{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/88986"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/88986","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Speech denoising using nonnegative matrix factorization and neural networks","abstract":"The main goal of this research is to do source separation of single-channel mixed signals such that we get a clean representation of each source. In our case, we are concerned specifically with separating speech of a speaker from background noise as another source. So we deal with single-channel mixtures of speech with stationary, semi-stationary and non-stationary noise types. This is what we define as speech denoising. Our goal is to build a system to which we input a noisy speech signal and get the clean speech out with as little distortion or artifacts as possible. The model requires no prior information about the speaker or the background noise. The separation is done in real-time as we can feed the input signal on a frame-by-frame basis. This model can be used in speech recognition systems to improve recognition accuracy in noisy environments. Two methods were mainly adopted for this purpose, nonnegative matrix factorization (NMF) and neural networks. Experiments were conducted to compare the performance of these two methods for speech denoising. For each of these methods, we compared the performance of the case where we had prior information of both the speaker and noise to having just a general speech dictionary. Also, some experiments were conducted to compare the different architectures and parameters in each of these approaches.","abstract_html":"The main goal of this research is to do source separation of single-channel mixed signals such that we get a clean representation of each source. In our case, we are concerned specifically with separating speech of a speaker from background noise as another source. So we deal with single-channel mixtures of speech with stationary, semi-stationary and non-stationary noise types. This is what we define as speech denoising. Our goal is to build a system to which we input a noisy speech signal and get the clean speech out with as little distortion or artifacts as possible. The model requires no prior information about the speaker or the background noise. The separation is done in real-time as we can feed the input signal on a frame-by-frame basis. This model can be used in speech recognition systems to improve recognition accuracy in noisy environments. Two methods were mainly adopted for this purpose, nonnegative matrix factorization (NMF) and neural networks. Experiments were conducted to compare the performance of these two methods for speech denoising. For each of these methods, we compared the performance of the case where we had prior information of both the speaker and noise to having just a general speech dictionary. Also, some experiments were conducted to compare the different architectures and parameters in each of these approaches.","abstract_has_math":false,"creators":["Maddali, Vinay"],"institution":"University of Illinois at Urbana-Champaign","degree_name":"M.S.","degree_level":"Thesis","degree_discipline":"Electrical & Computer Engineering","degree_department":null,"school":null,"contributors":["Smaragdis, Paris"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2016,"date_issued":"2016-03-02T19:33:37Z","date_published":"2016-03-02T19:33:37Z","updated_at":"2026-07-22T22:26:32Z","subjects":["Nonnegative matrix factorization","neural networks","speech denoising","source separation"],"languages":["en"],"rights":["Copyright 2015 Vinay Maddali"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/2142/88986","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Smaragdis, Paris"]},{"key":"dc:creator","label":"Author","values":["Maddali, Vinay"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2016-03-02T19:33:37Z","2015-11-12","2015-12"]},{"key":"dc:type","label":"Dc Type","values":["text"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Electrical & Computer Engineering"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["M.S."]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Illinois at Urbana-Champaign"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Nonnegative matrix factorization","neural networks","speech denoising","source separation"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright 2015 Vinay Maddali"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/2142/88986"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["The main goal of this research is to do source separation of single-channel mixed signals such that we get a clean representation of each source. In our case, we are concerned specifically with separating speech of a speaker from background noise as another source. So we deal with single-channel mixtures of speech with stationary, semi-stationary and non-stationary noise types. This is what we define as speech denoising. Our goal is to build a system to which we input a noisy speech signal and get the clean speech out with as little distortion or artifacts as possible. The model requires no prior information about the speaker or the background noise. The separation is done in real-time as we can feed the input signal on a frame-by-frame basis. This model can be used in speech recognition systems to improve recognition accuracy in noisy environments. Two methods were mainly adopted for this purpose, nonnegative matrix factorization (NMF) and neural networks. Experiments were conducted to compare the performance of these two methods for speech denoising. For each of these methods, we compared the performance of the case where we had prior information of both the speaker and noise to having just a general speech dictionary. Also, some experiments were conducted to compare the different architectures and parameters in each of these approaches.","Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2016-03-02 without embargo terms","The student, Vinay Maddali, accepted the attached license on 2015-11-10 at 21:59.","The student, Vinay Maddali, submitted this Thesis for approval on 2015-11-10 at 22:13.","This Thesis was approved for publication on 2015-11-12 at 14:32.","DSpace SAF Submission Ingestion Package generated from Vireo submission #8774 on 2016-03-02 at 12:50:01","Made available in DSpace on 2016-03-02T19:33:37Z (GMT). No. of bitstreams: 2 MADDALI-THESIS-2015.pdf: 2439585 bytes, checksum: ab05fcfe294f3ec1e3fd5d3d2c032b74 (MD5) LICENSE.txt: 4210 bytes, checksum: 4d3d8cb19c0c426f315c78836ab940b5 (MD5) Previous issue date: 2015-11-12"]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Speech denoising using nonnegative matrix factorization and neural networks"]}]}],"canonical_facts":{"dc:contributor":["Smaragdis, Paris"],"dc:creator":["Maddali, Vinay"],"dc:date":["2016-03-02T19:33:37Z","2015-11-12","2015-12"],"dc:description":["The main goal of this research is to do source separation of single-channel mixed signals such that we get a clean representation of each source. In our case, we are concerned specifically with separating speech of a speaker from background noise as another source. So we deal with single-channel mixtures of speech with stationary, semi-stationary and non-stationary noise types. This is what we define as speech denoising. Our goal is to build a system to which we input a noisy speech signal and get the clean speech out with as little distortion or artifacts as possible. The model requires no prior information about the speaker or the background noise. The separation is done in real-time as we can feed the input signal on a frame-by-frame basis. This model can be used in speech recognition systems to improve recognition accuracy in noisy environments. Two methods were mainly adopted for this purpose, nonnegative matrix factorization (NMF) and neural networks. Experiments were conducted to compare the performance of these two methods for speech denoising. For each of these methods, we compared the performance of the case where we had prior information of both the speaker and noise to having just a general speech dictionary. Also, some experiments were conducted to compare the different architectures and parameters in each of these approaches.","Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2016-03-02 without embargo terms","The student, Vinay Maddali, accepted the attached license on 2015-11-10 at 21:59.","The student, Vinay Maddali, submitted this Thesis for approval on 2015-11-10 at 22:13.","This Thesis was approved for publication on 2015-11-12 at 14:32.","DSpace SAF Submission Ingestion Package generated from Vireo submission #8774 on 2016-03-02 at 12:50:01","Made available in DSpace on 2016-03-02T19:33:37Z (GMT). No. of bitstreams: 2 MADDALI-THESIS-2015.pdf: 2439585 bytes, checksum: ab05fcfe294f3ec1e3fd5d3d2c032b74 (MD5) LICENSE.txt: 4210 bytes, checksum: 4d3d8cb19c0c426f315c78836ab940b5 (MD5) Previous issue date: 2015-11-12"],"dc:format":["application/pdf"],"dc:identifier":["http://hdl.handle.net/2142/88986"],"dc:language":["en"],"dc:rights":["Copyright 2015 Vinay Maddali"],"dc:subject":["Nonnegative matrix factorization","neural networks","speech denoising","source separation"],"dc:title":["Speech denoising using nonnegative matrix factorization and neural networks"],"dc:type":["text"],"thesis:degree_discipline":["Electrical & Computer Engineering"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["M.S."],"thesis:institution_name":["University of Illinois at Urbana-Champaign"]},"updated_at":"2026-07-22T22:26:32Z"}