{"id":"https://openalex.org/W3007871793","doi":"https://doi.org/10.1109/icassp40776.2020.9054401","title":"Efficient Trainable Front-Ends for Neural Speech Enhancement","display_name":"Efficient Trainable Front-Ends for Neural Speech Enhancement","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3007871793","doi":"https://doi.org/10.1109/icassp40776.2020.9054401","mag":"3007871793"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054401","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054401","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2002.09286","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014125577","display_name":"Jonah Casebeer","orcid":"https://orcid.org/0000-0002-8741-9773"},"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":true,"raw_author_name":"Jonah Casebeer","raw_affiliation_strings":["University of Illinois, Urbana-Champaign","University of Illinois Urbana Champaign >  >  >  >"],"affiliations":[{"raw_affiliation_string":"University of Illinois, Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"University of Illinois Urbana Champaign >  >  >  >","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036092393","display_name":"Umut Isik","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Umut Isik","raw_affiliation_strings":["Amazon Web Services, Amazon AI","Amazon AI,Amazon Web Services"],"affiliations":[{"raw_affiliation_string":"Amazon Web Services, Amazon AI","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon AI,Amazon Web Services","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001842601","display_name":"Shrikant Venkataramani","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":"Shrikant Venkataramani","raw_affiliation_strings":["University of Illinois, Urbana-Champaign","University of Illinois Urbana Champaign >  >  >  >"],"affiliations":[{"raw_affiliation_string":"University of Illinois, Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"University of Illinois Urbana Champaign >  >  >  >","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112751528","display_name":"Arvindh Krishnaswamy","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arvindh Krishnaswamy","raw_affiliation_strings":["Amazon Web Services, Amazon AI","Amazon AI,Amazon Web Services"],"affiliations":[{"raw_affiliation_string":"Amazon Web Services, Amazon AI","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon AI,Amazon Web Services","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5014125577"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01904949,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6639","last_page":"6643"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9980999827384949,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.9156689643859863},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7186785936355591},{"id":"https://openalex.org/keywords/fourier-transform","display_name":"Fourier transform","score":0.7003106474876404},{"id":"https://openalex.org/keywords/front-and-back-ends","display_name":"Front and back ends","score":0.6254836916923523},{"id":"https://openalex.org/keywords/discrete-fourier-transform","display_name":"Discrete Fourier transform (general)","score":0.5512651801109314},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5020790100097656},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4858529269695282},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.45636340975761414},{"id":"https://openalex.org/keywords/fast-fourier-transform","display_name":"Fast Fourier transform","score":0.4519958794116974},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4056296944618225},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.31603750586509705},{"id":"https://openalex.org/keywords/fourier-analysis","display_name":"Fourier analysis","score":0.16942599415779114},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14736732840538025}],"concepts":[{"id":"https://openalex.org/C166386157","wikidata":"https://www.wikidata.org/wiki/Q1477735","display_name":"Short-time Fourier transform","level":4,"score":0.9156689643859863},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7186785936355591},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.7003106474876404},{"id":"https://openalex.org/C53016008","wikidata":"https://www.wikidata.org/wiki/Q620167","display_name":"Front and back ends","level":2,"score":0.6254836916923523},{"id":"https://openalex.org/C57733114","wikidata":"https://www.wikidata.org/wiki/Q1006032","display_name":"Discrete Fourier transform (general)","level":5,"score":0.5512651801109314},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5020790100097656},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4858529269695282},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.45636340975761414},{"id":"https://openalex.org/C75172450","wikidata":"https://www.wikidata.org/wiki/Q623950","display_name":"Fast Fourier transform","level":2,"score":0.4519958794116974},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4056296944618225},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.31603750586509705},{"id":"https://openalex.org/C203024314","wikidata":"https://www.wikidata.org/wiki/Q1365258","display_name":"Fourier analysis","level":3,"score":0.16942599415779114},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14736732840538025},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054401","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054401","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2002.09286","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2002.09286","pdf_url":"https://arxiv.org/pdf/2002.09286","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":"","raw_type":"text"},{"id":"mag:3007871793","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2002.09286.pdf","pdf_url":null,"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2002.09286","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2002.09286","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"},{"id":"doi:10.17023/q7cc-7276","is_oa":true,"landing_page_url":"https://doi.org/10.17023/q7cc-7276","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2002.09286","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2002.09286","pdf_url":"https://arxiv.org/pdf/2002.09286","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":"","raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6399999856948853}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3007871793.pdf","grobid_xml":"https://content.openalex.org/works/W3007871793.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1901129140","https://openalex.org/W1952824372","https://openalex.org/W2031647436","https://openalex.org/W2046869671","https://openalex.org/W2134572726","https://openalex.org/W2186615578","https://openalex.org/W2221409856","https://openalex.org/W2460742184","https://openalex.org/W2504718840","https://openalex.org/W2603567530","https://openalex.org/W2757519008","https://openalex.org/W2902132730","https://openalex.org/W2952218014","https://openalex.org/W2962935966","https://openalex.org/W2963103134","https://openalex.org/W2963341071","https://openalex.org/W2963443859","https://openalex.org/W2963902628","https://openalex.org/W2973054567","https://openalex.org/W6631190155","https://openalex.org/W6639824700","https://openalex.org/W6751512325","https://openalex.org/W6756251360"],"related_works":["https://openalex.org/W3160428055","https://openalex.org/W2614024025","https://openalex.org/W2789016743","https://openalex.org/W2944972166","https://openalex.org/W2028561103","https://openalex.org/W2535125847","https://openalex.org/W3126187707","https://openalex.org/W2765654763","https://openalex.org/W3205770165","https://openalex.org/W2767340368","https://openalex.org/W3127902358","https://openalex.org/W3173044051","https://openalex.org/W3204732550","https://openalex.org/W1605856301","https://openalex.org/W2766930522","https://openalex.org/W3160190545","https://openalex.org/W3099662743","https://openalex.org/W2021956099","https://openalex.org/W3193481629","https://openalex.org/W2963512705"],"abstract_inverted_index":{"Many":[0],"neural":[1,71],"speech":[2,72],"enhancement":[3,73],"and":[4,62,66],"source":[5],"separation":[6],"systems":[7],"operate":[8],"in":[9],"the":[10,53,58,78,82],"time-frequency":[11],"domain.":[12],"Such":[13],"models":[14],"often":[15],"benefit":[16],"from":[17],"making":[18,81],"their":[19],"Short-Time":[20],"Fourier":[21,35,60],"Transform":[22,36],"(STFT)":[23],"front-ends":[24],"trainable.":[25,85],"In":[26],"current":[27],"literature,":[28],"these":[29],"are":[30,39],"implemented":[31],"as":[32],"large":[33],"Discrete":[34],"matrices;":[37],"which":[38],"prohibitively":[40],"inefficient":[41],"for":[42,69],"low-compute":[43,70],"systems.":[44],"We":[45,75],"present":[46],"an":[47],"efficient,":[48],"trainable":[49],"front-end":[50],"based":[51],"on":[52],"butterfly":[54],"mechanism":[55],"to":[56],"compute":[57],"Fast":[59],"Transform,":[61],"show":[63],"its":[64],"accuracy":[65],"efficiency":[67],"benefits":[68],"models.":[74],"also":[76],"explore":[77],"effects":[79],"of":[80],"STFT":[83],"window":[84]},"counts_by_year":[],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}