{"id":"https://openalex.org/W4395471070","doi":"https://doi.org/10.1109/taslp.2024.3393738","title":"Learning to Solve Inverse Problems for Perceptual Sound Matching","display_name":"Learning to Solve Inverse Problems for Perceptual Sound Matching","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4395471070","doi":"https://doi.org/10.1109/taslp.2024.3393738"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2024.3393738","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3393738","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.science/hal-04580765v1/document","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100321765","display_name":"Han Han","orcid":"https://orcid.org/0009-0002-4496-420X"},"institutions":[{"id":"https://openalex.org/I100445878","display_name":"\u00c9cole Centrale de Nantes","ror":"https://ror.org/03nh7d505","country_code":"FR","type":"education","lineage":["https://openalex.org/I100445878","https://openalex.org/I97188460"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210117005","display_name":"Laboratoire des Sciences du Num\u00e9rique de Nantes","ror":"https://ror.org/02snf8m58","country_code":"FR","type":"facility","lineage":["https://openalex.org/I100445878","https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I205703379","https://openalex.org/I4210117005","https://openalex.org/I4210124215","https://openalex.org/I4210127572","https://openalex.org/I4210139971","https://openalex.org/I97188460","https://openalex.org/I97188460"]},{"id":"https://openalex.org/I97188460","display_name":"Nantes Universit\u00e9","ror":"https://ror.org/03gnr7b55","country_code":"FR","type":"education","lineage":["https://openalex.org/I97188460"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Han Han","raw_affiliation_strings":["École Centrale Nantes, CNRS, LS2N, Nantes Université, Nantes, France"],"affiliations":[{"raw_affiliation_string":"École Centrale Nantes, CNRS, LS2N, Nantes Université, Nantes, France","institution_ids":["https://openalex.org/I97188460","https://openalex.org/I100445878","https://openalex.org/I4210117005","https://openalex.org/I1294671590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027789239","display_name":"Vincent Lostanlen","orcid":"https://orcid.org/0000-0003-0580-1651"},"institutions":[{"id":"https://openalex.org/I100445878","display_name":"\u00c9cole Centrale de Nantes","ror":"https://ror.org/03nh7d505","country_code":"FR","type":"education","lineage":["https://openalex.org/I100445878","https://openalex.org/I97188460"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210117005","display_name":"Laboratoire des Sciences du Num\u00e9rique de Nantes","ror":"https://ror.org/02snf8m58","country_code":"FR","type":"facility","lineage":["https://openalex.org/I100445878","https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I205703379","https://openalex.org/I4210117005","https://openalex.org/I4210124215","https://openalex.org/I4210127572","https://openalex.org/I4210139971","https://openalex.org/I97188460","https://openalex.org/I97188460"]},{"id":"https://openalex.org/I97188460","display_name":"Nantes Universit\u00e9","ror":"https://ror.org/03gnr7b55","country_code":"FR","type":"education","lineage":["https://openalex.org/I97188460"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Vincent Lostanlen","raw_affiliation_strings":["École Centrale Nantes, CNRS, LS2N, Nantes Université, Nantes, France"],"affiliations":[{"raw_affiliation_string":"École Centrale Nantes, CNRS, LS2N, Nantes Université, Nantes, France","institution_ids":["https://openalex.org/I97188460","https://openalex.org/I100445878","https://openalex.org/I4210117005","https://openalex.org/I1294671590"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029522748","display_name":"Mathieu Lagrange","orcid":"https://orcid.org/0000-0002-1253-4427"},"institutions":[{"id":"https://openalex.org/I100445878","display_name":"\u00c9cole Centrale de Nantes","ror":"https://ror.org/03nh7d505","country_code":"FR","type":"education","lineage":["https://openalex.org/I100445878","https://openalex.org/I97188460"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210117005","display_name":"Laboratoire des Sciences du Num\u00e9rique de Nantes","ror":"https://ror.org/02snf8m58","country_code":"FR","type":"facility","lineage":["https://openalex.org/I100445878","https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I205703379","https://openalex.org/I4210117005","https://openalex.org/I4210124215","https://openalex.org/I4210127572","https://openalex.org/I4210139971","https://openalex.org/I97188460","https://openalex.org/I97188460"]},{"id":"https://openalex.org/I97188460","display_name":"Nantes Universit\u00e9","ror":"https://ror.org/03gnr7b55","country_code":"FR","type":"education","lineage":["https://openalex.org/I97188460"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Mathieu Lagrange","raw_affiliation_strings":["École Centrale Nantes, CNRS, LS2N, Nantes Université, Nantes, France"],"affiliations":[{"raw_affiliation_string":"École Centrale Nantes, CNRS, LS2N, Nantes Université, Nantes, France","institution_ids":["https://openalex.org/I97188460","https://openalex.org/I100445878","https://openalex.org/I4210117005","https://openalex.org/I1294671590"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100321765"],"corresponding_institution_ids":["https://openalex.org/I100445878","https://openalex.org/I1294671590","https://openalex.org/I4210117005","https://openalex.org/I97188460"],"apc_list":null,"apc_paid":null,"fwci":1.4017,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.80014855,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"32","issue":null,"first_page":"2605","last_page":"2615"},"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/T11309","display_name":"Music 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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9965000152587891,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.6163219213485718},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.577556312084198},{"id":"https://openalex.org/keywords/inverse","display_name":"Inverse","score":0.5576531291007996},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5488685369491577},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5133794546127319},{"id":"https://openalex.org/keywords/inverse-problem","display_name":"Inverse problem","score":0.5031184554100037},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3793853521347046},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.3310825824737549},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.32796502113342285},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.2344871163368225},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.1226469874382019},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.09691700339317322},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08736532926559448},{"id":"https://openalex.org/keywords/neuroscience","display_name":"Neuroscience","score":0.08411416411399841}],"concepts":[{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.6163219213485718},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.577556312084198},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.5576531291007996},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5488685369491577},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5133794546127319},{"id":"https://openalex.org/C135252773","wikidata":"https://www.wikidata.org/wiki/Q1567213","display_name":"Inverse problem","level":2,"score":0.5031184554100037},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3793853521347046},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.3310825824737549},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.32796502113342285},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2344871163368225},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.1226469874382019},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.09691700339317322},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08736532926559448},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.08411416411399841},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/taslp.2024.3393738","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3393738","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:HAL:hal-04580765v1","is_oa":true,"landing_page_url":"https://hal.science/hal-04580765","pdf_url":"https://hal.science/hal-04580765v1/document","source":{"id":"https://openalex.org/S4406922466","display_name":"SPIRE - Sciences Po Institutional REpository","issn_l":null,"issn":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech and Language Processing, 2024, 32, pp.2605-2615. ⟨10.1109/TASLP.2024.3393738⟩","raw_type":"Journal articles"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-04580765v1","is_oa":true,"landing_page_url":"https://hal.science/hal-04580765","pdf_url":"https://hal.science/hal-04580765v1/document","source":{"id":"https://openalex.org/S4406922466","display_name":"SPIRE - Sciences Po Institutional REpository","issn_l":null,"issn":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech and Language Processing, 2024, 32, pp.2605-2615. ⟨10.1109/TASLP.2024.3393738⟩","raw_type":"Journal articles"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8868169146","display_name":"Sensorimotor integration of variability during birdsong learning","funder_award_id":"ANR-23-CE37-0025","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"}],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"},{"id":"https://openalex.org/F4320326256","display_name":"Grand \u00c9quipement National De Calcul Intensif","ror":"https://ror.org/0010d1q40"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4395471070.pdf","grobid_xml":"https://content.openalex.org/works/W4395471070.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W130921173","https://openalex.org/W1543133788","https://openalex.org/W2054139811","https://openalex.org/W2102960446","https://openalex.org/W2127302078","https://openalex.org/W2791716806","https://openalex.org/W2945837706","https://openalex.org/W2977735357","https://openalex.org/W2990440871","https://openalex.org/W3006956021","https://openalex.org/W3096429957","https://openalex.org/W3109975354","https://openalex.org/W3111213250","https://openalex.org/W3157152805","https://openalex.org/W3159239022","https://openalex.org/W3184587295","https://openalex.org/W4206592572","https://openalex.org/W4316660651","https://openalex.org/W4372259957","https://openalex.org/W4372260533","https://openalex.org/W4372348434","https://openalex.org/W4386589137","https://openalex.org/W4386707775","https://openalex.org/W4386763353","https://openalex.org/W4390745914","https://openalex.org/W6762718338","https://openalex.org/W6771763809","https://openalex.org/W6780861951","https://openalex.org/W6787485125","https://openalex.org/W6788012183","https://openalex.org/W6810616001","https://openalex.org/W6842676699","https://openalex.org/W6846529734","https://openalex.org/W6852950611","https://openalex.org/W6999359274","https://openalex.org/W7042548776"],"related_works":["https://openalex.org/W2909726438","https://openalex.org/W2067046791","https://openalex.org/W2909888262","https://openalex.org/W2025747832","https://openalex.org/W3020957235","https://openalex.org/W2056769785","https://openalex.org/W611303608","https://openalex.org/W4313595395","https://openalex.org/W2331917905","https://openalex.org/W3155039083"],"abstract_inverted_index":{"Perceptual":[0],"sound":[1],"matching":[2],"(PSM)":[3],"aims":[4,67],"to":[5,10,15,29,84,119,150],"find":[6,194],"the":[7,41,50,86,95,170],"input":[8],"parameters":[9,90],"a":[11,26,45,56,70,112,138],"synthesizer":[12],"so":[13],"as":[14,159],"best":[16],"imitate":[17],"an":[18,134],"audio":[19],"target.":[20],"Deep":[21],"learning":[22],"for":[23],"PSM":[24,202],"optimizes":[25],"neural":[27],"network":[28],"analyze":[30],"and":[31,75,110,137,183,193],"reconstruct":[32],"prerecorded":[33],"samples.":[34],"In":[35],"this":[36],"context,":[37],"our":[38],"article":[39],"addresses":[40],"problem":[42],"of":[43,88,97,131,141,172],"designing":[44],"suitable":[46],"loss":[47,64],"function":[48],"when":[49],"training":[51,99],"set":[52],"is":[53,62,83,104,148],"generated":[54],"by":[55],"differentiable":[57,120],"synthesizer.":[58],"Our":[59],"main":[60],"contribution":[61],"perceptual\u2013neural\u2013physical":[63],"(PNP),":[65],"which":[66],"at":[68],"addressing":[69],"tradeoff":[71],"between":[72],"perceptual":[73,165],"relevance":[74],"computational":[76],"efficiency.":[77],"The":[78,101],"key":[79],"idea":[80],"behind":[81],"PNP":[82,127,147],"linearize":[85],"effect":[87],"synthesis":[89],"upon":[91],"auditory":[92,160,181],"features":[93],"in":[94,176],"vicinity":[96],"each":[98],"sample.":[100],"linearization":[102],"procedure":[103],"massively":[105],"parallelizable,":[106],"can":[107],"be":[108],"precomputed,":[109],"offers":[111],"100-fold":[113],"speedup":[114],"during":[115],"gradient":[116,184],"descent":[117],"compared":[118],"digital":[121],"signal":[122],"processing":[123],"(DDSP).":[124],"We":[125,144,186],"demonstrate":[126],"on":[128,190,201],"two":[129],"datasets":[130,192],"nonstationary":[132],"sounds:":[133],"AM/FM":[135],"arpeggiator":[136],"physical":[139],"model":[140],"rectangular":[142],"membranes.":[143],"show":[145],"that":[146,195],"able":[149],"accelerate":[151],"DDSP":[152],"with":[153],"joint":[154],"time\u2013frequency":[155],"scattering":[156],"transform":[157],"(JTFS)":[158],"feature":[161],"while":[162],"preserving":[163],"its":[164],"fidelity.":[166],"Additionally,":[167],"we":[168],"evaluate":[169],"impact":[171],"other":[173,206],"design":[174,207],"choices":[175],"PSM:":[177],"parameter":[178],"rescaling,":[179],"pretraining,":[180],"representation,":[182],"clipping.":[185],"report":[187],"state-of-the-art":[188],"results":[189],"both":[191],"PNP-accelerated":[196],"JTFS":[197],"has":[198],"greater":[199],"influence":[200],"performance":[203],"than":[204],"any":[205],"choice.":[208]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}