{"id":"https://openalex.org/W4392910606","doi":"https://doi.org/10.1109/icassp48485.2024.10447010","title":"RVAE-EM: Generative Speech Dereverberation Based On Recurrent Variational Auto-Encoder And Convolutive Transfer Function","display_name":"RVAE-EM: Generative Speech Dereverberation Based On Recurrent Variational Auto-Encoder And Convolutive Transfer Function","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392910606","doi":"https://doi.org/10.1109/icassp48485.2024.10447010"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447010","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447010","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/A5100317564","display_name":"Pengyu Wang","orcid":"https://orcid.org/0000-0002-3704-1530"},"institutions":[{"id":"https://openalex.org/I3133055985","display_name":"Westlake University","ror":"https://ror.org/05hfa4n20","country_code":"CN","type":"education","lineage":["https://openalex.org/I3133055985"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Pengyu Wang","raw_affiliation_strings":["Zhejiang University,Hangzhou,China","School of Engineering, Westlake University, Hangzhou, China","Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University,Hangzhou,China","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"School of Engineering, Westlake University, Hangzhou, China","institution_ids":["https://openalex.org/I3133055985"]},{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100358320","display_name":"Xiaofei Li","orcid":"https://orcid.org/0000-0003-0393-9905"},"institutions":[{"id":"https://openalex.org/I3133055985","display_name":"Westlake University","ror":"https://ror.org/05hfa4n20","country_code":"CN","type":"education","lineage":["https://openalex.org/I3133055985"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaofei Li","raw_affiliation_strings":["Westlake University,School of Engineering,Hangzhou,China","School of Engineering, Westlake University, Hangzhou, China","Institute of Advanced Technology, Westlake Institute for Advanced Study, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Westlake University,School of Engineering,Hangzhou,China","institution_ids":["https://openalex.org/I3133055985"]},{"raw_affiliation_string":"School of Engineering, Westlake University, Hangzhou, China","institution_ids":["https://openalex.org/I3133055985"]},{"raw_affiliation_string":"Institute of Advanced Technology, Westlake Institute for Advanced Study, Hangzhou, China","institution_ids":["https://openalex.org/I3133055985"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100317564"],"corresponding_institution_ids":["https://openalex.org/I3133055985","https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":2.9884,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.91668898,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"496","last_page":"500"},"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9969000220298767,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9932000041007996,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7362102270126343},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.6613318920135498},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.651317834854126},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6246397495269775},{"id":"https://openalex.org/keywords/maximum-a-posteriori-estimation","display_name":"Maximum a posteriori estimation","score":0.5667071342468262},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.5449735522270203},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5334104895591736},{"id":"https://openalex.org/keywords/expectation\u2013maximization-algorithm","display_name":"Expectation\u2013maximization algorithm","score":0.50565505027771},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.48464900255203247},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4437967538833618},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.44140657782554626},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.43976569175720215},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.4300907850265503},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4230871796607971},{"id":"https://openalex.org/keywords/maximization","display_name":"Maximization","score":0.42029380798339844},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32071244716644287},{"id":"https://openalex.org/keywords/maximum-likelihood","display_name":"Maximum likelihood","score":0.2719290256500244},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1648268699645996},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.0993274450302124},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.07114553451538086}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7362102270126343},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.6613318920135498},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.651317834854126},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6246397495269775},{"id":"https://openalex.org/C9810830","wikidata":"https://www.wikidata.org/wiki/Q635384","display_name":"Maximum a posteriori estimation","level":3,"score":0.5667071342468262},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.5449735522270203},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5334104895591736},{"id":"https://openalex.org/C182081679","wikidata":"https://www.wikidata.org/wiki/Q1275153","display_name":"Expectation\u2013maximization algorithm","level":3,"score":0.50565505027771},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.48464900255203247},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4437967538833618},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.44140657782554626},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.43976569175720215},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.4300907850265503},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4230871796607971},{"id":"https://openalex.org/C2776330181","wikidata":"https://www.wikidata.org/wiki/Q18358244","display_name":"Maximization","level":2,"score":0.42029380798339844},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32071244716644287},{"id":"https://openalex.org/C49781872","wikidata":"https://www.wikidata.org/wiki/Q1045555","display_name":"Maximum likelihood","level":2,"score":0.2719290256500244},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1648268699645996},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0993274450302124},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.07114553451538086},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447010","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447010","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W1965555277","https://openalex.org/W1985690171","https://openalex.org/W2024490156","https://openalex.org/W2125114513","https://openalex.org/W2127851351","https://openalex.org/W2131968171","https://openalex.org/W2141998673","https://openalex.org/W2156676906","https://openalex.org/W2516001803","https://openalex.org/W2739296442","https://openalex.org/W2898268964","https://openalex.org/W2918296821","https://openalex.org/W2924334974","https://openalex.org/W2940385941","https://openalex.org/W3005621653","https://openalex.org/W3026111682","https://openalex.org/W3036167779","https://openalex.org/W3096159803","https://openalex.org/W3096831136","https://openalex.org/W3104196160","https://openalex.org/W3160085755","https://openalex.org/W3161480375","https://openalex.org/W3163305913","https://openalex.org/W3174264304","https://openalex.org/W4296068772","https://openalex.org/W4372263902","https://openalex.org/W4380434618","https://openalex.org/W6640963894","https://openalex.org/W6757817989","https://openalex.org/W6779823529"],"related_works":["https://openalex.org/W1783992599","https://openalex.org/W2114899076","https://openalex.org/W2045588782","https://openalex.org/W2124697778","https://openalex.org/W2135468550","https://openalex.org/W2133422797","https://openalex.org/W1571591724","https://openalex.org/W2181917637","https://openalex.org/W1591800537","https://openalex.org/W1503775322"],"abstract_inverted_index":{"In":[0,17],"indoor":[1],"scenes,":[2],"reverberation":[3],"is":[4,28,69,80],"a":[5,22,31,35,72],"crucial":[6],"factor":[7],"in":[8],"degrading":[9],"the":[10,42,53,60,63,70,84,93,111,117],"perceived":[11],"quality":[12],"and":[13,41,100],"intelligibility":[14],"of":[15,55,62,76,95],"speech.":[16,65],"this":[18],"work,":[19],"we":[20],"propose":[21],"generative":[23,113],"dereverberation":[24,108],"method.":[25],"Our":[26],"approach":[27],"based":[29],"on":[30,105],"probabilistic":[32],"model":[33],"utilizing":[34],"recurrent":[36],"variational":[37],"auto-encoder":[38],"(RVAE)":[39],"network":[40],"convolutive":[43],"transfer":[44],"function":[45],"(CTF)":[46],"approximation.":[47],"Different":[48],"from":[49],"most":[50],"previous":[51],"approaches,":[52],"output":[54],"our":[56,67],"RVAE":[57],"serves":[58],"as":[59],"prior":[61,98],"clean":[64,77],"And":[66],"target":[68],"maximum":[71],"posteriori":[73],"(MAP)":[74],"estimation":[75],"speech,":[78],"which":[79],"achieved":[81],"iteratively":[82],"through":[83],"expectation":[85],"maximization":[86],"(EM)":[87],"algorithm.":[88],"The":[89],"proposed":[90,112],"method":[91,114],"integrates":[92],"capabilities":[94],"network-based":[96],"speech":[97,107],"modelling":[99],"CTF-based":[101],"observation":[102],"modelling.":[103],"Experiments":[104],"single-channel":[106],"show":[109],"that":[110],"noticeably":[115],"outperforms":[116],"advanced":[118],"discriminative":[119],"networks.":[120]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}