{"id":"https://openalex.org/W4392910492","doi":"https://doi.org/10.1109/icassp48485.2024.10447818","title":"DiffRENT: A Diffusion Model for Recording Environment Transfer of Speech","display_name":"DiffRENT: A Diffusion Model for Recording Environment Transfer of Speech","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392910492","doi":"https://doi.org/10.1109/icassp48485.2024.10447818"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447818","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447818","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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5083693790","display_name":"Jaekwon Im","orcid":null},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Jaekwon Im","raw_affiliation_strings":["KAIST,Graduate School of Culture Technology,Republic of Korea","Graduate School of Culture Technology, KAIST, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"KAIST,Graduate School of Culture Technology,Republic of Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"Graduate School of Culture Technology, KAIST, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056437111","display_name":"Juhan Nam","orcid":"https://orcid.org/0000-0003-2664-2119"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Juhan Nam","raw_affiliation_strings":["KAIST,Graduate School of Culture Technology,Republic of Korea","Graduate School of Culture Technology, KAIST, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"KAIST,Graduate School of Culture Technology,Republic of Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"Graduate School of Culture Technology, KAIST, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5083693790"],"corresponding_institution_ids":["https://openalex.org/I157485424"],"apc_list":null,"apc_paid":null,"fwci":1.4942,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.8073031,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"7425","last_page":"7429"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9162999987602234,"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":0.9162999987602234,"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":0.9108999967575073,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.6699599623680115},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6227201819419861},{"id":"https://openalex.org/keywords/transfer","display_name":"Transfer (computing)","score":0.45035940408706665},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.41130322217941284},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.37526658177375793},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.1111510694026947}],"concepts":[{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.6699599623680115},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6227201819419861},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.45035940408706665},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.41130322217941284},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.37526658177375793},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.1111510694026947},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447818","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447818","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"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/13","display_name":"Climate action","score":0.6299999952316284}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1552314771","https://openalex.org/W1989314204","https://openalex.org/W2121388655","https://openalex.org/W2133665775","https://openalex.org/W2408467190","https://openalex.org/W2519091744","https://openalex.org/W2535255545","https://openalex.org/W2555915854","https://openalex.org/W2794506738","https://openalex.org/W2900429685","https://openalex.org/W2933224119","https://openalex.org/W3015676952","https://openalex.org/W3024869864","https://openalex.org/W3036167779","https://openalex.org/W3092028330","https://openalex.org/W3139813613","https://openalex.org/W3178031393","https://openalex.org/W3212516020","https://openalex.org/W4200483526","https://openalex.org/W4221144097","https://openalex.org/W4224133928","https://openalex.org/W4226320669","https://openalex.org/W4297841519","https://openalex.org/W4312095956","https://openalex.org/W6679045638","https://openalex.org/W6779823529","https://openalex.org/W6782288879","https://openalex.org/W6783182287","https://openalex.org/W6783867762","https://openalex.org/W6784407856","https://openalex.org/W6801426729"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"Properly":[0],"setting":[1],"up":[2],"recording":[3,46,64],"conditions,":[4],"including":[5],"microphone":[6],"type":[7],"and":[8,12,67,80,92,106,118],"placement,":[9],"room":[10],"acoustics,":[11],"ambient":[13],"noise,":[14],"is":[15],"essential":[16],"to":[17,43,103],"obtaining":[18],"the":[19,40,45,54,60,63,68,73,89,110],"desired":[20],"acoustic":[21,93],"characteristics":[22],"of":[23,48,123],"speech.":[24],"In":[25],"this":[26],"paper,":[27],"we":[28],"propose":[29],"Diff-R-EN-T,":[30],"a":[31,49],"Diffusion":[32],"model":[33,58,112,126],"for":[34],"Recording":[35],"ENvironment":[36],"Transfer":[37],"which":[38,71],"transforms":[39],"input":[41,83],"speech":[42,51,55,90],"have":[44],"conditions":[47],"reference":[50],"while":[52],"preserving":[53],"content.":[56],"Our":[57],"comprises":[59],"content":[61],"enhancer,":[62],"environment":[65],"encoder,":[66],"diffusion":[69],"decoder":[70],"generates":[72],"target":[74],"mel-spectrogram":[75],"by":[76],"utilizing":[77],"both":[78],"enhancer":[79],"encoder":[81],"as":[82],"conditions.":[84],"We":[85],"evaluate":[86],"DiffRENT":[87,100],"in":[88,116],"enhancement":[91],"matching":[94],"scenarios.":[95],"The":[96],"results":[97],"show":[98],"that":[99],"generalizes":[101],"well":[102],"unseen":[104],"environments":[105],"new":[107],"speakers.":[108],"Also,":[109],"proposed":[111,125],"achieves":[113],"superior":[114],"performances":[115],"objective":[117],"subjective":[119],"evaluation.":[120],"Sound":[121],"examples":[122],"our":[124],"are":[127],"available":[128],"online":[129],"<sup":[130],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[131],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[132],".":[133]},"counts_by_year":[{"year":2025,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}