{"id":"https://openalex.org/W4416250896","doi":"https://doi.org/10.1109/waspaa66052.2025.11230982","title":"ReverbMiipher: Generative Speech Restoration meets Reverberation Characteristics Controllability","display_name":"ReverbMiipher: Generative Speech Restoration meets Reverberation Characteristics Controllability","publication_year":2025,"publication_date":"2025-10-12","ids":{"openalex":"https://openalex.org/W4416250896","doi":"https://doi.org/10.1109/waspaa66052.2025.11230982"},"language":null,"primary_location":{"id":"doi:10.1109/waspaa66052.2025.11230982","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa66052.2025.11230982","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":"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/A5068962900","display_name":"Wataru Nakata","orcid":"https://orcid.org/0000-0003-3953-6534"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wataru Nakata","raw_affiliation_strings":["Google DeepMind,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google DeepMind,Tokyo,Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101503856","display_name":"Yuma Koizumi","orcid":"https://orcid.org/0000-0003-3645-6213"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuma Koizumi","raw_affiliation_strings":["Google DeepMind,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google DeepMind,Tokyo,Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036532214","display_name":"Shigeki Karita","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shigeki Karita","raw_affiliation_strings":["Google DeepMind,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google DeepMind,Tokyo,Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020401831","display_name":"Robin Scheibler","orcid":"https://orcid.org/0000-0002-5205-8365"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Robin Scheibler","raw_affiliation_strings":["Google DeepMind,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google DeepMind,Tokyo,Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114246027","display_name":"Haruko Ishikawa","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haruko Ishikawa","raw_affiliation_strings":["Google DeepMind,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google DeepMind,Tokyo,Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112684044","display_name":"Adriana Guevara\u2010Rukoz","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Adriana Guevara-Rukoz","raw_affiliation_strings":["Google,Zurich,Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google,Zurich,Switzerland","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003420204","display_name":"Heiga Zen","orcid":"https://orcid.org/0000-0002-8959-5471"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Heiga Zen","raw_affiliation_strings":["Google DeepMind,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google DeepMind,Tokyo,Japan","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049614700","display_name":"Michiel Bacchiani","orcid":"https://orcid.org/0000-0003-4527-0197"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michiel Bacchiani","raw_affiliation_strings":["Google DeepMind,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google DeepMind,Tokyo,Japan","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"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":0.9828000068664551,"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":0.9828000068664551,"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":0.006800000090152025,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.0031999999191612005,"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/reverberation","display_name":"Reverberation","score":0.942300021648407},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6126999855041504},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.5054000020027161},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4611000120639801},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.427700012922287},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.3853999972343445},{"id":"https://openalex.org/keywords/controllability","display_name":"Controllability","score":0.38370001316070557},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.37869998812675476},{"id":"https://openalex.org/keywords/impulse-response","display_name":"Impulse response","score":0.3752000033855438},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36629998683929443}],"concepts":[{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.942300021648407},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7245000004768372},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7032999992370605},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6126999855041504},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.5054000020027161},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4611000120639801},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.427700012922287},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41130000352859497},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.3853999972343445},{"id":"https://openalex.org/C48209547","wikidata":"https://www.wikidata.org/wiki/Q1331104","display_name":"Controllability","level":2,"score":0.38370001316070557},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.37869998812675476},{"id":"https://openalex.org/C72279823","wikidata":"https://www.wikidata.org/wiki/Q1139726","display_name":"Impulse response","level":2,"score":0.3752000033855438},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36629998683929443},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.3571999967098236},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.35440000891685486},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3434999883174896},{"id":"https://openalex.org/C70836080","wikidata":"https://www.wikidata.org/wiki/Q837940","display_name":"Impulse (physics)","level":2,"score":0.3257000148296356},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.32100000977516174},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.3206000030040741},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.31940001249313354},{"id":"https://openalex.org/C137800194","wikidata":"https://www.wikidata.org/wiki/Q11713455","display_name":"Interpolation (computer graphics)","level":3,"score":0.31610000133514404},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3009999990463257},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3001999855041504},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.2978000044822693},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.2939999997615814},{"id":"https://openalex.org/C2780909371","wikidata":"https://www.wikidata.org/wiki/Q4801092","display_name":"Artificial noise","level":4,"score":0.2809999883174896},{"id":"https://openalex.org/C52421305","wikidata":"https://www.wikidata.org/wiki/Q1151499","display_name":"Particle filter","level":3,"score":0.27649998664855957},{"id":"https://openalex.org/C24574437","wikidata":"https://www.wikidata.org/wiki/Q7135228","display_name":"Parametric model","level":3,"score":0.2615000009536743},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.2612999975681305},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.25839999318122864},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.25189998745918274},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/waspaa66052.2025.11230982","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa66052.2025.11230982","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W1517841224","https://openalex.org/W1646670924","https://openalex.org/W1989314204","https://openalex.org/W2107740512","https://openalex.org/W2107860279","https://openalex.org/W2117678320","https://openalex.org/W2144786298","https://openalex.org/W2164502538","https://openalex.org/W2555915854","https://openalex.org/W2622227326","https://openalex.org/W2747732471","https://openalex.org/W2747976101","https://openalex.org/W2763188033","https://openalex.org/W2962866211","https://openalex.org/W2972541922","https://openalex.org/W2998498479","https://openalex.org/W3001387854","https://openalex.org/W3043119899","https://openalex.org/W3097777922","https://openalex.org/W3097930518","https://openalex.org/W3178031393","https://openalex.org/W3198454118","https://openalex.org/W4200483526","https://openalex.org/W4221161734","https://openalex.org/W4224133928","https://openalex.org/W4232954285","https://openalex.org/W4248855359","https://openalex.org/W4251733995","https://openalex.org/W4296927107","https://openalex.org/W4312933868","https://openalex.org/W4319862245","https://openalex.org/W4380434618","https://openalex.org/W4381786045","https://openalex.org/W4385822808","https://openalex.org/W4386764866","https://openalex.org/W4390971714","https://openalex.org/W4402111490","https://openalex.org/W4402112296","https://openalex.org/W4402112435","https://openalex.org/W4402115964","https://openalex.org/W4403990754","https://openalex.org/W4405974256","https://openalex.org/W4408352314","https://openalex.org/W4408354662","https://openalex.org/W4412945293","https://openalex.org/W4416248326"],"related_works":[],"abstract_inverted_index":{"Reverberation":[0],"encodes":[1,82],"spatial":[2],"information":[3],"regarding":[4],"the":[5,60,67,79,129],"acoustic":[6],"source":[7],"environment,":[8],"yet":[9],"traditional":[10],"Speech":[11],"Restoration":[12],"(SR)":[13],"usually":[14],"completely":[15],"removes":[16,124],"reverberation.":[17,38],"We":[18,140],"propose":[19],"ReverbMiipher,":[20],"an":[21],"SR":[22,132],"model":[23],"extending":[24],"parametric":[25],"resynthesis":[26],"framework,":[27],"designed":[28],"to":[29,44,58,145],"denoise":[30],"speech":[31,61,88],"while":[32,65],"preserving":[33],"and":[34,116,127,133],"enabling":[35],"control":[36,95],"over":[37],"ReverbMiipher":[39,120],"incorporates":[40],"a":[41,46,56,112],"dedicated":[42],"ReverbEncoder":[43],"extract":[45],"reverb":[47],"feature":[48,54,80,151],"vector":[49],"from":[50,86,106,111],"noisy":[51],"input.":[52],"This":[53,90],"conditions":[55],"vocoder":[57],"reconstruct":[59],"signal,":[62],"removing":[63],"noise":[64],"retaining":[66],"original":[68],"reverberation":[69,94,148],"characteristics.":[70],"A":[71],"stochastic":[72],"zero-vector":[73],"replacement":[74,103],"strategy":[75],"during":[76],"training":[77],"ensures":[78],"specifically":[81],"reverberation,":[83,123],"disentangling":[84],"it":[85],"other":[87,107,125],"attributes.":[89],"learned":[91],"representation":[92],"facilitates":[93],"via":[96],"techniques":[97],"such":[98],"as":[99],"interpolation":[100],"between":[101],"features,":[102],"with":[104],"features":[105],"utterances,":[108],"or":[109],"sampling":[110],"latent":[113],"space.":[114],"Objective":[115],"subjective":[117],"evaluations":[118],"confirm":[119],"effectively":[121],"preserves":[122],"artifacts,":[126],"outperforms":[128],"conventional":[130],"two-stage":[131],"convolving":[134],"simulated":[135],"room":[136],"impulse":[137],"response":[138],"approach.":[139],"further":[141],"demonstrate":[142],"its":[143],"ability":[144],"generate":[146],"novel":[147],"effects":[149],"through":[150],"manipulation.":[152]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-14T00:00:00"}