{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/109453"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/109453","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Differential DSP: An audio toolbox for end-to-end ml","abstract":"The short-time Fourier transform (STFT) has been a staple of signal processing, often being the first step for many audio tasks. A very familiar process when using the STFT is the search for the best STFT parameters, as they often have significant side effects if chosen poorly. These parameters are often de ned in terms of an integer number of samples, which makes their optimization non-trivial. We present a toolbox that allows us to obtain gradients for commonly used audio filter parameters, and for STFT parameters with respect to arbitrary cost functions, thus enabling gradient descent optimization of quantities like the STFT window length or the STFT hop size. We do so for parameter values that stay constant throughout an input, but also for cases where these parameters have to dynamically change over time to accommodate varying signal characteristics.","abstract_html":"The short-time Fourier transform (STFT) has been a staple of signal processing, often being the first step for many audio tasks. A very familiar process when using the STFT is the search for the best STFT parameters, as they often have significant side effects if chosen poorly. These parameters are often de ned in terms of an integer number of samples, which makes their optimization non-trivial. We present a toolbox that allows us to obtain gradients for commonly used audio filter parameters, and for STFT parameters with respect to arbitrary cost functions, thus enabling gradient descent optimization of quantities like the STFT window length or the STFT hop size. We do so for parameter values that stay constant throughout an input, but also for cases where these parameters have to dynamically change over time to accommodate varying signal characteristics.","abstract_has_math":false,"creators":["Zhao, An"],"institution":"University of Illinois at Urbana-Champaign","degree_name":"M.S.","degree_level":"Thesis","degree_discipline":"Electrical & Computer Engr","degree_department":null,"school":null,"contributors":["Smaragdis, Paris"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2021,"date_issued":"2021-03-05T21:38:25Z","date_published":"2021-03-05T21:38:25Z","updated_at":"2026-07-22T22:24:50Z","subjects":["Classification","Differential","DSP","DDSP","Machine learning","Audio"],"languages":["en"],"rights":["Copyright 2020 An Zhao"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/2142/109453","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":["Zhao, An"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2021-03-05T21:38:25Z","2020-12-10","2020-12"]},{"key":"dc:type","label":"Dc Type","values":["text","Thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Electrical & Computer Engr"]},{"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":["Classification","Differential","DSP","DDSP","Machine learning","Audio"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright 2020 An Zhao"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/2142/109453"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["The short-time Fourier transform (STFT) has been a staple of signal processing, often being the first step for many audio tasks. A very familiar process when using the STFT is the search for the best STFT parameters, as they often have significant side effects if chosen poorly. These parameters are often de ned in terms of an integer number of samples, which makes their optimization non-trivial. We present a toolbox that allows us to obtain gradients for commonly used audio filter parameters, and for STFT parameters with respect to arbitrary cost functions, thus enabling gradient descent optimization of quantities like the STFT window length or the STFT hop size. We do so for parameter values that stay constant throughout an input, but also for cases where these parameters have to dynamically change over time to accommodate varying signal characteristics.","Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2021-03-04 without embargo terms","The student, An Zhao, accepted the attached license on 2020-12-09 at 16:27.","The student, An Zhao, submitted this Thesis for approval on 2020-12-09 at 16:42.","This Thesis was approved for publication on 2020-12-10 at 16:58.","DSpace SAF Submission Ingestion Package generated from Vireo submission #16109 on 2021-03-04 at 15:36:24","Made available in DSpace on 2021-03-05T21:38:25Z (GMT). No. of bitstreams: 3 ZHAO-THESIS-2020.pdf: 4651193 bytes, checksum: bbec0cc91f79599baf258c48cf001cd9 (MD5) thesis.zip: 39213106 bytes, checksum: 4abb0f9f37571566778a3bfc1e5dc41d (MD5) LICENSE.txt: 4204 bytes, checksum: e15e47612959f171e1975a259230438b (MD5) Previous issue date: 2020-12-10"]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Differential DSP: An audio toolbox for end-to-end ml"]}]}],"canonical_facts":{"dc:contributor":["Smaragdis, Paris"],"dc:creator":["Zhao, An"],"dc:date":["2021-03-05T21:38:25Z","2020-12-10","2020-12"],"dc:description":["The short-time Fourier transform (STFT) has been a staple of signal processing, often being the first step for many audio tasks. A very familiar process when using the STFT is the search for the best STFT parameters, as they often have significant side effects if chosen poorly. These parameters are often de ned in terms of an integer number of samples, which makes their optimization non-trivial. We present a toolbox that allows us to obtain gradients for commonly used audio filter parameters, and for STFT parameters with respect to arbitrary cost functions, thus enabling gradient descent optimization of quantities like the STFT window length or the STFT hop size. We do so for parameter values that stay constant throughout an input, but also for cases where these parameters have to dynamically change over time to accommodate varying signal characteristics.","Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2021-03-04 without embargo terms","The student, An Zhao, accepted the attached license on 2020-12-09 at 16:27.","The student, An Zhao, submitted this Thesis for approval on 2020-12-09 at 16:42.","This Thesis was approved for publication on 2020-12-10 at 16:58.","DSpace SAF Submission Ingestion Package generated from Vireo submission #16109 on 2021-03-04 at 15:36:24","Made available in DSpace on 2021-03-05T21:38:25Z (GMT). No. of bitstreams: 3 ZHAO-THESIS-2020.pdf: 4651193 bytes, checksum: bbec0cc91f79599baf258c48cf001cd9 (MD5) thesis.zip: 39213106 bytes, checksum: 4abb0f9f37571566778a3bfc1e5dc41d (MD5) LICENSE.txt: 4204 bytes, checksum: e15e47612959f171e1975a259230438b (MD5) Previous issue date: 2020-12-10"],"dc:format":["application/pdf"],"dc:identifier":["http://hdl.handle.net/2142/109453"],"dc:language":["en"],"dc:rights":["Copyright 2020 An Zhao"],"dc:subject":["Classification","Differential","DSP","DDSP","Machine learning","Audio"],"dc:title":["Differential DSP: An audio toolbox for end-to-end ml"],"dc:type":["text","Thesis"],"thesis:degree_discipline":["Electrical & Computer Engr"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["M.S."],"thesis:institution_name":["University of Illinois at Urbana-Champaign"]},"updated_at":"2026-07-22T22:24:50Z"}