{"id":"https://openalex.org/W4392910551","doi":"https://doi.org/10.1109/icassp48485.2024.10447011","title":"Unsupervised Harmonic Parameter Estimation Using Differentiable DSP and Spectral Optimal Transport","display_name":"Unsupervised Harmonic Parameter Estimation Using Differentiable DSP and Spectral Optimal Transport","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392910551","doi":"https://doi.org/10.1109/icassp48485.2024.10447011"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447011","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447011","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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-04358467v3/file/ICASSP_2024_camera_ready_preprint_v3.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5083296120","display_name":"Bernardo Torres","orcid":null},"institutions":[{"id":"https://openalex.org/I12356871","display_name":"T\u00e9l\u00e9com Paris","ror":"https://ror.org/01naq7912","country_code":"FR","type":"education","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102"]},{"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":"Bernardo Torres","raw_affiliation_strings":["LTCI, Telecom Paris, Institut Polytechnique de Paris"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LTCI, Telecom Paris, Institut Polytechnique de Paris","institution_ids":["https://openalex.org/I4210165912","https://openalex.org/I12356871"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063097936","display_name":"Geoffroy Peeters","orcid":"https://orcid.org/0000-0001-5255-3019"},"institutions":[{"id":"https://openalex.org/I12356871","display_name":"T\u00e9l\u00e9com Paris","ror":"https://ror.org/01naq7912","country_code":"FR","type":"education","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102"]},{"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, Telecom Paris, Institut Polytechnique de Paris"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LTCI, Telecom Paris, Institut Polytechnique de Paris","institution_ids":["https://openalex.org/I4210165912","https://openalex.org/I12356871"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055423112","display_name":"Ga\u00ebl Richard","orcid":"https://orcid.org/0000-0002-4960-0010"},"institutions":[{"id":"https://openalex.org/I12356871","display_name":"T\u00e9l\u00e9com Paris","ror":"https://ror.org/01naq7912","country_code":"FR","type":"education","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102"]},{"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, Telecom Paris, Institut Polytechnique de Paris"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LTCI, Telecom Paris, Institut Polytechnique de Paris","institution_ids":["https://openalex.org/I4210165912","https://openalex.org/I12356871"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1004,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.75910269,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1176","last_page":"1180"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14225","display_name":"Advanced Sensor and Control Systems","score":0.7439000010490417,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T14225","display_name":"Advanced Sensor and Control Systems","score":0.7439000010490417,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"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/T11372","display_name":"Hydraulic and Pneumatic Systems","score":0.7360000014305115,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical Engineering"},"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/T14156","display_name":"Engineering Applied Research","score":0.7188000082969666,"subfield":{"id":"https://openalex.org/subfields/2205","display_name":"Civil and Structural Engineering"},"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/differentiable-function","display_name":"Differentiable function","score":0.7518394589424133},{"id":"https://openalex.org/keywords/digital-signal-processing","display_name":"Digital signal processing","score":0.618414580821991},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5100067853927612},{"id":"https://openalex.org/keywords/spectral-density-estimation","display_name":"Spectral density estimation","score":0.5081758499145508},{"id":"https://openalex.org/keywords/harmonic","display_name":"Harmonic","score":0.5046318769454956},{"id":"https://openalex.org/keywords/harmonic-analysis","display_name":"Harmonic analysis","score":0.49235665798187256},{"id":"https://openalex.org/keywords/estimation-theory","display_name":"Estimation theory","score":0.45346346497535706},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3659316301345825},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.33726751804351807},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.3348225951194763},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2943209409713745},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.1434290111064911},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.13975325226783752},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.12948688864707947},{"id":"https://openalex.org/keywords/fourier-transform","display_name":"Fourier transform","score":0.08968585729598999}],"concepts":[{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.7518394589424133},{"id":"https://openalex.org/C84462506","wikidata":"https://www.wikidata.org/wiki/Q173142","display_name":"Digital signal processing","level":2,"score":0.618414580821991},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5100067853927612},{"id":"https://openalex.org/C30049272","wikidata":"https://www.wikidata.org/wiki/Q6555326","display_name":"Spectral density estimation","level":3,"score":0.5081758499145508},{"id":"https://openalex.org/C127934551","wikidata":"https://www.wikidata.org/wiki/Q1148098","display_name":"Harmonic","level":2,"score":0.5046318769454956},{"id":"https://openalex.org/C131770355","wikidata":"https://www.wikidata.org/wiki/Q876215","display_name":"Harmonic analysis","level":2,"score":0.49235665798187256},{"id":"https://openalex.org/C167928553","wikidata":"https://www.wikidata.org/wiki/Q1376021","display_name":"Estimation theory","level":2,"score":0.45346346497535706},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3659316301345825},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.33726751804351807},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.3348225951194763},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2943209409713745},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.1434290111064911},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.13975325226783752},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.12948688864707947},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.08968585729598999},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447011","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447011","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-04358467v3","is_oa":true,"landing_page_url":"https://hal.science/hal-04358467","pdf_url":"https://hal.science/hal-04358467v3/file/ICASSP_2024_camera_ready_preprint_v3.pdf","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, Apr 2024, Seoul, South Korea. ⟨10.1109/ICASSP48485.2024.10447011⟩","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-04358467v3","is_oa":true,"landing_page_url":"https://hal.science/hal-04358467","pdf_url":"https://hal.science/hal-04358467v3/file/ICASSP_2024_camera_ready_preprint_v3.pdf","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, Apr 2024, Seoul, South Korea. ⟨10.1109/ICASSP48485.2024.10447011⟩","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[{"score":0.4300000071525574,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[{"id":"https://openalex.org/G4326088756","display_name":"Hybrid and Interpretable Deep neural audio machines","funder_award_id":"101052978","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4392910551.pdf","grobid_xml":"https://content.openalex.org/works/W4392910551.grobid-xml"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W2088432713","https://openalex.org/W2164764235","https://openalex.org/W2168103573","https://openalex.org/W2407685581","https://openalex.org/W2528314500","https://openalex.org/W2604231069","https://openalex.org/W2661419034","https://openalex.org/W2735418187","https://openalex.org/W2785932384","https://openalex.org/W2793477525","https://openalex.org/W2888169323","https://openalex.org/W2952055536","https://openalex.org/W2990440871","https://openalex.org/W3000389243","https://openalex.org/W3011176162","https://openalex.org/W3081424945","https://openalex.org/W3101009555","https://openalex.org/W3103913581","https://openalex.org/W3116275044","https://openalex.org/W4255839052","https://openalex.org/W4287245321","https://openalex.org/W4290865547","https://openalex.org/W4316660651","https://openalex.org/W4318751639","https://openalex.org/W4372348434","https://openalex.org/W4386557674","https://openalex.org/W4390745914","https://openalex.org/W6714030504","https://openalex.org/W6727623532","https://openalex.org/W6736723571","https://openalex.org/W6764491943","https://openalex.org/W6771763809","https://openalex.org/W6784488536","https://openalex.org/W6787485125","https://openalex.org/W6795007937","https://openalex.org/W6846529734","https://openalex.org/W6849446024","https://openalex.org/W6856125517"],"related_works":["https://openalex.org/W4285277090","https://openalex.org/W4327738859","https://openalex.org/W2348722996","https://openalex.org/W2334570605","https://openalex.org/W3181683615","https://openalex.org/W4286826125","https://openalex.org/W1633485514","https://openalex.org/W1604739066","https://openalex.org/W2115878407","https://openalex.org/W2284539688"],"abstract_inverted_index":{"In":[0],"neural":[1,115],"audio":[2,116],"signal":[3],"processing,":[4],"pitch":[5,19,37],"conditioning":[6],"has":[7],"been":[8],"used":[9],"to":[10,33,76],"enhance":[11],"the":[12,57,82,95],"performance":[13],"of":[14,59,87],"synthesizers.":[15],"However,":[16],"jointly":[17,80],"training":[18],"estimators":[20],"and":[21,85,93],"synthesizers":[22],"is":[23],"a":[24,46,73,90,98,106],"challenge":[25],"when":[26],"using":[27,45,89,97],"standard":[28],"audio-to-audio":[29],"reconstruction":[30],"loss,":[31],"leading":[32],"reliance":[34],"on":[35],"external":[36],"trackers.":[38],"To":[39],"address":[40],"this":[41,64],"issue,":[42],"we":[43],"propose":[44],"spectral":[47,60],"loss":[48],"function":[49],"inspired":[50],"by":[51],"optimal":[52],"transportation":[53],"theory":[54],"that":[55,71],"minimizes":[56],"displacement":[58],"energy.":[61],"We":[62,79],"validate":[63],"approach":[65,104],"through":[66],"an":[67],"unsupervised":[68,111],"autoencoding":[69],"task":[70],"fits":[72],"harmonic":[74,77,100],"template":[75],"signals.":[78],"estimate":[81],"fundamental":[83],"frequency":[84],"amplitudes":[86],"harmonics":[88],"lightweight":[91],"encoder":[92],"reconstruct":[94],"signals":[96],"differentiable":[99],"synthesizer.":[101],"The":[102],"proposed":[103],"offers":[105],"promising":[107],"direction":[108],"for":[109],"improving":[110],"parameter":[112],"estimation":[113],"in":[114],"applications.":[117]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-10-10T00:00:00"}