{"id":"https://openalex.org/W4375869182","doi":"https://doi.org/10.1109/icassp49357.2023.10097153","title":"Learning Interpretable Filters In Wav-UNet For Speech Enhancement","display_name":"Learning Interpretable Filters In Wav-UNet For Speech Enhancement","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375869182","doi":"https://doi.org/10.1109/icassp49357.2023.10097153"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10097153","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10097153","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://telecom-paris.hal.science/hal-04048829/document","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5038985810","display_name":"F\u00e9lix Mathieu","orcid":null},"institutions":[{"id":"https://openalex.org/I2801356230","display_name":"Thales (Australia)","ror":"https://ror.org/00f7vya03","country_code":"AU","type":"company","lineage":["https://openalex.org/I2801356230","https://openalex.org/I4210140930"]},{"id":"https://openalex.org/I4210165912","display_name":"Laboratoire Traitement et Communication de l\u2019Information","ror":"https://ror.org/057er4c39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4210165912"]}],"countries":["AU","FR"],"is_corresponding":false,"raw_author_name":"F\u00e9lix Mathieu","raw_affiliation_strings":["LTCI, Télécom Paris, IP-Paris","Thales SIX, Advanced Studies AI Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LTCI, Télécom Paris, IP-Paris","institution_ids":["https://openalex.org/I4210165912"]},{"raw_affiliation_string":"Thales SIX, Advanced Studies AI Lab","institution_ids":["https://openalex.org/I2801356230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024072047","display_name":"Thomas Courtat","orcid":null},"institutions":[{"id":"https://openalex.org/I2801356230","display_name":"Thales (Australia)","ror":"https://ror.org/00f7vya03","country_code":"AU","type":"company","lineage":["https://openalex.org/I2801356230","https://openalex.org/I4210140930"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Thomas Courtat","raw_affiliation_strings":["Thales SIX, Advanced Studies AI Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Thales SIX, Advanced Studies AI Lab","institution_ids":["https://openalex.org/I2801356230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055423112","display_name":"Ga\u00ebl Richard","orcid":"https://orcid.org/0000-0002-4960-0010"},"institutions":[{"id":"https://openalex.org/I4210165912","display_name":"Laboratoire Traitement et Communication de l\u2019Information","ror":"https://ror.org/057er4c39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4210165912"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Ga\u00ebl Richard","raw_affiliation_strings":["LTCI, Télécom Paris, IP-Paris"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LTCI, Télécom Paris, IP-Paris","institution_ids":["https://openalex.org/I4210165912"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063097936","display_name":"Geoffroy Peeters","orcid":"https://orcid.org/0000-0001-5255-3019"},"institutions":[{"id":"https://openalex.org/I4210165912","display_name":"Laboratoire Traitement et Communication de l\u2019Information","ror":"https://ror.org/057er4c39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4210165912"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Geoffroy Peeters","raw_affiliation_strings":["LTCI, Télécom Paris, IP-Paris"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LTCI, Télécom Paris, IP-Paris","institution_ids":["https://openalex.org/I4210165912"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3695,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.52847592,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998000264167786,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9988999962806702,"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/interpretability","display_name":"Interpretability","score":0.8389859795570374},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7540678977966309},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6503148078918457},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.6383904814720154},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6209053993225098},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5984510779380798},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.5183663964271545},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4707176089286804},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.44994300603866577},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4455448389053345},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.42293310165405273},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4115256071090698},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34579038619995117},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.32960790395736694},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.11701327562332153},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08314171433448792}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.8389859795570374},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7540678977966309},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6503148078918457},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.6383904814720154},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6209053993225098},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5984510779380798},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.5183663964271545},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4707176089286804},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.44994300603866577},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4455448389053345},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.42293310165405273},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4115256071090698},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34579038619995117},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.32960790395736694},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.11701327562332153},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08314171433448792},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp49357.2023.10097153","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10097153","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-04048829v1","is_oa":true,"landing_page_url":"https://telecom-paris.hal.science/hal-04048829","pdf_url":"https://telecom-paris.hal.science/hal-04048829/document","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Jun 2023, Rhodes, Greece","raw_type":"Conference papers"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-04048829v1","is_oa":true,"landing_page_url":"https://telecom-paris.hal.science/hal-04048829","pdf_url":"https://telecom-paris.hal.science/hal-04048829/document","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Jun 2023, Rhodes, Greece","raw_type":"Conference papers"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.4099999964237213}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4375869182.pdf"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W1901129140","https://openalex.org/W2031647436","https://openalex.org/W2067295501","https://openalex.org/W2918296821","https://openalex.org/W2952218014","https://openalex.org/W2962866211","https://openalex.org/W2962935966","https://openalex.org/W2963341071","https://openalex.org/W2963452667","https://openalex.org/W2964052309","https://openalex.org/W2971458685","https://openalex.org/W2998832642","https://openalex.org/W3004940340","https://openalex.org/W3007948068","https://openalex.org/W3096408984","https://openalex.org/W3097034112","https://openalex.org/W3099330747","https://openalex.org/W3102190437","https://openalex.org/W3131332223","https://openalex.org/W3160085755","https://openalex.org/W3160129476","https://openalex.org/W3174264304","https://openalex.org/W4221144097","https://openalex.org/W4224925594","https://openalex.org/W4225905067","https://openalex.org/W4297775537","https://openalex.org/W6639824700","https://openalex.org/W6737664043","https://openalex.org/W6743462201","https://openalex.org/W6751512325"],"related_works":["https://openalex.org/W4319993887","https://openalex.org/W4297789176","https://openalex.org/W2768346313","https://openalex.org/W2963249138","https://openalex.org/W2998594699","https://openalex.org/W4396882122","https://openalex.org/W3178016723","https://openalex.org/W2968060152","https://openalex.org/W4313400923","https://openalex.org/W4377865163"],"abstract_inverted_index":{"Due":[0],"to":[1,26,51,71,109,120,130],"their":[2],"performances,":[3,56],"deep":[4,47],"neural":[5,21,116,127],"networks":[6,22],"have":[7],"emerged":[8],"as":[9,63],"a":[10,33,72,92,114,139],"major":[11],"method":[12],"in":[13,36,42,81,86,104,149],"nearly":[14],"all":[15],"modern":[16],"audio":[17],"processing":[18],"applications.":[19],"Deep":[20],"can":[23,49],"be":[24],"used":[25,80],"estimate":[27],"some":[28,37],"parameters":[29],"or":[30,35],"hyperparameters":[31],"of":[32,53,98,125,141,156],"model,":[34],"cases":[38],"the":[39,54,77,96,99,123,126,136,147,154,157],"entire":[40],"model":[41],"an":[43,87,107],"end-to-end":[44],"fashion.":[45],"Although":[46],"learning":[48],"lead":[50],"state":[52],"art":[55],"they":[57,64],"also":[58],"suffer":[59],"from":[60],"inherent":[61],"weaknesses":[62],"usually":[65],"remain":[66],"complex":[67],"and":[68,129,144],"non":[69],"interpretable":[70,111],"large":[73],"extent.":[74],"For":[75],"instance,":[76],"internal":[78],"filters":[79,112],"each":[82],"layers":[83],"are":[84],"chosen":[85],"adhoc":[88],"manner":[89],"with":[90,95],"only":[91],"loose":[93],"relation":[94],"nature":[97],"processed":[100],"signal.":[101],"We":[102,134],"propose":[103],"this":[105],"paper":[106],"approach":[108,137],"learn":[110],"within":[113],"specific":[115],"architecture":[117],"which":[118],"allow":[119],"better":[121],"understand":[122],"behaviour":[124],"network":[128],"reduce":[131],"its":[132],"complexity.":[133],"validate":[135],"on":[138],"task":[140],"speech":[142],"enhancement":[143],"show":[145],"that":[146],"gain":[148],"interpretability":[150],"does":[151],"not":[152],"degrade":[153],"performance":[155],"model.":[158]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}