DalSpace Institutional Repository
DalSpace is a digital service that collects, preserves, and distributes digital material produced by the Dalhousie community.
- To learn about content guidelines, policies, and how to deposit, view the Help documents.
- Contact us to get started submitting content to DalSpace at dalspace@dal.ca
Communities in DSpace
Select a community to browse its collections.
Recent Submissions
To “Actualize” Users’ Fair Dealing Rights: Guidelines If Necessary But Not Necessarily Guidelines
(2025-04-30) Knopf, Howard
Howard Knopf will examine the Court’s rulings on fair dealing, the statute, and the role of guidelines in Canada’s post-secondary institutions.
Salmon Stories: Social and Cultural Narratives of Salmon Production, Conservation, and Care
(2025-02-28) Berseth, Valerie; Miglani, Sugeet; Chance, Tom; Spidle, Adrian; Harrison, Hannah L.
ABC Copyright 2025 unAGM Notes
(2025-04-29) Chambers Page, Jaclyn
Notes from the 2025 ABC Copyright unAGM, held online April 29, 2025.
Pre-training and self-supervised learning for speech-based mental health assessment
(2025-05-08) Dumpala, Sri Harsha; No; Doctor of Philosophy; Faculty of Computer Science; Not Applicable; Dr. Theodora Chaspari; No; Dr. Rudolf Uher; Dr. Frank Rudzicz; Dr. Sageev Oore
Major depressive disorder (MDD), commonly known as depression, is a leading cause of disability, absenteeism, and premature death. Automatic depression assessment from speech is a vital step towards improving the diagnosis and treatment of this condition. While previous research has explored conventional acoustic features for speech-based depression assessment, these methods have not yet achieved clinical-level performance, highlighting the need for further advancements. A significant challenge is the non-availability of large training datasets required to train deep learning models from scratch for automated depression assessment. To address these issues, this thesis proposes the use of self-supervised learning (SSL) models based on speech to enhance the performance of automatic depression assessment systems. The pre-training objective function of SSL models determines the types of information encoded, such as semantic, speaker, and prosodic features. I first demonstrate that combining SSL models, which capture different aspects of speech—both local and global information—leads to improved performance in detecting depression. Additionally, I show that SSL-based speech embeddings are more effective at identifying specific symptoms of depression than traditional speech features. Furthermore, I compare various SSL pre-trained models to identify which aspects of speech contribute most to the detection of different symptoms. Finally, I extend test-time training (TTT) for depression detection to improve model robustness under naturally occurring covariate (distributional) shifts. This work underscores the potential of SSL techniques in developing more accurate and resilient models for depression assessment, thereby fostering further research into automated mental health evaluation.
Canadian copyright and Canadian sovereignty: rights and relations
(2025-04-29) Bannerman, Sara
Canadian copyright has user rights in its DNA. These rights, and copyright broadly, are tied to a complex web of forces and struggles that have shaped history for people living within Canadian borders and beyond. British imperialism and settler colonialism; tariffs and trade; race, ability and gender relations; struggles for rights and struggles for sovereignty—all have shaped the history of Canadian copyright. This presentation will examine copyright in relation to the broader relations that shape it.