{"584868":{"#nid":"584868","#data":{"type":"event","title":"Ph.D. Proposal Oral Exam - Babafemi Odelowo","body":[{"value":"\u003Cp\u003E\u003Cstrong\u003ETitle:\u0026nbsp; \u003C\/strong\u003E\u003Cem\u003EDevelopment of a Neural Network Based Speech Enhancement Processor\u003C\/em\u003E\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003ECommittee:\u0026nbsp; \u003C\/strong\u003E\u003C\/p\u003E\r\n\r\n\u003Cp\u003EDr. Anderson, Advisor\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003EDr. Moore, Chair\u003C\/p\u003E\r\n\r\n\u003Cp\u003EDr. Clements\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003EAbstract: \u003C\/strong\u003E\u003C\/p\u003E\r\n\r\n\u003Cp\u003EThe objective of the proposed research is to develop an efficient neural network-based speech enhancement processor.\u0026nbsp; Neural networks are powerful models that have in the last few years been applied to several speech processing problems including speech enhancement.\u0026nbsp; There, however, remain several questions such as the most suitable architectures, training features, and best practices for obtaining optimal results.\u0026nbsp; We investigate the use of the extreme learning machine, an algorithm that allows feed-forward networks to be quickly trained and provides good generalization, for speech enhancement.\u0026nbsp; We propose modifications to the extreme learning machine to increase its accuracy.\u0026nbsp; The proposed research also investigates the use of a time domain noise subtraction architecture for enhancing low-SNR signals; the use of artifact-free block processing methods; and the incorporation of perceptual criteria in the design of neural network-based speech enhancement systems.\u003C\/p\u003E\r\n","summary":null,"format":"limited_html"}],"field_subtitle":"","field_summary":"","field_summary_sentence":[{"value":"Development of a Neural Network Based Speech Enhancement Processor"}],"uid":"28475","created_gmt":"2016-12-08 21:20:29","changed_gmt":"2016-12-08 21:20:29","author":"Daniela Staiculescu","boilerplate_text":"","field_publication":"","field_article_url":"","field_event_time":{"event_time_start":"2017-01-04T09:00:00-05:00","event_time_end":"2017-01-04T11:00:00-05:00","event_time_end_last":"2017-01-04T11:00:00-05:00","gmt_time_start":"2017-01-04 14:00:00","gmt_time_end":"2017-01-04 16:00:00","gmt_time_end_last":"2017-01-04 16:00:00","rrule":null,"timezone":"America\/New_York"},"extras":[],"groups":[{"id":"434371","name":"ECE Ph.D. Proposal Oral Exams"}],"categories":[],"keywords":[{"id":"102851","name":"Phd proposal"},{"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":""}}}