{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/125528"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/125528","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Understanding modern deep learning techniques for audio applications and beyond","abstract":"Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2025-02-04 without embargo terms","abstract_html":"Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2025-02-04 without embargo terms","abstract_has_math":false,"creators":["Phan, Duc Huy"],"institution":"University of Illinois at Urbana-Champaign","degree_name":"Ph.D.","degree_level":"Dissertation","degree_discipline":"Electrical & Computer Engr","degree_department":null,"school":null,"contributors":["Jones, Douglas L","Choudhury, Romit Roy","Smaragdis, Paris","Do, Minh N"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2024,"date_issued":"2024-07-12","date_published":"2024-07-12","updated_at":"2026-07-22T22:25:02Z","subjects":["Machine Learning Training","Training By Pairing Samples","Audio Classification And Detection","Deep Relu Network"],"languages":["en","eng"],"rights":["Copyright 2024 Duc Huy Phan"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/2142/125528","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Jones, Douglas L","Choudhury, Romit Roy","Smaragdis, Paris","Do, Minh N"]},{"key":"dc:creator","label":"Author","values":["Phan, Duc Huy"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2024-07-12","2024-08"]},{"key":"dc:type","label":"Dc Type","values":["text","Thesis"]},{"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 at Urbana-Champaign"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Machine Learning Training","Training By Pairing Samples","Audio Classification And Detection","Deep Relu Network"]}]},{"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 2024 Duc Huy Phan"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://hdl.handle.net/2142/125528"]}]},{"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 2025-02-04 without embargo terms","The student, Duc Phan, accepted the attached license on 2024-06-27 at 09:42.","The student, Duc Phan, submitted this Dissertation for approval on 2024-06-27 at 09:58.","This Dissertation was approved for publication on 2024-07-12 at 06:15.","DSpace SAF Submission Ingestion Package generated from Vireo submission #20854 on 2025-02-04 at 21:03:46","Deep neural networks (DNN) have been widely applied in different application domains. The DNN was first studied intensively in vision applications before adapting it to other fields. To migrate DNN solutions from the vision domain to another application domain, a neural network solution may be influenced by new structures or improved training processes. This thesis introduces several enhancements of the DNN in both model architectures and training processes for acoustic classification and detection applications. First, in acoustic scene classification applications, the introduction of time- frequency separable convolutions reduces the model size 8 to 10 times without loss of performance. In addition, our experiments with an alternate DNN architecture which is a predictor feed forward network for anomaly detection in machine audio data show 5% to 20% improvement in Area Under the Curve (AUC). Finally, for training process modification, we propose a pairing technique that simultaneously optimizes the performance of the models on pairs of training samples during the training process. A pair includes an original training example and a corresponding modified version. Our pairing techniques adapt the similarity part of the constrastive loss as an additional regularization term for the loss function of a given machine learning task. The pairing techniques show at least 1% improvement in network accuracy on top of mix-up augmentation for the CIFAR10 dataset and 2% increase in accuracy for DCASE 2020 Task 1A data. We show that the proposed training by pairs provides parameter regularization for ReLU deep networks. As a result, the technique can potentially apply to many other machine learning applications."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Understanding modern deep learning techniques for audio applications and beyond"]}]}],"canonical_facts":{"dc:contributor":["Jones, Douglas L","Choudhury, Romit Roy","Smaragdis, Paris","Do, Minh N"],"dc:creator":["Phan, Duc Huy"],"dc:date":["2024-07-12","2024-08"],"dc:description":["Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2025-02-04 without embargo terms","The student, Duc Phan, accepted the attached license on 2024-06-27 at 09:42.","The student, Duc Phan, submitted this Dissertation for approval on 2024-06-27 at 09:58.","This Dissertation was approved for publication on 2024-07-12 at 06:15.","DSpace SAF Submission Ingestion Package generated from Vireo submission #20854 on 2025-02-04 at 21:03:46","Deep neural networks (DNN) have been widely applied in different application domains. The DNN was first studied intensively in vision applications before adapting it to other fields. To migrate DNN solutions from the vision domain to another application domain, a neural network solution may be influenced by new structures or improved training processes. This thesis introduces several enhancements of the DNN in both model architectures and training processes for acoustic classification and detection applications. First, in acoustic scene classification applications, the introduction of time- frequency separable convolutions reduces the model size 8 to 10 times without loss of performance. In addition, our experiments with an alternate DNN architecture which is a predictor feed forward network for anomaly detection in machine audio data show 5% to 20% improvement in Area Under the Curve (AUC). Finally, for training process modification, we propose a pairing technique that simultaneously optimizes the performance of the models on pairs of training samples during the training process. A pair includes an original training example and a corresponding modified version. Our pairing techniques adapt the similarity part of the constrastive loss as an additional regularization term for the loss function of a given machine learning task. The pairing techniques show at least 1% improvement in network accuracy on top of mix-up augmentation for the CIFAR10 dataset and 2% increase in accuracy for DCASE 2020 Task 1A data. We show that the proposed training by pairs provides parameter regularization for ReLU deep networks. As a result, the technique can potentially apply to many other machine learning applications."],"dc:format":["application/pdf"],"dc:identifier":["https://hdl.handle.net/2142/125528"],"dc:language":["en","eng"],"dc:rights":["Copyright 2024 Duc Huy Phan"],"dc:subject":["Machine Learning Training","Training By Pairing Samples","Audio Classification And Detection","Deep Relu Network"],"dc:title":["Understanding modern deep learning techniques for audio applications and beyond"],"dc:type":["text","Thesis"],"thesis:degree_discipline":["Electrical & Computer Engr"],"thesis:degree_level":["Dissertation"],"thesis:degree_name":["Ph.D."],"thesis:institution_name":["University of Illinois at Urbana-Champaign"]},"updated_at":"2026-07-22T22:25:02Z"}