{"id":"https://openalex.org/W4416250962","doi":"https://doi.org/10.1109/waspaa66052.2025.11230991","title":"Conditioned Wave-U-Net for Acoustic Matching of Speech in Shared XR Environments","display_name":"Conditioned Wave-U-Net for Acoustic Matching of Speech in Shared XR Environments","publication_year":2025,"publication_date":"2025-10-12","ids":{"openalex":"https://openalex.org/W4416250962","doi":"https://doi.org/10.1109/waspaa66052.2025.11230991"},"language":null,"primary_location":{"id":"doi:10.1109/waspaa66052.2025.11230991","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa66052.2025.11230991","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","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/A5088054835","display_name":"Joanna Luberadzka","orcid":null},"institutions":[{"id":"https://openalex.org/I4210087295","display_name":"Centre Tecnologic de Telecomunicacions de Catalunya","ror":"https://ror.org/001cwea56","country_code":"ES","type":"nonprofit","lineage":["https://openalex.org/I4210087295","https://openalex.org/I4387153040"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Joanna Luberadzka","raw_affiliation_strings":["Centre Tecn&#x00F2;logic de Catalunya, Tecnologies Multim&#x00E8;dia,Eurecat,Barcelona"],"affiliations":[{"raw_affiliation_string":"Centre Tecn&#x00F2;logic de Catalunya, Tecnologies Multim&#x00E8;dia,Eurecat,Barcelona","institution_ids":["https://openalex.org/I4210087295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020961604","display_name":"Enric Gus\u00f3","orcid":"https://orcid.org/0009-0009-5222-7702"},"institutions":[{"id":"https://openalex.org/I4210087295","display_name":"Centre Tecnologic de Telecomunicacions de Catalunya","ror":"https://ror.org/001cwea56","country_code":"ES","type":"nonprofit","lineage":["https://openalex.org/I4210087295","https://openalex.org/I4387153040"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Enric Gus\u00f3","raw_affiliation_strings":["Centre Tecn&#x00F2;logic de Catalunya, Tecnologies Multim&#x00E8;dia,Eurecat,Barcelona"],"affiliations":[{"raw_affiliation_string":"Centre Tecn&#x00F2;logic de Catalunya, Tecnologies Multim&#x00E8;dia,Eurecat,Barcelona","institution_ids":["https://openalex.org/I4210087295"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071824067","display_name":"Umut Sayin","orcid":null},"institutions":[{"id":"https://openalex.org/I4210087295","display_name":"Centre Tecnologic de Telecomunicacions de Catalunya","ror":"https://ror.org/001cwea56","country_code":"ES","type":"nonprofit","lineage":["https://openalex.org/I4210087295","https://openalex.org/I4387153040"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Umut Sayin","raw_affiliation_strings":["Centre Tecn&#x00F2;logic de Catalunya, Tecnologies Multim&#x00E8;dia,Eurecat,Barcelona"],"affiliations":[{"raw_affiliation_string":"Centre Tecn&#x00F2;logic de Catalunya, Tecnologies Multim&#x00E8;dia,Eurecat,Barcelona","institution_ids":["https://openalex.org/I4210087295"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5088054835"],"corresponding_institution_ids":["https://openalex.org/I4210087295"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.45336692,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"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":0.5303000211715698,"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":0.5303000211715698,"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":0.1412000060081482,"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":0.12620000541210175,"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/convolution","display_name":"Convolution (computer science)","score":0.5537999868392944},{"id":"https://openalex.org/keywords/impulse-response","display_name":"Impulse response","score":0.536300003528595},{"id":"https://openalex.org/keywords/impulse","display_name":"Impulse (physics)","score":0.4878999888896942},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4779999852180481},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.4336000084877014},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.39309999346733093},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.3774000108242035}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6929000020027161},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.5537999868392944},{"id":"https://openalex.org/C72279823","wikidata":"https://www.wikidata.org/wiki/Q1139726","display_name":"Impulse response","level":2,"score":0.536300003528595},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5288000106811523},{"id":"https://openalex.org/C70836080","wikidata":"https://www.wikidata.org/wiki/Q837940","display_name":"Impulse (physics)","level":2,"score":0.4878999888896942},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4779999852180481},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.4336000084877014},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.42559999227523804},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.39309999346733093},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.3774000108242035},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.3244999945163727},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.3005000054836273},{"id":"https://openalex.org/C178432105","wikidata":"https://www.wikidata.org/wiki/Q2182127","display_name":"Room acoustics","level":3,"score":0.29660001397132874},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29330000281333923},{"id":"https://openalex.org/C198386975","wikidata":"https://www.wikidata.org/wiki/Q117785","display_name":"Finite impulse response","level":2,"score":0.2928999960422516},{"id":"https://openalex.org/C157138929","wikidata":"https://www.wikidata.org/wiki/Q570","display_name":"Loudspeaker","level":2,"score":0.2851000130176544},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.2615000009536743},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.25119999051094055},{"id":"https://openalex.org/C38956757","wikidata":"https://www.wikidata.org/wiki/Q716215","display_name":"Audio feedback","level":2,"score":0.25099998712539673}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/waspaa66052.2025.11230991","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa66052.2025.11230991","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","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":31,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W1982217276","https://openalex.org/W1998648683","https://openalex.org/W2014768838","https://openalex.org/W2107860279","https://openalex.org/W2121122425","https://openalex.org/W2125114513","https://openalex.org/W2141998673","https://openalex.org/W2410879554","https://openalex.org/W2760103357","https://openalex.org/W2933224119","https://openalex.org/W2963920537","https://openalex.org/W2982059757","https://openalex.org/W3015338123","https://openalex.org/W3015676952","https://openalex.org/W3163341049","https://openalex.org/W3163735648","https://openalex.org/W3165004824","https://openalex.org/W3178031393","https://openalex.org/W3205770165","https://openalex.org/W4229049812","https://openalex.org/W4233415207","https://openalex.org/W4312779270","https://openalex.org/W4372260337","https://openalex.org/W4372270198","https://openalex.org/W4387870105","https://openalex.org/W4387938956","https://openalex.org/W4392910492","https://openalex.org/W4394595534","https://openalex.org/W4408354742","https://openalex.org/W4415799266"],"related_works":[],"abstract_inverted_index":{"Mismatch":[0],"in":[1,11,43,55],"acoustics":[2],"between":[3,90],"users":[4],"is":[5,46],"an":[6,56],"important":[7],"challenge":[8],"for":[9,65],"interaction":[10],"shared":[12],"XR":[13],"environments.":[14],"It":[15],"can":[16],"be":[17],"mitigated":[18],"through":[19],"acoustic":[20,88],"matching,":[21],"which":[22],"traditionally":[23],"involves":[24],"dereverberation":[25],"followed":[26],"by":[27,80],"convolution":[28],"with":[29,63],"a":[30,81],"room":[31],"impulse":[32],"response":[33],"(RIR)":[34],"of":[35],"the":[36,40,77,87,106],"target":[37,41],"space.":[38],"However,":[39],"RIR":[42],"such":[44],"settings":[45],"usually":[47],"unavailable.":[48],"We":[49,68,95],"propose":[50],"to":[51,72,85,108],"tackle":[52],"this":[53,74,98],"problem":[54],"end-to-end":[57],"manner":[58],"using":[59],"wave-u-net":[60],"encoder-decoder":[61],"network":[62,75],"potential":[64],"real-time":[66],"operation.":[67],"use":[69],"FiLM":[70],"layers":[71],"condition":[73],"on":[76],"embeddings":[78],"extracted":[79],"separate":[82],"reverb":[83],"encoder":[84],"match":[86],"properties":[89],"two":[91,101],"arbitrarily":[92],"chosen":[93],"signals.":[94,114],"demonstrate":[96],"that":[97],"approach":[99],"outperforms":[100],"baseline":[102],"methods":[103],"and":[104,111],"provides":[105],"flexibility":[107],"both":[109],"dereverberate":[110],"rereverberate":[112],"audio":[113]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-14T00:00:00"}
