{"id":"https://openalex.org/W4323322934","doi":"https://doi.org/10.1145/3544548.3580706","title":"WESPER: Zero-shot and Realtime Whisper to Normal Voice Conversion for Whisper-based Speech Interactions","display_name":"WESPER: Zero-shot and Realtime Whisper to Normal Voice Conversion for Whisper-based Speech Interactions","publication_year":2023,"publication_date":"2023-04-19","ids":{"openalex":"https://openalex.org/W4323322934","doi":"https://doi.org/10.1145/3544548.3580706"},"language":"en","primary_location":{"id":"doi:10.1145/3544548.3580706","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3544548.3580706","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3544548.3580706","source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3544548.3580706","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082649952","display_name":"Jun Rekimoto","orcid":"https://orcid.org/0000-0002-3629-2514"},"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/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Jun Rekimoto","raw_affiliation_strings":["The University of Tokyo, Japan and Sony CSL Kyoto, Japan"],"raw_orcid":"https://orcid.org/0000-0002-3629-2514","affiliations":[{"raw_affiliation_string":"The University of Tokyo, Japan and Sony CSL Kyoto, Japan","institution_ids":["https://openalex.org/I4210122684","https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5082649952"],"corresponding_institution_ids":["https://openalex.org/I4210122684","https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":22,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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/T10860","display_name":"Speech and Audio Processing","score":0.9995999932289124,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9941999912261963,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.795167088508606},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7927562594413757},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.635040283203125},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.5780001878738403},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5777747631072998},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5096831321716309},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5031465888023376},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.4247402846813202},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4228888750076294},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.416980504989624},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4120536744594574},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2632737457752228}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.795167088508606},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7927562594413757},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.635040283203125},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.5780001878738403},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5777747631072998},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5096831321716309},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5031465888023376},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.4247402846813202},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4228888750076294},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.416980504989624},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4120536744594574},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2632737457752228},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3544548.3580706","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3544548.3580706","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3544548.3580706","source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2303.01639","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2303.01639","pdf_url":"https://arxiv.org/pdf/2303.01639","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3544548.3580706","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3544548.3580706","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3544548.3580706","source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5699999928474426}],"awards":[{"id":"https://openalex.org/G6744148916","display_name":null,"funder_award_id":"JPMJCR17A3","funder_id":"https://openalex.org/F4320338075","funder_display_name":"Core Research for Evolutional Science and Technology"}],"funders":[{"id":"https://openalex.org/F4320322832","display_name":"University of Tokyo","ror":"https://ror.org/057zh3y96"},{"id":"https://openalex.org/F4320335839","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349"},{"id":"https://openalex.org/F4320338075","display_name":"Core Research for Evolutional Science and Technology","ror":"https://ror.org/00097mb19"},{"id":"https://openalex.org/F4320338247","display_name":"Moonshot Research and Development Program","ror":null}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4323322934.pdf"},"referenced_works_count":51,"referenced_works":["https://openalex.org/W96541173","https://openalex.org/W110017167","https://openalex.org/W1494198834","https://openalex.org/W1904948456","https://openalex.org/W1969139822","https://openalex.org/W2008120082","https://openalex.org/W2083932711","https://openalex.org/W2121895216","https://openalex.org/W2127141656","https://openalex.org/W2302259492","https://openalex.org/W2499854530","https://openalex.org/W2516855573","https://openalex.org/W2518172956","https://openalex.org/W2604184139","https://openalex.org/W2737426676","https://openalex.org/W2747874407","https://openalex.org/W2768731046","https://openalex.org/W2774848319","https://openalex.org/W2786672974","https://openalex.org/W2793257307","https://openalex.org/W2805669069","https://openalex.org/W2896457183","https://openalex.org/W2896622783","https://openalex.org/W2897318954","https://openalex.org/W2928664166","https://openalex.org/W2941048526","https://openalex.org/W2945478979","https://openalex.org/W3015465870","https://openalex.org/W3036601975","https://openalex.org/W3092028330","https://openalex.org/W3102538494","https://openalex.org/W3105124182","https://openalex.org/W3113594615","https://openalex.org/W3130016944","https://openalex.org/W3154296827","https://openalex.org/W3161704465","https://openalex.org/W3197642003","https://openalex.org/W3208900277","https://openalex.org/W3209059054","https://openalex.org/W3210530853","https://openalex.org/W4283031696","https://openalex.org/W4287752738","https://openalex.org/W4288079605","https://openalex.org/W4289666046","https://openalex.org/W4290607240","https://openalex.org/W4293239651","https://openalex.org/W4297677272","https://openalex.org/W4307475373","https://openalex.org/W4307536511","https://openalex.org/W4394671563","https://openalex.org/W6967178875"],"related_works":["https://openalex.org/W2294333436","https://openalex.org/W2653598178","https://openalex.org/W2747006289","https://openalex.org/W231741463","https://openalex.org/W4200068392","https://openalex.org/W2072884270","https://openalex.org/W4252682934","https://openalex.org/W2772686614","https://openalex.org/W2356426224","https://openalex.org/W2734909224"],"abstract_inverted_index":{"Recognizing":[0],"whispered":[1,20,83,121,154],"speech":[2,8,13,21,37,51,55,60,66,86,99,116,132,136,163,170,180,189,212,217],"and":[3,84,122,125,146,155,172],"converting":[4],"it":[5,30,173],"to":[6,45,49,119,210],"normal":[7,28,50,85,123,156],"creates":[9],"many":[10],"possibilities":[11],"for":[12,57,153,214],"interaction.":[14],"Because":[15],"the":[16,54,134,139,185,188,204,207],"sound":[17],"pressure":[18],"of":[19,27,80,82,108,187,206],"is":[22,144],"significantly":[23],"lower":[24],"than":[25],"that":[26,184],"speech,":[29,124],"can":[31,161],"be":[32],"used":[33],"as":[34],"a":[35,95,109,126,150,192],"semi-silent":[36],"interaction":[38],"in":[39,164],"public":[40],"places":[41],"without":[42],"being":[43],"audible":[44],"others.":[46],"Converting":[47],"whispers":[48],"also":[52],"improves":[53],"quality":[56,74,186],"people":[58,215],"with":[59,216],"or":[61,75,218],"hearing":[62,219],"impairments.":[63],"However,":[64],"conventional":[65],"conversion":[67,73,100,143],"techniques":[68],"do":[69],"not":[70,148],"provide":[71],"sufficient":[72],"require":[76,149],"speaker-dependent":[77],"datasets":[78],"consisting":[79],"pairs":[81],"utterances.":[87],"To":[88],"address":[89],"these":[90],"problems,":[91],"we":[92,202],"propose":[93],"WESPER,":[94],"zero-shot,":[96],"real-time":[97],"whisper-to-normal":[98],"mechanism":[101],"based":[102],"on":[103],"self-supervised":[104],"learning.":[105],"WESPER":[106],"consists":[107],"speech-to-unit":[110],"(STU)":[111],"encoder,":[112],"which":[113,130],"generates":[114],"hidden":[115],"units":[117],"common":[118],"both":[120],"unit-to-speech":[127],"(UTS)":[128],"decoder,":[129],"reconstructs":[131],"from":[133,169,191],"encoded":[135],"units.":[137],"Unlike":[138],"existing":[140],"methods,":[141],"this":[142],"user-independent":[145],"does":[147],"paired":[151],"dataset":[152],"speech.":[157],"The":[158],"UTS":[159],"decoder":[160],"reconstruct":[162],"any":[165],"target":[166,178],"speaker\u2019s":[167,179],"voice":[168],"units,":[171],"requires":[174],"only":[175],"an":[176],"unlabeled":[177],"data.":[181],"We":[182],"confirmed":[183,203],"converted":[190],"whisper":[193],"was":[194],"improved":[195],"while":[196],"preserving":[197],"its":[198],"natural":[199],"prosody.":[200],"Additionally,":[201],"effectiveness":[205],"proposed":[208],"approach":[209],"perform":[211],"reconstruction":[213],"disabilities.":[220]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2023-03-07T00:00:00"}