{"id":"https://openalex.org/W4372259957","doi":"https://doi.org/10.1109/icassp49357.2023.10095391","title":"Perceptual\u2013Neural\u2013Physical Sound Matching","display_name":"Perceptual\u2013Neural\u2013Physical Sound Matching","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372259957","doi":"https://doi.org/10.1109/icassp49357.2023.10095391"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095391","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095391","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://hal.science/hal-04027307v1/file/pnp_icassp_han.pdf","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":["Nantes Universit&#x00E9;, &#x00C9;cole Centrale Nantes, CNRS, LS2N, UMR 6004,Nantes,France,F-44000","LS2N - \u00e9quipe SIMS  - Signal, IMage et Son (France)","LS2N - Laboratoire des Sciences du Num\u00e9rique de Nantes (Nantes Universit\u00e9 \u2013 facult\u00e9 des Sciences et Techniques (FST)\r\n2 Chemin de la Houssini\u00e8re\r\nBP 92208, 44322 Nantes Cedex 3 - France)"],"affiliations":[{"raw_affiliation_string":"Nantes Universit&#x00E9;, &#x00C9;cole Centrale Nantes, CNRS, LS2N, UMR 6004,Nantes,France,F-44000","institution_ids":["https://openalex.org/I97188460","https://openalex.org/I100445878","https://openalex.org/I4210117005","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"LS2N - \u00e9quipe SIMS  - Signal, IMage et Son (France)","institution_ids":["https://openalex.org/I97188460","https://openalex.org/I4210117005"]},{"raw_affiliation_string":"LS2N - Laboratoire des Sciences du Num\u00e9rique de Nantes (Nantes Universit\u00e9 \u2013 facult\u00e9 des Sciences et Techniques (FST)\r\n2 Chemin de la Houssini\u00e8re\r\nBP 92208, 44322 Nantes Cedex 3 - France)","institution_ids":["https://openalex.org/I4210117005","https://openalex.org/I97188460"]}]},{"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":["Nantes Universit&#x00E9;, &#x00C9;cole Centrale Nantes, CNRS, LS2N, UMR 6004,Nantes,France,F-44000","LS2N - Laboratoire des Sciences du Num\u00e9rique de Nantes (Nantes Universit\u00e9 \u2013 facult\u00e9 des Sciences et Techniques (FST)\r\n2 Chemin de la Houssini\u00e8re\r\nBP 92208, 44322 Nantes Cedex 3 - France)","LS2N - \u00e9quipe SIMS  - Signal, IMage et Son (France)"],"affiliations":[{"raw_affiliation_string":"Nantes Universit&#x00E9;, &#x00C9;cole Centrale Nantes, CNRS, LS2N, UMR 6004,Nantes,France,F-44000","institution_ids":["https://openalex.org/I97188460","https://openalex.org/I100445878","https://openalex.org/I4210117005","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"LS2N - Laboratoire des Sciences du Num\u00e9rique de Nantes (Nantes Universit\u00e9 \u2013 facult\u00e9 des Sciences et Techniques (FST)\r\n2 Chemin de la Houssini\u00e8re\r\nBP 92208, 44322 Nantes Cedex 3 - France)","institution_ids":["https://openalex.org/I4210117005","https://openalex.org/I97188460"]},{"raw_affiliation_string":"LS2N - \u00e9quipe SIMS  - Signal, IMage et Son (France)","institution_ids":["https://openalex.org/I97188460","https://openalex.org/I4210117005"]}]},{"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":["Nantes Universit&#x00E9;, &#x00C9;cole Centrale Nantes, CNRS, LS2N, UMR 6004,Nantes,France,F-44000","LS2N - \u00e9quipe SIMS  - Signal, IMage et Son (France)","LS2N - Laboratoire des Sciences du Num\u00e9rique de Nantes (Nantes Universit\u00e9 \u2013 facult\u00e9 des Sciences et Techniques (FST)\r\n2 Chemin de la Houssini\u00e8re\r\nBP 92208, 44322 Nantes Cedex 3 - France)","LS2N - Laboratoire des Sciences du Num\u00e9rique de Nantes (Universit\u00e9 de Nantes \u2013 facult\u00e9 des Sciences et Techniques (FST)\r\n2 Chemin de la Houssini\u00e8re\r\nBP 92208, 44322 Nantes Cedex 3 - France)"],"affiliations":[{"raw_affiliation_string":"Nantes Universit&#x00E9;, &#x00C9;cole Centrale Nantes, CNRS, LS2N, UMR 6004,Nantes,France,F-44000","institution_ids":["https://openalex.org/I97188460","https://openalex.org/I100445878","https://openalex.org/I4210117005","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"LS2N - \u00e9quipe SIMS  - Signal, IMage et Son (France)","institution_ids":["https://openalex.org/I97188460","https://openalex.org/I4210117005"]},{"raw_affiliation_string":"LS2N - Laboratoire des Sciences du Num\u00e9rique de Nantes (Nantes Universit\u00e9 \u2013 facult\u00e9 des Sciences et Techniques (FST)\r\n2 Chemin de la Houssini\u00e8re\r\nBP 92208, 44322 Nantes Cedex 3 - France)","institution_ids":["https://openalex.org/I4210117005","https://openalex.org/I97188460"]},{"raw_affiliation_string":"LS2N - Laboratoire des Sciences du Num\u00e9rique de Nantes (Universit\u00e9 de Nantes \u2013 facult\u00e9 des Sciences et Techniques (FST)\r\n2 Chemin de la Houssini\u00e8re\r\nBP 92208, 44322 Nantes Cedex 3 - France)","institution_ids":["https://openalex.org/I4210117005","https://openalex.org/I97188460"]}]}],"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":1.0089,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.74670136,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"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":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech 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/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/T11349","display_name":"Music Technology and Sound Studies","score":0.9983999729156494,"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/computer-science","display_name":"Computer science","score":0.5876415371894836},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.5788755416870117},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5185030698776245},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.46685487031936646},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.451978862285614},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4473527669906616},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4416767656803131},{"id":"https://openalex.org/keywords/mean-squared-error","display_name":"Mean squared error","score":0.42332136631011963},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38580891489982605},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3348884582519531},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.07849207520484924}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5876415371894836},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.5788755416870117},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5185030698776245},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.46685487031936646},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.451978862285614},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4473527669906616},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4416767656803131},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.42332136631011963},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38580891489982605},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3348884582519531},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.07849207520484924},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095391","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095391","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-04027307v1","is_oa":true,"landing_page_url":"https://hal.science/hal-04027307","pdf_url":"https://hal.science/hal-04027307v1/file/pnp_icassp_han.pdf","source":{"id":"https://openalex.org/S4406922451","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":"Proceedings of the International Conference on Acoustics, Speech, and Signal Processing, Jun 2023, Rhodes Island, Greece, France. pp.1-5, &#x27E8;10.1109/ICASSP49357.2023.10095391&#x27E9;","raw_type":"Conference papers"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-04027307v1","is_oa":true,"landing_page_url":"https://hal.science/hal-04027307","pdf_url":"https://hal.science/hal-04027307v1/file/pnp_icassp_han.pdf","source":{"id":"https://openalex.org/S4406922451","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":"Proceedings of the International Conference on Acoustics, Speech, and Signal Processing, Jun 2023, Rhodes Island, Greece, France. pp.1-5, &#x27E8;10.1109/ICASSP49357.2023.10095391&#x27E9;","raw_type":"Conference papers"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4372259957.pdf","grobid_xml":"https://content.openalex.org/works/W4372259957.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W1541986262","https://openalex.org/W1543133788","https://openalex.org/W2054139811","https://openalex.org/W2259990426","https://openalex.org/W2790620558","https://openalex.org/W2791716806","https://openalex.org/W2908414239","https://openalex.org/W2945837706","https://openalex.org/W2955263139","https://openalex.org/W2955425717","https://openalex.org/W3000389243","https://openalex.org/W3111213250","https://openalex.org/W3131914614","https://openalex.org/W3185453408","https://openalex.org/W4224304391","https://openalex.org/W4226247372","https://openalex.org/W4287372095","https://openalex.org/W4321473516","https://openalex.org/W4386589137","https://openalex.org/W6632550847","https://openalex.org/W6692743877","https://openalex.org/W6757542112","https://openalex.org/W6762718338","https://openalex.org/W6765634264","https://openalex.org/W6771763809","https://openalex.org/W6780861951","https://openalex.org/W6789403026","https://openalex.org/W6810616001","https://openalex.org/W6811204662","https://openalex.org/W6850311597"],"related_works":["https://openalex.org/W1974895211","https://openalex.org/W2176409448","https://openalex.org/W2129841057","https://openalex.org/W3040712279","https://openalex.org/W2364769705","https://openalex.org/W2056136368","https://openalex.org/W2374664672","https://openalex.org/W4367555392","https://openalex.org/W2883092465","https://openalex.org/W2114441484"],"abstract_inverted_index":{"Sound":[0],"matching":[1,21,172],"algorithms":[2],"seek":[3],"to":[4,43,68],"approximate":[5],"a":[6,107,121],"target":[7],"waveform":[8],"by":[9],"parametric":[10,57],"audio":[11],"synthesis.":[12],"Deep":[13],"neural":[14],"networks":[15],"have":[16],"achieved":[17],"promising":[18],"results":[19],"in":[20,55,84,97,176],"sustained":[22],"harmonic":[23],"tones.":[24],"However,":[25],"the":[26,44,56,70,78,85,134],"task":[27],"is":[28,62,92,106,133],"more":[29],"challenging":[30],"when":[31],"targets":[32],"are":[33],"nonstationary":[34],"and":[35,64,95,113,158],"inharmonic,":[36],"e.g.,":[37],"percussion.":[38],"We":[39,149,167],"attribute":[40],"this":[41,125],"problem":[42],"inadequacy":[45],"of":[46,74,110,138],"loss":[47,105,130,140,180],"function.":[48],"On":[49,77],"one":[50],"hand,":[51,80],"mean":[52,81],"square":[53,82],"error":[54,83],"domain,":[58,87],"known":[59,88],"as":[60,89,143,145,156,164],"\"P-loss\",":[61],"simple":[63],"fast":[65,144],"but":[66],"fails":[67],"accommodate":[69],"differing":[71],"perceptual":[72],"significance":[73],"each":[75],"parameter.":[76],"other":[79,179],"spectrotemporal":[86],"\"spectral":[90],"loss\",":[91],"perceptually":[93],"motivated":[94],"serves":[96],"differentiable":[98],"digital":[99],"signal":[100],"processing":[101],"(DDSP).":[102],"Yet,":[103],"spectral":[104,139,165],"poor":[108],"predictor":[109],"pitch":[111],"intervals":[112],"its":[114,169],"gradient":[115],"may":[116],"be":[117],"computationally":[118],"expensive;":[119],"hence":[120],"slow":[122],"convergence.":[123],"Against":[124],"conundrum,":[126],"we":[127],"present":[128],"Perceptual-Neural-Physical":[129],"(PNP).":[131],"PNP":[132,151],"optimal":[135],"quadratic":[136],"approximation":[137],"while":[141],"being":[142],"P-loss":[146],"during":[147],"training.":[148],"instantiate":[150],"with":[152,178],"physical":[153],"modeling":[154],"synthesis":[155],"decoder":[157],"joint":[159],"time\u2013frequency":[160],"scattering":[161],"transform":[162],"(JTFS)":[163],"representation.":[166],"demonstrate":[168],"potential":[170],"on":[171],"synthetic":[173],"drum":[174],"sounds":[175],"comparison":[177],"functions.":[181]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-12T08:34:05.389933","created_date":"2025-10-10T00:00:00"}
