DEEP NEURAL NETWORK FOR DEREVERBERATION

Simple item page
dc.contributor.advisorDuraiswami, Ramanien_US
dc.contributor.authorJiao, Yangen_US
dc.contributor.departmentElectrical Engineeringen_US
dc.contributor.publisherDigital Repository at the University of Marylanden_US
dc.contributor.publisherUniversity of Maryland (College Park, Md.)en_US
dc.date.accessioned2020-02-06T06:35:09Z
dc.date.available2020-02-06T06:35:09Z
dc.date.issued2019en_US
dc.description.abstractRecently, deep neural networks have achieved incredible success in the area of computer vision and natural language processing. The research topics under the umbrella of speech enhancement have embraced this chance to revolutionize. Dereverberation as one such topics has gained less popularity compared to other tasks of speech enhancement such as cocktail party problem, speech enhancement in open area. Our aim is to extend method of deep learning into the domain of dereverberation. We leverage a successful neural network method on a similar task of speech enhancement to dereverberation, specifically, time frequency mask supported GEV beamformer. This data driven approach introduces feature transferrable to related tasks compared to hand-engineered methods. Our experiments illustrate that the original framework arise from open area enhancement tasks is proved to be effective in our closure space tasks.en_US
dc.identifierhttps://doi.org/10.13016/gbro-muhw
dc.identifier.urihttp://hdl.handle.net/1903/25533
dc.language.isoenen_US
dc.subject.pqcontrolledEngineeringen_US
dc.titleDEEP NEURAL NETWORK FOR DEREVERBERATIONen_US
dc.typeThesisen_US

Files

Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
Jiao_umd_0117N_20540.pdf
Size:
2.09 MB
Format:
Adobe Portable Document Format
Download
(RESTRICTED ACCESS)

Collections

UMD Theses and Dissertations
Electrical & Computer Engineering Theses and Dissertations