{"id":"https://openalex.org/W3097412542","doi":"https://doi.org/10.1109/icassp39728.2021.9413704","title":"Optimizing Short-Time Fourier Transform Parameters via Gradient Descent","display_name":"Optimizing Short-Time Fourier Transform Parameters via Gradient Descent","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3097412542","doi":"https://doi.org/10.1109/icassp39728.2021.9413704","mag":"3097412542"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9413704","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413704","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2010.15049","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101730224","display_name":"An Zhao","orcid":"https://orcid.org/0000-0002-6855-390X"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"An Zhao","raw_affiliation_strings":["University of Illinois, Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois, Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042472021","display_name":"Krishna Subramani","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Krishna Subramani","raw_affiliation_strings":["University of Illinois, Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois, Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038903729","display_name":"Paris Smaragdis","orcid":null},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]},{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Paris Smaragdis","raw_affiliation_strings":["Adobe Research","University of Illinois, Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe Research","institution_ids":["https://openalex.org/I1306409833"]},{"raw_affiliation_string":"University of Illinois, Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"736","last_page":"740"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10688","display_name":"Image and Signal Denoising Methods","score":0.9925000071525574,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/short-time-fourier-transform","display_name":"Short-time Fourier transform","score":0.9626705646514893},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.6689532995223999},{"id":"https://openalex.org/keywords/fourier-transform","display_name":"Fourier transform","score":0.6171111464500427},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5861955285072327},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5461689829826355},{"id":"https://openalex.org/keywords/window-function","display_name":"Window function","score":0.4563702642917633},{"id":"https://openalex.org/keywords/time\u2013frequency-analysis","display_name":"Time\u2013frequency analysis","score":0.4478045701980591},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.36436089873313904},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.36011385917663574},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3517569899559021},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33673352003097534},{"id":"https://openalex.org/keywords/fourier-analysis","display_name":"Fourier analysis","score":0.206851989030838},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.11390161514282227},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.09452754259109497},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.08139467239379883},{"id":"https://openalex.org/keywords/spectral-density","display_name":"Spectral density","score":0.07330116629600525},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07111901044845581}],"concepts":[{"id":"https://openalex.org/C166386157","wikidata":"https://www.wikidata.org/wiki/Q1477735","display_name":"Short-time Fourier transform","level":4,"score":0.9626705646514893},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.6689532995223999},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.6171111464500427},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5861955285072327},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5461689829826355},{"id":"https://openalex.org/C140101238","wikidata":"https://www.wikidata.org/wiki/Q1404885","display_name":"Window function","level":3,"score":0.4563702642917633},{"id":"https://openalex.org/C142433447","wikidata":"https://www.wikidata.org/wiki/Q7806653","display_name":"Time\u2013frequency analysis","level":3,"score":0.4478045701980591},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.36436089873313904},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.36011385917663574},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3517569899559021},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33673352003097534},{"id":"https://openalex.org/C203024314","wikidata":"https://www.wikidata.org/wiki/Q1365258","display_name":"Fourier analysis","level":3,"score":0.206851989030838},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.11390161514282227},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.09452754259109497},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.08139467239379883},{"id":"https://openalex.org/C168110828","wikidata":"https://www.wikidata.org/wiki/Q1331626","display_name":"Spectral density","level":2,"score":0.07330116629600525},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07111901044845581},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp39728.2021.9413704","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413704","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2010.15049","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.15049","pdf_url":"https://arxiv.org/pdf/2010.15049","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2010.15049","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.15049","pdf_url":"https://arxiv.org/pdf/2010.15049","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1587637155","https://openalex.org/W2019820129","https://openalex.org/W2115144768","https://openalex.org/W2120221444","https://openalex.org/W2127971633","https://openalex.org/W2165770301","https://openalex.org/W2323013332","https://openalex.org/W2970897180","https://openalex.org/W2990166781","https://openalex.org/W3000389243","https://openalex.org/W4288263001","https://openalex.org/W6635192221","https://openalex.org/W6766581138","https://openalex.org/W6771763809","https://openalex.org/W6996675354"],"related_works":["https://openalex.org/W4205152111","https://openalex.org/W2393357744","https://openalex.org/W2980984853","https://openalex.org/W4221076379","https://openalex.org/W2326454079","https://openalex.org/W564939545","https://openalex.org/W197430446","https://openalex.org/W2100209102","https://openalex.org/W2533590149","https://openalex.org/W4225639054"],"abstract_inverted_index":{"The":[0],"Short-Time":[1],"Fourier":[2],"Transform":[3],"(STFT)":[4],"has":[5],"been":[6],"a":[7,77],"staple":[8],"of":[9,54,58,98],"signal":[10,138],"processing,":[11],"often":[12,39,50],"being":[13],"the":[14,27,30,33,91,101,106],"first":[15],"step":[16],"for":[17,32,79,113,124],"many":[18],"audio":[19],"tasks.":[20],"A":[21],"very":[22],"familiar":[23],"process":[24],"when":[25],"using":[26],"STFT":[28,35,80,102,107],"is":[29],"search":[31],"best":[34],"parameters,":[36],"as":[37],"they":[38],"have":[40,129],"significant":[41],"side":[42],"effects":[43],"if":[44],"chosen":[45],"poorly.":[46],"These":[47],"parameters":[48,81,128],"are":[49],"defined":[51],"in":[52],"terms":[53],"an":[55,70,120],"integer":[56],"number":[57],"samples,":[59],"which":[60],"makes":[61],"their":[62],"optimization":[63,97],"non-trivial.":[64],"In":[65],"this":[66],"paper":[67],"we":[68],"show":[69],"approach":[71],"that":[72,116],"allows":[73],"us":[74],"to":[75,84,93,130,135],"obtain":[76],"gradient":[78,95],"with":[82],"respect":[83],"arbitrary":[85],"cost":[86],"functions,":[87],"and":[88],"thus":[89],"enable":[90],"ability":[92],"employ":[94],"descent":[96],"quantities":[99],"like":[100],"window":[103],"length,":[104],"or":[105],"hop":[108],"size.":[109],"We":[110],"do":[111],"so":[112],"parameter":[114],"values":[115],"stay":[117],"constant":[118],"throughout":[119],"input,":[121],"but":[122],"also":[123],"cases":[125],"where":[126],"these":[127],"dynamically":[131],"change":[132],"over":[133],"time":[134],"accommodate":[136],"varying":[137],"characteristics.":[139]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}