-22 at 11:17.","DSpace SAF Submission Ingestion Package generated from Vireo submission #19808 on 2024-03-01 at 13:13:14","Recent advances in deep learning for computational audio processing are established upon sufficient annotated audio data. However, obtaining a substantial volume of high-quality annotations from in-the-wild audio remains a significant challenge. In this thesis, we propose and analyze data-efficient approaches for modeling audio signals to perform sound classification and separation. First, we present neural network architectures based on multi-dimensional unrolling of recurrent neural networks that allow the model to perform sound event detection with efficient usage of training data. Equipped with adaptive computation, the model further learns to intelligently adjust the amount of computation and enables processing when only partial information is available. Next, we propose approaches for recognizing sound classes under a time-varying distribution. We investigate continual learning techniques to train a classifier that can efficiently learn new sound classes without forgetting the past using generative replay. We further extend our approach to an unsupervised learning setup, where the model progressively learns representations for an indefinite number of sound classes with few labels presented. Last but not least, we investigate learning with limited annotated data using semi-supervised learning. We demonstrate the effectiveness of the proposed teacher-student framework on tasks including cross-modal audio-text representation learning, singing voice separation, and personalized speech enhancement. To this end, our proposed data-efficient algorithms for audio classification and source separation show high potential for reducing the labor cost for collecting high-quality annotated data, improving computational and storage efficiency, and enabling processing on memory-limited edge devices."],"dc:format":["application/pdf"],"dc:identifier":["https://hdl.handle.net/2142/121935"],"dc:language":["en","eng"],"dc:rights":["Copyright 2023 Zhepei Wang"],"dc:subject":["Deep Learning","Sound Classification","Source Separation","Self-supervised Learning","Semi-supervised Learning","Continual Learning"],"dc:title":["Data-efficient approaches for audio classification and separation"],"dc:type":["text"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_level":["Dissertation"],"thesis:degree_name":["Ph.D."],"thesis:institution_name":["University of Illinois at Urbana-Champaign"]},"updated_at":"2026-07-22T22:25:00Z"}