{"id":"https://openalex.org/W4324153627","doi":"https://doi.org/10.1145/3582700.3582722","title":"AIx Speed: Playback Speed Optimization Using Listening Comprehension of Speech Recognition Models","display_name":"AIx Speed: Playback Speed Optimization Using Listening Comprehension of Speech Recognition Models","publication_year":2023,"publication_date":"2023-03-12","ids":{"openalex":"https://openalex.org/W4324153627","doi":"https://doi.org/10.1145/3582700.3582722"},"language":"en","primary_location":{"id":"doi:10.1145/3582700.3582722","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3582700.3582722","pdf_url":null,"source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Augmented Humans Conference","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2403.02938","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5087364594","display_name":"Kazuki Kawamura","orcid":"https://orcid.org/0000-0002-5181-320X"},"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":false,"raw_author_name":"Kazuki Kawamura","raw_affiliation_strings":["The University of Tokyo, Japan and Sony CSL Kyoto, Japan"],"raw_orcid":"https://orcid.org/0000-0002-5181-320X","affiliations":[{"raw_affiliation_string":"The University of Tokyo, Japan and Sony CSL Kyoto, Japan","institution_ids":["https://openalex.org/I4210122684","https://openalex.org/I74801974"]}]},{"author_position":"last","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":false,"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":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3695,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.51751888,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"200","last_page":"208"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998000264167786,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8275848627090454},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.748521625995636},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7189056873321533},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.4643595218658447},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4409022629261017},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4153323173522949},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32041478157043457}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8275848627090454},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.748521625995636},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7189056873321533},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.4643595218658447},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4409022629261017},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4153323173522949},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32041478157043457},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"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:10.1145/3582700.3582722","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3582700.3582722","pdf_url":null,"source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Augmented Humans Conference","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2403.02938","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.02938","pdf_url":"https://arxiv.org/pdf/2403.02938","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2403.02938","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.02938","pdf_url":"https://arxiv.org/pdf/2403.02938","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1063213209","display_name":null,"funder_award_id":"JPMJMS2012","funder_id":"https://openalex.org/F4320338247","funder_display_name":"Moonshot Research and Development Program"},{"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/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":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4324153627.pdf","grobid_xml":"https://content.openalex.org/works/W4324153627.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1967557272","https://openalex.org/W2141210837","https://openalex.org/W2191779130","https://openalex.org/W2533523411","https://openalex.org/W2742830501","https://openalex.org/W2892181857","https://openalex.org/W3012245936","https://openalex.org/W3016906310","https://openalex.org/W3030958012","https://openalex.org/W3137249133","https://openalex.org/W3171302872","https://openalex.org/W3210314917","https://openalex.org/W3211857125","https://openalex.org/W4235798148","https://openalex.org/W4281956585"],"related_works":["https://openalex.org/W2085637247","https://openalex.org/W2127461790","https://openalex.org/W2069324367","https://openalex.org/W3135230428","https://openalex.org/W2904739811","https://openalex.org/W2152158029","https://openalex.org/W2012540220","https://openalex.org/W2131711534","https://openalex.org/W2559040841","https://openalex.org/W114661351"],"abstract_inverted_index":{"Since":[0],"humans":[1,108],"can":[2,109,148,167,171],"listen":[3,17,221],"to":[4,18,29,50,59,79,100,161,174,220],"audio":[5],"and":[6,54,97,114,155,195,209],"watch":[7,20],"videos":[8],"at":[9,25,123,190],"faster":[10],"speeds":[11,28],"than":[12],"actually":[13],"observed,":[14],"we":[15,105,184],"often":[16],"or":[19],"these":[21,77],"pieces":[22],"of":[23,34,57,65,153],"content":[24,35,58,67],"higher":[26],"playback":[27,47,89,121,159],"increase":[30],"the":[31,46,51,55,111,136,157,162,181,186,196,202,212],"time":[32,95],"efficiency":[33],"comprehension.":[36],"To":[37],"further":[38,80],"utilize":[39],"this":[40,103],"capability,":[41],"systems":[42,78],"that":[43,118,164,211,217],"automatically":[44,119],"adjust":[45],"speed":[48,90,122,160,194],"according":[49],"user\u2019s":[52],"condition":[53],"type":[56],"assist":[60],"in":[61,205],"more":[62],"efficient":[63],"comprehension":[64],"time-series":[66],"have":[68],"been":[69],"developed.":[70],"However,":[71],"there":[72],"is":[73],"still":[74],"room":[75],"for":[76,92,143],"extend":[81],"human":[82,147,166],"speed-listening":[83],"ability":[84],"by":[85,201],"generating":[86],"speech":[87,113,131,137,154,158,187,199,216],"with":[88],"optimized":[91,112],"even":[93],"finer":[94],"units":[96,124],"providing":[98],"it":[99],"humans.":[101],"In":[102,180],"study,":[104],"determine":[106],"whether":[107],"hear":[110,149],"propose":[115],"a":[116,141,146,150,165,191,206],"system":[117,134],"adjusts":[120],"as":[125,127,140],"small":[126],"phonemes":[128],"while":[129],"ensuring":[130],"intelligibility.":[132],"The":[133],"uses":[135],"recognizer":[138],"score":[139],"proxy":[142],"how":[144],"well":[145],"certain":[151],"unit":[152],"maximizes":[156],"extent":[163],"hear.":[168],"This":[169],"method":[170,204,214],"be":[172],"used":[173],"produce":[175],"fast":[176,193],"but":[177],"intelligible":[178],"speech.":[179],"evaluation":[182],"experiment,":[183],"compared":[185],"played":[188],"back":[189],"constant":[192],"flexibly":[197],"speed-up":[198],"generated":[200],"proposed":[203,213],"blind":[207],"test":[208],"confirmed":[210],"produced":[215],"was":[218],"easier":[219],"to.":[222]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
