{"id":"https://openalex.org/W4307485686","doi":"https://doi.org/10.1145/3526114.3558727","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":2022,"publication_date":"2022-10-28","ids":{"openalex":"https://openalex.org/W4307485686","doi":"https://doi.org/10.1145/3526114.3558727"},"language":"en","primary_location":{"id":"doi:10.1145/3526114.3558727","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3526114.3558727","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":"Adjunct Proceedings of the 35th Annual ACM Symposium on User Interface Software and Technology","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/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":true,"raw_author_name":"Kazuki Kawamura","raw_affiliation_strings":["The University of Tokyo, Japan and Sony CSL Kyoto, Japan"],"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"],"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/A5087364594"],"corresponding_institution_ids":["https://openalex.org/I4210122684","https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":0.1007,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.38998118,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"3"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9998999834060669,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music 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/T10860","display_name":"Speech and Audio Processing","score":0.9991999864578247,"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":0.8211303949356079},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6808953881263733},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5666687488555908},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5517268180847168},{"id":"https://openalex.org/keywords/entertainment","display_name":"Entertainment","score":0.45714452862739563},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.42504602670669556},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34517383575439453},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.34168118238449097},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08606588840484619}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8211303949356079},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6808953881263733},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5666687488555908},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5517268180847168},{"id":"https://openalex.org/C512170562","wikidata":"https://www.wikidata.org/wiki/Q173799","display_name":"Entertainment","level":2,"score":0.45714452862739563},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.42504602670669556},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34517383575439453},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.34168118238449097},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08606588840484619},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"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:10.1145/3526114.3558727","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3526114.3558727","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":"Adjunct Proceedings of the 35th Annual ACM Symposium on User Interface Software and Technology","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.47999998927116394}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1967557272","https://openalex.org/W2141210837","https://openalex.org/W2533523411","https://openalex.org/W2933138175","https://openalex.org/W2973049979","https://openalex.org/W2979476256","https://openalex.org/W3012245936","https://openalex.org/W3016906310","https://openalex.org/W3030958012","https://openalex.org/W4281956585"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W98480971","https://openalex.org/W2150291671","https://openalex.org/W2027972911","https://openalex.org/W2146343568","https://openalex.org/W2013643406","https://openalex.org/W2157978810","https://openalex.org/W2597809628","https://openalex.org/W3046370962"],"abstract_inverted_index":{"In":[0,18],"recent":[1],"years,":[2],"more":[3,5,51],"and":[4,16,49,55,88,113],"time":[6,22,112],"has":[7],"been":[8],"spent":[9],"watching":[10],"videos":[11],"for":[12,46,59,94,122],"online":[13],"seminars,":[14],"lectures,":[15],"entertainment.":[17],"order":[19],"to":[20,30,41,53,103,117],"improve":[21],"efficiency,":[23],"people":[24],"often":[25],"adjust":[26,42,56],"the":[27,43,57,75,79,82,91,95,119,123],"playback":[28,76,92,107,111,120],"speed":[29,32,45,58,77,93,108,121],"a":[31,63,71,105],"that":[33,73,109],"suits":[34],"them":[35],"best.":[36],"However,":[37],"it":[38,101],"is":[39],"troublesome":[40],"optimal":[44],"each":[47,60],"video":[48],"even":[50],"challenging":[52],"change":[54],"speaker":[61],"within":[62,78],"single":[64],"video.":[65,97,125],"Therefore,":[66],"we":[67],"propose":[68],"\u201dAIx":[69],"speed,\u201d":[70],"system":[72,99],"maximizes":[74],"range":[80],"where":[81],"speech":[83],"recognition":[84],"model":[85],"can":[86],"recognize":[87],"flexibly":[89],"adjusts":[90],"entire":[96,124],"This":[98],"makes":[100],"possible":[102],"set":[104],"flexible":[106],"balances":[110],"content":[114],"comprehension,":[115],"compared":[116],"fixing":[118]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}