2026-09-20T10:23:35Zhttps://dspace.mit.edu/server/oai/request

oai:dspace.mit.edu:1721.1/1197332026-06-06T00:55:55Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023

James Glass and Hao Tang. McEachern, Matthew Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science. Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science 2018-12-18T19:47:43Z 2018-12-18T19:47:43Z 2018 2018 http://hdl.handle.net/1721.1/119733 1078688644 Thesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2018. This electronic version was submitted by the student author. The certified thesis is available in the Institute Archives and Special Collections. Cataloged from student-submitted PDF version of thesis. Includes bibliographical references (pages 87-90). The task of producing a Voice Activity Detector (VAD) that is robust in the presence of non-stationary background noise has been an active area of research for several decades. Historically, many of the proposed VAD models have been highly heuristic in nature. More recently, however, statistical models, including Deep Neural Networks (DNNs) have been explored. In this thesis, I explore the use of a lightweight, deep, recurrent neural architecture for VAD. I also explore a variant that is fully end-to-end, learning features directly from raw waveform data. In obtaining data for these models, I introduce a data augmentation methodology that allows for the artificial generation of large amounts of noisy speech data from a clean speech source. I describe how these neural models, once trained, can be deployed in a live environment with a real-time audio stream. I find that while these models perform well in their closed-domain testing environment, the live deployment scenario presents challenges related to generalizability. by Matthew McEachern. M.Eng. 90 pages eng Massachusetts Institute of Technology MIT theses are protected by copyright. They may be viewed, downloaded, or printed from this source but further reproduction or distribution in any format is prohibited without written permission. http://dspace.mit.edu/handle/1721.1/7582 Electrical Engineering and Computer Science. Neural Voice Activity Detection and its practical use Neural VAD and its practical use Thesis application/pdf false Publication unknown unknown <Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="d3e19e51-90bb-4cd0-acf8-9be6c8970987"> <Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843</Type> <Language>eng</Language> <Title>Neural Voice Activity Detection and its practical use</Title> <Subtitle>Neural VAD and its practical use</Subtitle> <PublishedIn> <Publication> </Publication> </PublishedIn> <PublicationDate>2018</PublicationDate> <Authors> <Author> <DisplayName>McEachern, Matthew</DisplayName> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> </Authors> <Editors> </Editors> <Publishers> <Publisher> <DisplayName>Massachusetts Institute of Technology</DisplayName> <OrgUnit /> </Publisher> </Publishers> <License>http://dspace.mit.edu/handle/1721.1/7582</License> <Keyword>Electrical Engineering and Computer Science.</Keyword> <Abstract>The task of producing a Voice Activity Detector (VAD) that is robust in the presence of non-stationary background noise has been an active area of research for several decades. Historically, many of the proposed VAD models have been highly heuristic in nature. More recently, however, statistical models, including Deep Neural Networks (DNNs) have been explored. In this thesis, I explore the use of a lightweight, deep, recurrent neural architecture for VAD. I also explore a variant that is fully end-to-end, learning features directly from raw waveform data. In obtaining data for these models, I introduce a data augmentation methodology that allows for the artificial generation of large amounts of noisy speech data from a clean speech source. I describe how these neural models, once trained, can be deployed in a live environment with a real-time audio stream. I find that while these models perform well in their closed-domain testing environment, the live deployment scenario presents challenges related to generalizability.</Abstract> <Access xmlns="http://purl.org/coar/access_right" > </Access> </Publication>