{"id":"https://openalex.org/W4372259754","doi":"https://doi.org/10.1109/icassp49357.2023.10094854","title":"Optimal Transport in Diffusion Modeling for Conversion Tasks in Audio Domain","display_name":"Optimal Transport in Diffusion Modeling for Conversion Tasks in Audio Domain","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372259754","doi":"https://doi.org/10.1109/icassp49357.2023.10094854"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10094854","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094854","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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079224579","display_name":"Popov Va","orcid":"https://orcid.org/0000-0003-1395-2951"},"institutions":[{"id":"https://openalex.org/I4210159102","display_name":"Huawei Technologies (Sweden)","ror":"https://ror.org/0500fyd17","country_code":"SE","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210159102"]}],"countries":["SE"],"is_corresponding":true,"raw_author_name":"Vadim Popov","raw_affiliation_strings":["Huawei Noah’s Ark Lab"],"affiliations":[{"raw_affiliation_string":"Huawei Noah’s Ark Lab","institution_ids":["https://openalex.org/I4210159102"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068909795","display_name":"Amantur Amatov","orcid":null},"institutions":[{"id":"https://openalex.org/I4210159102","display_name":"Huawei Technologies (Sweden)","ror":"https://ror.org/0500fyd17","country_code":"SE","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210159102"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Amantur Amatov","raw_affiliation_strings":["Huawei Noah’s Ark Lab"],"affiliations":[{"raw_affiliation_string":"Huawei Noah’s Ark Lab","institution_ids":["https://openalex.org/I4210159102"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034257289","display_name":"Mikhail Kudinov","orcid":"https://orcid.org/0000-0002-8555-4891"},"institutions":[{"id":"https://openalex.org/I4210159102","display_name":"Huawei Technologies (Sweden)","ror":"https://ror.org/0500fyd17","country_code":"SE","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210159102"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Mikhail Kudinov","raw_affiliation_strings":["Huawei Noah’s Ark Lab"],"affiliations":[{"raw_affiliation_string":"Huawei Noah’s Ark Lab","institution_ids":["https://openalex.org/I4210159102"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073461297","display_name":"Vladimir Gogoryan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210159102","display_name":"Huawei Technologies (Sweden)","ror":"https://ror.org/0500fyd17","country_code":"SE","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210159102"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Vladimir Gogoryan","raw_affiliation_strings":["Huawei Noah’s Ark Lab"],"affiliations":[{"raw_affiliation_string":"Huawei Noah’s Ark Lab","institution_ids":["https://openalex.org/I4210159102"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025256499","display_name":"Tasnima Sadekova","orcid":null},"institutions":[{"id":"https://openalex.org/I4210159102","display_name":"Huawei Technologies (Sweden)","ror":"https://ror.org/0500fyd17","country_code":"SE","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210159102"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Tasnima Sadekova","raw_affiliation_strings":["Huawei Noah’s Ark Lab"],"affiliations":[{"raw_affiliation_string":"Huawei Noah’s Ark Lab","institution_ids":["https://openalex.org/I4210159102"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026972667","display_name":"Ivan Vovk","orcid":null},"institutions":[{"id":"https://openalex.org/I4210159102","display_name":"Huawei Technologies (Sweden)","ror":"https://ror.org/0500fyd17","country_code":"SE","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210159102"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Ivan Vovk","raw_affiliation_strings":["Huawei Noah’s Ark Lab"],"affiliations":[{"raw_affiliation_string":"Huawei Noah’s Ark Lab","institution_ids":["https://openalex.org/I4210159102"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5079224579"],"corresponding_institution_ids":["https://openalex.org/I4210159102"],"apc_list":null,"apc_paid":null,"fwci":0.6113,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.63255086,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"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/T11309","display_name":"Music and Audio Processing","score":0.9983999729156494,"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":0.9983999729156494,"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":0.9940999746322632,"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"}},{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.989300012588501,"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/timbre","display_name":"Timbre","score":0.8252111077308655},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7807140946388245},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.6486420035362244},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4529397487640381},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.38249772787094116},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3408307135105133},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2704426050186157}],"concepts":[{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.8252111077308655},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7807140946388245},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.6486420035362244},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4529397487640381},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.38249772787094116},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3408307135105133},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2704426050186157},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10094854","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094854","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2129069237","https://openalex.org/W2962866891","https://openalex.org/W2963889406","https://openalex.org/W2972359262","https://openalex.org/W2998572311","https://openalex.org/W3092028330","https://openalex.org/W3110257065","https://openalex.org/W3121370741","https://openalex.org/W3162926177","https://openalex.org/W3168160162","https://openalex.org/W3197659778","https://openalex.org/W3204602440","https://openalex.org/W4221139906","https://openalex.org/W4226334413","https://openalex.org/W4281908781","https://openalex.org/W4287250916","https://openalex.org/W4287599852","https://openalex.org/W4297786137","https://openalex.org/W4298187450","https://openalex.org/W4310695675","https://openalex.org/W6639824700","https://openalex.org/W6748253163","https://openalex.org/W6757028937","https://openalex.org/W6772349387","https://openalex.org/W6783713337","https://openalex.org/W6783867762","https://openalex.org/W6784864884","https://openalex.org/W6786375611","https://openalex.org/W6793578827","https://openalex.org/W6795288823","https://openalex.org/W6802527329","https://openalex.org/W6810093873","https://openalex.org/W6810793953","https://openalex.org/W6811034091","https://openalex.org/W6843813467"],"related_works":["https://openalex.org/W2406877384","https://openalex.org/W2595839522","https://openalex.org/W2124576126","https://openalex.org/W2138455584","https://openalex.org/W1984264321","https://openalex.org/W3109975354","https://openalex.org/W2357614930","https://openalex.org/W2008642382","https://openalex.org/W1541822869","https://openalex.org/W2037604299"],"abstract_inverted_index":{"Diffusion":[0],"models":[1,28],"have":[2],"recently":[3],"become":[4],"a":[5,36,70,74],"popular":[6],"generative":[7],"modeling":[8,67],"framework":[9],"in":[10,148],"various":[11],"domains":[12],"because":[13],"of":[14,63,73,115,138,150],"their":[15],"high-quality":[16],"sampling":[17],"capabilities.":[18],"Lately,":[19],"it":[20],"has":[21],"been":[22],"hypothesized":[23],"that":[24,57,105],"optimally":[25],"trained":[26],"diffusion":[27,66,79,135],"supplied":[29],"with":[30,145],"specific":[31],"differential":[32],"equation":[33],"solvers":[34],"provide":[35],"solution":[37],"to":[38,111],"the":[39,44,48,59,77,94,99,106,113,116,122,133,151],"optimal":[40,60,107],"transport":[41,61,108],"problem":[42],"between":[43],"data":[45],"distribution":[46],"and":[47,90,103],"prior":[49],"distribution.":[50],"In":[51,93],"this":[52],"paper,":[53],"we":[54,96,131],"empirically":[55],"show":[56],"applying":[58],"point":[62],"view":[64],"on":[65,143],"allows":[68],"making":[69],"good":[71],"choice":[72],"noise":[75],"sample":[76],"reverse":[78],"starts":[80],"generating":[81],"from.":[82],"We":[83],"consider":[84],"two":[85],"audio-related":[86],"tasks:":[87],"voice":[88],"conversion":[89],"timbre":[91,129,140],"transfer.":[92],"former,":[95],"improve":[97],"upon":[98],"recent":[100],"state-of-the-art":[101],"model":[102,125,136],"demonstrate":[104],"helps":[109],"us":[110],"keep":[112],"prosody":[114],"source":[117],"utterances":[118],"significantly":[119],"better":[120],"than":[121],"vanilla":[123],"diffusion-based":[124],"does.":[126],"As":[127],"for":[128],"transfer,":[130],"propose":[132],"novel":[134],"capable":[137],"many-to-many":[139],"transfer":[141],"performing":[142],"par":[144],"common":[146],"algorithms":[147],"terms":[149],"overall":[152],"music":[153],"quality.":[154]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}