{"678251":{"#nid":"678251","#data":{"type":"event","title":"Ph.D. Dissertation Defense - Hu Hu","body":[{"value":"\u003Cp\u003E\u003Cstrong\u003ETitle\u003C\/strong\u003E\u003Cem\u003E:\u0026nbsp; Bayesian Adaptive Learning of Deep Latent Variables for Acoustic Knowledge Transfer\u003C\/em\u003E\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003ECommittee:\u003C\/strong\u003E\u003C\/p\u003E\u003Cp\u003EDr.\u0026nbsp;Chin-Hui Lee, ECE, Chair, Advisor\u003C\/p\u003E\u003Cp\u003EDr.\u0026nbsp;David Anderson, ECE\u003C\/p\u003E\u003Cp\u003EDr.\u0026nbsp;Larry Heck, ECE\u003C\/p\u003E\u003Cp\u003EDr.\u0026nbsp;Elliot Moore, ECE\u003C\/p\u003E\u003Cp\u003EDr.\u0026nbsp;Sabato Marco Siniscalchi, U of Palermo\u003C\/p\u003E","summary":"","format":"limited_html"}],"field_subtitle":"","field_summary":[{"value":"\u003Cp\u003EThis dissertation proposes a Bayesian adaptive learning framework that focuses on estimating a manageable number of latent variables. We explore both variational Bayesian (VB) and maximum a posteriori (MAP) estimation techniques within this framework. Experimental results on acoustic scene classification and spoken command recognition tasks demonstrate that our approach outperforms other knowledge transfer methods.\u003C\/p\u003E","format":"limited_html"}],"field_summary_sentence":[{"value":"Bayesian Adaptive Learning of Deep Latent Variables for Acoustic Knowledge Transfer "}],"uid":"28475","created_gmt":"2024-11-07 14:40:59","changed_gmt":"2024-11-07 14:42:10","author":"Daniela Staiculescu","boilerplate_text":"","field_publication":"","field_article_url":"","field_event_time":{"event_time_start":"2024-11-08T09:00:00-05:00","event_time_end":"2024-11-08T11:00:00-05:00","event_time_end_last":"2024-11-08T11:00:00-05:00","gmt_time_start":"2024-11-08 14:00:00","gmt_time_end":"2024-11-08 16:00:00","gmt_time_end_last":"2024-11-08 16:00:00","rrule":null,"timezone":"America\/New_York"},"location":"Room 5126, Centergy ","extras":[],"groups":[{"id":"434381","name":"ECE Ph.D. Dissertation Defenses"}],"categories":[],"keywords":[{"id":"100811","name":"Phd Defense"},{"id":"1808","name":"graduate students"}],"core_research_areas":[],"news_room_topics":[],"event_categories":[{"id":"1788","name":"Other\/Miscellaneous"}],"invited_audience":[{"id":"78771","name":"Public"}],"affiliations":[],"classification":[],"areas_of_expertise":[],"news_and_recent_appearances":[],"phone":[],"contact":[],"email":[],"slides":[],"orientation":[],"userdata":""}}}