{"id":"https://openalex.org/W4392903897","doi":"https://doi.org/10.1109/icassp48485.2024.10448429","title":"Diffusion-Based Speech Enhancement with Joint Generative and Predictive Decoders","display_name":"Diffusion-Based Speech Enhancement with Joint Generative and Predictive Decoders","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903897","doi":"https://doi.org/10.1109/icassp48485.2024.10448429"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10448429","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448429","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":"conference-paper","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/A5101860389","display_name":"Hao Shi","orcid":"https://orcid.org/0000-0001-5979-2119"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]},{"id":"https://openalex.org/I39012071","display_name":"Kyoto College of Graduate Studies for Informatics","ror":"https://ror.org/05mzj8a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I39012071"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hao Shi","raw_affiliation_strings":["Kyoto University,Graduate School of Informatics,Kyoto,Japan","Graduate School of Informatics, Kyoto University, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyoto University,Graduate School of Informatics,Kyoto,Japan","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]},{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051965288","display_name":"Kazuki Shimada","orcid":"https://orcid.org/0000-0001-5389-2346"},"institutions":[{"id":"https://openalex.org/I4210122684","display_name":"Sony Computer Science Laboratories","ror":"https://ror.org/02nc46417","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210122684"]},{"id":"https://openalex.org/I4210143797","display_name":"Sony (Japan)","ror":"https://ror.org/04wzv3n59","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210143797"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazuki Shimada","raw_affiliation_strings":["Sony AI,Tokyo,Japan","Sony AI, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sony AI,Tokyo,Japan","institution_ids":["https://openalex.org/I4210122684","https://openalex.org/I4210143797"]},{"raw_affiliation_string":"Sony AI, Tokyo, Japan","institution_ids":["https://openalex.org/I4210122684"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036188375","display_name":"Masato Hirano","orcid":"https://orcid.org/0000-0001-7219-5212"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Masato Hirano","raw_affiliation_strings":["Sony Group Corporation,Tokyo,Japan","Sony Group Corporation, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sony Group Corporation,Tokyo,Japan","institution_ids":[]},{"raw_affiliation_string":"Sony Group Corporation, Tokyo, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084845461","display_name":"Takashi Shibuya","orcid":"https://orcid.org/0000-0002-4277-0164"},"institutions":[{"id":"https://openalex.org/I4210122684","display_name":"Sony Computer Science Laboratories","ror":"https://ror.org/02nc46417","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210122684"]},{"id":"https://openalex.org/I4210143797","display_name":"Sony (Japan)","ror":"https://ror.org/04wzv3n59","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210143797"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takashi Shibuya","raw_affiliation_strings":["Sony AI,Tokyo,Japan","Sony AI, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sony AI,Tokyo,Japan","institution_ids":["https://openalex.org/I4210122684","https://openalex.org/I4210143797"]},{"raw_affiliation_string":"Sony AI, Tokyo, Japan","institution_ids":["https://openalex.org/I4210122684"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017785136","display_name":"Yuichiro Koyama","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuichiro Koyama","raw_affiliation_strings":["Sony Group Corporation,Tokyo,Japan","Sony Group Corporation, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sony Group Corporation,Tokyo,Japan","institution_ids":[]},{"raw_affiliation_string":"Sony Group Corporation, Tokyo, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040961663","display_name":"Zhi Zhong","orcid":"https://orcid.org/0000-0002-8730-5530"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhi Zhong","raw_affiliation_strings":["Sony Group Corporation,Tokyo,Japan","Sony Group Corporation, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sony Group Corporation,Tokyo,Japan","institution_ids":[]},{"raw_affiliation_string":"Sony Group Corporation, Tokyo, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104117184","display_name":"Shusuke Takahashi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shusuke Takahashi","raw_affiliation_strings":["Sony Group Corporation,Tokyo,Japan","Sony Group Corporation, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sony Group Corporation,Tokyo,Japan","institution_ids":[]},{"raw_affiliation_string":"Sony Group Corporation, Tokyo, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038044080","display_name":"Tatsuya Kawahara","orcid":"https://orcid.org/0000-0002-2686-2296"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]},{"id":"https://openalex.org/I39012071","display_name":"Kyoto College of Graduate Studies for Informatics","ror":"https://ror.org/05mzj8a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I39012071"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tatsuya Kawahara","raw_affiliation_strings":["Kyoto University,Graduate School of Informatics,Kyoto,Japan","Graduate School of Informatics, Kyoto University, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyoto University,Graduate School of Informatics,Kyoto,Japan","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]},{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088754502","display_name":"Yuki Mitsufuji","orcid":"https://orcid.org/0000-0002-6806-6140"},"institutions":[{"id":"https://openalex.org/I4210122684","display_name":"Sony Computer Science Laboratories","ror":"https://ror.org/02nc46417","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210122684"]},{"id":"https://openalex.org/I4210143797","display_name":"Sony (Japan)","ror":"https://ror.org/04wzv3n59","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210143797"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuki Mitsufuji","raw_affiliation_strings":["Sony AI,Tokyo,Japan","Sony Group Corporation, Tokyo, Japan","Sony AI, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sony AI,Tokyo,Japan","institution_ids":["https://openalex.org/I4210122684","https://openalex.org/I4210143797"]},{"raw_affiliation_string":"Sony Group Corporation, Tokyo, Japan","institution_ids":[]},{"raw_affiliation_string":"Sony AI, Tokyo, Japan","institution_ids":["https://openalex.org/I4210122684"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"12951","last_page":"12955"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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":0.9987999796867371,"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/T11309","display_name":"Music and Audio Processing","score":0.9980999827384949,"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/computer-science","display_name":"Computer science","score":0.7312380075454712},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.6584925651550293},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5297974944114685},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5178318619728088},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4931783080101013},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.43432751297950745},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4292244613170624},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.42062538862228394},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.4175947904586792},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4121486246585846},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36545515060424805}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7312380075454712},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.6584925651550293},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5297974944114685},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5178318619728088},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4931783080101013},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.43432751297950745},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4292244613170624},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.42062538862228394},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.4175947904586792},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4121486246585846},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36545515060424805},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10448429","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448429","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W1991111872","https://openalex.org/W1992475611","https://openalex.org/W2044893557","https://openalex.org/W2051057783","https://openalex.org/W2054566816","https://openalex.org/W2096779346","https://openalex.org/W2141411743","https://openalex.org/W2290318471","https://openalex.org/W2516001803","https://openalex.org/W2603567530","https://openalex.org/W2883322837","https://openalex.org/W2952218014","https://openalex.org/W2963341071","https://openalex.org/W2964058413","https://openalex.org/W2971417062","https://openalex.org/W2998161426","https://openalex.org/W3015912787","https://openalex.org/W3032514799","https://openalex.org/W3099330747","https://openalex.org/W3137249133","https://openalex.org/W3164223074","https://openalex.org/W3197912330","https://openalex.org/W3213188934","https://openalex.org/W4205683915","https://openalex.org/W4221144097","https://openalex.org/W4238187298","https://openalex.org/W4281820413","https://openalex.org/W4372266968","https://openalex.org/W4379933627","https://openalex.org/W4380434618","https://openalex.org/W4384080510","https://openalex.org/W4385822703","https://openalex.org/W4386555699","https://openalex.org/W4393689014","https://openalex.org/W4399665795","https://openalex.org/W4402111962","https://openalex.org/W6765775151","https://openalex.org/W6786375611","https://openalex.org/W6795747053","https://openalex.org/W6796411514","https://openalex.org/W6797906067","https://openalex.org/W6803519332","https://openalex.org/W6853140940","https://openalex.org/W6855309294","https://openalex.org/W6856292475"],"related_works":["https://openalex.org/W2368824897","https://openalex.org/W1508050556","https://openalex.org/W1910862367","https://openalex.org/W4365211920","https://openalex.org/W2379365082","https://openalex.org/W2370747590","https://openalex.org/W2030109976","https://openalex.org/W323006901","https://openalex.org/W2369260257","https://openalex.org/W3014948380"],"abstract_inverted_index":{"Diffusion-based":[0],"generative":[1,45,63,76,87,108],"speech":[2],"enhancement":[3],"(SE)":[4],"has":[5],"recently":[6],"received":[7],"attention,":[8],"but":[9],"reverse":[10,20],"diffusion":[11,21,124,131,177],"remains":[12],"time-consuming.":[13],"One":[14],"solution":[15],"is":[16],"to":[17,54,137,150,166],"initialize":[18],"the":[19,33,56,92,97,103,113,120,126,130,134,141,145,157],"process":[22,132],"with":[23,133,174],"enhanced":[24],"features":[25,106],"estimated":[26],"by":[27,107],"a":[28,41,70],"predictive":[29,47,50,60,78,89,110,135,163],"SE":[30,115,136,148,152,178],"system.":[31],"However,":[32],"pipeline":[34],"structure":[35],"currently":[36],"does":[37],"not":[38],"consider":[39],"for":[40],"combined":[42],"use":[43,55,74],"of":[44],"and":[46,61,77,88,109,122,140,169,180],"decoders.":[48,111],"The":[49,83],"decoder":[51],"allows":[52],"us":[53],"further":[57],"complementarity":[58],"between":[59],"diffusion-based":[62],"SE.":[64],"In":[65],"this":[66],"paper,":[67],"we":[68,101],"propose":[69],"unified":[71],"system":[72],"that":[73,161],"jointly":[75],"decoders":[79],"across":[80],"two":[81,104,114,146],"levels.":[82],"encoder":[84],"encodes":[85],"both":[86],"information":[90,164],"at":[91],"shared":[93],"encoding":[94],"level.":[95],"At":[96],"decoded":[98,105],"feature":[99],"level,":[100],"fuse":[102],"Specifically,":[112],"modules":[116],"are":[117],"fused":[118],"in":[119],"initial":[121,127],"final":[123,142],"steps:":[125],"fusion":[128,143],"initializes":[129],"improve":[138],"convergence,":[139],"combines":[144],"complementary":[147],"outputs":[149],"enhance":[151],"performance.":[153],"Experiments":[154],"conducted":[155],"on":[156],"Voice-Bank":[158],"dataset":[159],"demonstrate":[160],"incorporating":[162],"leads":[165],"faster":[167],"decoding":[168],"higher":[170],"PESQ":[171],"scores":[172],"compared":[173],"other":[175],"score-based":[176],"(StoRM":[179],"SGMSE+).":[181]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
