{"id":"https://openalex.org/W3014271217","doi":"https://doi.org/10.1109/icassp40776.2020.9054181","title":"Vapar Synth - A Variational Parametric Model for Audio Synthesis","display_name":"Vapar Synth - A Variational Parametric Model for Audio Synthesis","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3014271217","doi":"https://doi.org/10.1109/icassp40776.2020.9054181","mag":"3014271217"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054181","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054181","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":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2004.00001","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5042472021","display_name":"Krishna Subramani","orcid":null},"institutions":[{"id":"https://openalex.org/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Krishna Subramani","raw_affiliation_strings":["Indian Institute of Technology Bombay"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Bombay","institution_ids":["https://openalex.org/I162827531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084496610","display_name":"Preeti Rao","orcid":"https://orcid.org/0000-0002-2842-8450"},"institutions":[{"id":"https://openalex.org/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Preeti Rao","raw_affiliation_strings":["Indian Institute of Technology Bombay"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Bombay","institution_ids":["https://openalex.org/I162827531"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031909229","display_name":"Alexandre D'Hooge","orcid":"https://orcid.org/0000-0003-1634-3406"},"institutions":[{"id":"https://openalex.org/I29607241","display_name":"\u00c9cole Normale Sup\u00e9rieure - PSL","ror":"https://ror.org/05a0dhs15","country_code":"FR","type":"other","lineage":["https://openalex.org/I2746051580","https://openalex.org/I29607241"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Alexandre D'Hooge","raw_affiliation_strings":["ENS Paris-Saclay"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ENS Paris-Saclay","institution_ids":["https://openalex.org/I29607241"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0394,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.75673491,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"138","issue":null,"first_page":"796","last_page":"800"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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":0.9988999962806702,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9968000054359436,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/timbre","display_name":"Timbre","score":0.7802879810333252},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.7606685161590576},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.7407476305961609},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6927180886268616},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6220813989639282},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.5968012809753418},{"id":"https://openalex.org/keywords/parametric-model","display_name":"Parametric model","score":0.5576719045639038},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5283889174461365},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4623934030532837},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.44579270482063293},{"id":"https://openalex.org/keywords/nonparametric-statistics","display_name":"Nonparametric statistics","score":0.42997461557388306},{"id":"https://openalex.org/keywords/frequency-domain","display_name":"Frequency domain","score":0.4224799871444702},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3357446491718292},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.32688409090042114},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.3112031817436218},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.20206943154335022},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1779627501964569},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.13437730073928833},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.08081915974617004}],"concepts":[{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.7802879810333252},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.7606685161590576},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.7407476305961609},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6927180886268616},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6220813989639282},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.5968012809753418},{"id":"https://openalex.org/C24574437","wikidata":"https://www.wikidata.org/wiki/Q7135228","display_name":"Parametric model","level":3,"score":0.5576719045639038},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5283889174461365},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4623934030532837},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.44579270482063293},{"id":"https://openalex.org/C102366305","wikidata":"https://www.wikidata.org/wiki/Q1097688","display_name":"Nonparametric statistics","level":2,"score":0.42997461557388306},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.4224799871444702},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3357446491718292},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32688409090042114},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.3112031817436218},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.20206943154335022},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1779627501964569},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.13437730073928833},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.08081915974617004},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054181","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054181","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:2004.00001","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2004.00001","pdf_url":"https://arxiv.org/pdf/2004.00001","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":null,"raw_type":"text"},{"id":"pmh:oai:HAL:hal-05128819v1","is_oa":true,"landing_page_url":"https://hal.science/hal-05128819","pdf_url":null,"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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), May 2020, Barcelona, France. pp.796-800, &#x27E8;10.1109/ICASSP40776.2020.9054181&#x27E9;","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2004.00001","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2004.00001","pdf_url":"https://arxiv.org/pdf/2004.00001","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":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.4399999976158142}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1571477232","https://openalex.org/W1878791236","https://openalex.org/W1959608418","https://openalex.org/W1967147184","https://openalex.org/W1990611383","https://openalex.org/W2133239587","https://openalex.org/W2188365844","https://openalex.org/W2293272996","https://openalex.org/W2343253662","https://openalex.org/W2467604901","https://openalex.org/W2515020857","https://openalex.org/W2519091744","https://openalex.org/W2606176153","https://openalex.org/W2753738274","https://openalex.org/W2804967784","https://openalex.org/W2810655876","https://openalex.org/W2890043615","https://openalex.org/W2899771611","https://openalex.org/W2946149332","https://openalex.org/W2949382160","https://openalex.org/W2951004968","https://openalex.org/W2951535099","https://openalex.org/W2951928450","https://openalex.org/W3000389243","https://openalex.org/W4238189448","https://openalex.org/W6631190155","https://openalex.org/W6634367950","https://openalex.org/W6639475232","https://openalex.org/W6640963894","https://openalex.org/W6687045409","https://openalex.org/W6697058068","https://openalex.org/W6704348834","https://openalex.org/W6720208624","https://openalex.org/W6736723571","https://openalex.org/W6744627333","https://openalex.org/W6752193400","https://openalex.org/W6752996073","https://openalex.org/W6756040250","https://openalex.org/W6762849721","https://openalex.org/W6771763809"],"related_works":["https://openalex.org/W4283026649","https://openalex.org/W4378498754","https://openalex.org/W2289868279","https://openalex.org/W4254916641","https://openalex.org/W2053531689","https://openalex.org/W1546240199","https://openalex.org/W1842536210","https://openalex.org/W2109142991","https://openalex.org/W2970176078","https://openalex.org/W4231351862"],"abstract_inverted_index":{"With":[0],"the":[1,30,36,43,58,65,106],"advent":[2],"of":[3,38,57,110],"data-driven":[4],"statistical":[5],"modeling":[6],"and":[7,72,108],"abundant":[8],"computing":[9],"power,":[10],"researchers":[11],"are":[12],"turning":[13],"increasingly":[14],"to":[15,24,51,64],"deep":[16],"learning":[17],"for":[18],"audio":[19,26],"synthesis.":[20],"These":[21],"methods":[22],"try":[23],"model":[25],"signals":[27],"directly":[28,63],"in":[29],"time":[31],"or":[32],"frequency":[33],"domain.":[34],"In":[35],"interest":[37],"more":[39,49,62],"flexible":[40,114],"control":[41,115],"over":[42,116],"generated":[44],"sound,":[45],"it":[46],"could":[47],"be":[48],"useful":[50],"work":[52],"with":[53,113],"a":[54,79,85,92],"parametric":[55,94],"representation":[56],"signal":[59],"which":[60,83],"corresponds":[61],"musical":[66],"attributes":[67],"such":[68],"as":[69],"pitch,":[70],"dynamics":[71],"timbre.":[73],"We":[74,96],"present":[75],"Va-Par":[76],"Synth":[77],"-":[78],"Variational":[80],"Parametric":[81],"Synthesizer":[82],"utilizes":[84],"conditional":[86],"variational":[87],"autoencoder":[88],"(CVAE)":[89],"trained":[90],"on":[91],"suitable":[93],"representation.":[95],"demonstrate":[97],"<sup":[98],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[99],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[100],"our":[101],"proposed":[102],"model's":[103],"capabilities":[104],"via":[105],"reconstruction":[107],"generation":[109],"instrumental":[111],"tones":[112],"their":[117],"pitch.":[118]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}