{"id":{"repo_id":"uwo","oai_identifier":"oai:uwo.scholaris.ca:20.500.14721/31151"},"canonical_url":"https://search.dev.ndltd.org/etd/uwo/oai:uwo.scholaris.ca:20.500.14721/31151","repository":{"repo_id":"uwo","name":"Western University","base_url":"https://uwo.scholaris.ca/server/oai/request"},"display":{"title":"Contrastive Learning of Auditory Representations","abstract":"Learning rich visual representations using contrastive self-supervised learning has been extremely successful. However, it is still a major question whether we could use a similar approach to learn more efficient auditory and audio-visual representations. In this thesis, we expand on prior self-supervised methods to learn better auditory and audio-visual representations. We introduce various data augmentations suitable for auditory and audio-visual data and evaluate their impact on predictive performance, and demonstrate that training with both supervised and contrastive losses simultaneously improves the learned representations compared to self-supervised pre-training followed by supervised fine-tuning. We illustrate that by combining all these methods and with substantially less labeled data, our framework achieves significant improvement on prediction performance compared to the supervised approach. Moreover, compared to the self-supervised approach, our framework converges faster with significantly better representations.","abstract_html":"Learning rich visual representations using contrastive self-supervised learning has been extremely successful. However, it is still a major question whether we could use a similar approach to learn more efficient auditory and audio-visual representations. In this thesis, we expand on prior self-supervised methods to learn better auditory and audio-visual representations. We introduce various data augmentations suitable for auditory and audio-visual data and evaluate their impact on predictive performance, and demonstrate that training with both supervised and contrastive losses simultaneously improves the learned representations compared to self-supervised pre-training followed by supervised fine-tuning. We illustrate that by combining all these methods and with substantially less labeled data, our framework achieves significant improvement on prediction performance compared to the supervised approach. Moreover, compared to the self-supervised approach, our framework converges faster with significantly better representations.","abstract_has_math":false,"creators":["Al-Tahan, Haider"],"institution":"The University of Western Ontario","degree_name":"M Sc","degree_level":null,"degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":[],"advisors":["Mohsenzadeh, Yalda"],"committee_chairs":[],"committee_members":[],"year":2021,"date_issued":"2021-05-06","date_published":"2021-05-06","updated_at":"2026-07-27T21:55:56Z","subjects":["Self-supervised Learning","Contrastive Learning","Supervised Learning"],"languages":["en_ca"],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/20.500.14721/31151","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Mohsenzadeh, Yalda"]},{"key":"dc:creator","label":"Author","values":["Al-Tahan, Haider"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2025-07-10T18:51:56Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2025-07-10T18:51:56Z"]},{"key":"dc:date.issued","label":"Date","values":["2021-05-06"]},{"key":"dc:publisher","label":"Institution","values":["The University of Western Ontario"]},{"key":"dc:type","label":"Dc Type","values":["thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"key":"thesis:degree_name","label":"Degree Name","values":["M Sc"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Self-supervised Learning","Contrastive Learning","Supervised Learning"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["en_ca"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/20.500.14721/31151"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Collaborative Specialization: Artificial Intelligence","The thesis cover page in the PDF document includes references to Western University’s previous institutional repository platform, known as Scholarship@Western, and links to that platform (beginning with ir.lib.uwo.ca). In citing or referring to this thesis, use the DOI or handle from this page instead. Sample citation: Author name, \"Thesis title.\" (Year). Western University Open Repository. https://doi.org/10.71858/123456."]},{"key":"dc:description.abstract","label":"Abstract","values":["Learning rich visual representations using contrastive self-supervised learning has been extremely successful. However, it is still a major question whether we could use a similar approach to learn more efficient auditory and audio-visual representations. In this thesis, we expand on prior self-supervised methods to learn better auditory and audio-visual representations. We introduce various data augmentations suitable for auditory and audio-visual data and evaluate their impact on predictive performance, and demonstrate that training with both supervised and contrastive losses simultaneously improves the learned representations compared to self-supervised pre-training followed by supervised fine-tuning. We illustrate that by combining all these methods and with substantially less labeled data, our framework achieves significant improvement on prediction performance compared to the supervised approach. Moreover, compared to the self-supervised approach, our framework converges faster with significantly better representations."]},{"key":"dc:title","label":"Title","values":["Contrastive Learning of Auditory Representations"]}]}],"canonical_facts":{"dc:contributor.advisor":["Mohsenzadeh, Yalda"],"dc:creator":["Al-Tahan, Haider"],"dc:date.accessioned":["2025-07-10T18:51:56Z"],"dc:date.available":["2025-07-10T18:51:56Z"],"dc:date.issued":["2021-05-06"],"dc:description":["Collaborative Specialization: Artificial Intelligence","The thesis cover page in the PDF document includes references to Western University’s previous institutional repository platform, known as Scholarship@Western, and links to that platform (beginning with ir.lib.uwo.ca). In citing or referring to this thesis, use the DOI or handle from this page instead. Sample citation: Author name, \"Thesis title.\" (Year). Western University Open Repository. https://doi.org/10.71858/123456."],"dc:description.abstract":["Learning rich visual representations using contrastive self-supervised learning has been extremely successful. However, it is still a major question whether we could use a similar approach to learn more efficient auditory and audio-visual representations. In this thesis, we expand on prior self-supervised methods to learn better auditory and audio-visual representations. We introduce various data augmentations suitable for auditory and audio-visual data and evaluate their impact on predictive performance, and demonstrate that training with both supervised and contrastive losses simultaneously improves the learned representations compared to self-supervised pre-training followed by supervised fine-tuning. We illustrate that by combining all these methods and with substantially less labeled data, our framework achieves significant improvement on prediction performance compared to the supervised approach. Moreover, compared to the self-supervised approach, our framework converges faster with significantly better representations."],"dc:identifier.uri":["https://hdl.handle.net/20.500.14721/31151"],"dc:language.iso":["en_ca"],"dc:publisher":["The University of Western Ontario"],"dc:subject":["Self-supervised Learning","Contrastive Learning","Supervised Learning"],"dc:title":["Contrastive Learning of Auditory Representations"],"dc:type":["thesis"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_name":["M Sc"]},"updated_at":"2026-07-27T21:55:56Z"}