{"id":"https://openalex.org/W2289925289","doi":"https://doi.org/10.1109/apsipa.2015.7415335","title":"Audio-visual speech recognition using deep bottleneck features and high-performance lipreading","display_name":"Audio-visual speech recognition using deep bottleneck features and high-performance lipreading","publication_year":2015,"publication_date":"2015-12-01","ids":{"openalex":"https://openalex.org/W2289925289","doi":"https://doi.org/10.1109/apsipa.2015.7415335","mag":"2289925289"},"language":"en","primary_location":{"id":"doi:10.1109/apsipa.2015.7415335","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipa.2015.7415335","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA)","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/A5101808735","display_name":"Satoshi Tamura","orcid":"https://orcid.org/0000-0001-6916-4618"},"institutions":[{"id":"https://openalex.org/I42405503","display_name":"Gifu University","ror":"https://ror.org/024exxj48","country_code":"JP","type":"education","lineage":["https://openalex.org/I42405503"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Satoshi Tamura","raw_affiliation_strings":["Gifu University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Gifu University, Japan","institution_ids":["https://openalex.org/I42405503"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101639573","display_name":"Hiroshi Ninomiya","orcid":"https://orcid.org/0000-0003-3418-3178"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroshi Ninomiya","raw_affiliation_strings":["Nagoya University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077234015","display_name":"Norihide Kitaoka","orcid":"https://orcid.org/0000-0003-2028-8585"},"institutions":[{"id":"https://openalex.org/I922474255","display_name":"Tokushima University","ror":"https://ror.org/044vy1d05","country_code":"JP","type":"education","lineage":["https://openalex.org/I922474255"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Norihide Kitaoka","raw_affiliation_strings":["Tokushima University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokushima University, Japan","institution_ids":["https://openalex.org/I922474255"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040638962","display_name":"Shin Osuga","orcid":null},"institutions":[{"id":"https://openalex.org/I4210098271","display_name":"Aisin (Japan)","ror":"https://ror.org/00vtxwp63","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210098271"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shin Osuga","raw_affiliation_strings":["Aisin Seiki Co., Ltd., Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aisin Seiki Co., Ltd., Japan","institution_ids":["https://openalex.org/I4210098271"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112017946","display_name":"Yurie Iribe","orcid":null},"institutions":[{"id":"https://openalex.org/I45205469","display_name":"Aichi Prefectural University","ror":"https://ror.org/047n0b268","country_code":"JP","type":"education","lineage":["https://openalex.org/I45205469"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yurie Iribe","raw_affiliation_strings":["Aichi Prefectural University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aichi Prefectural University, Japan","institution_ids":["https://openalex.org/I45205469"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042118446","display_name":"Kazuya Takeda","orcid":"https://orcid.org/0000-0002-0330-1787"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazuya Takeda","raw_affiliation_strings":["Nagoya University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008108612","display_name":"Satoru Hayamizu","orcid":null},"institutions":[{"id":"https://openalex.org/I42405503","display_name":"Gifu University","ror":"https://ror.org/024exxj48","country_code":"JP","type":"education","lineage":["https://openalex.org/I42405503"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Satoru Hayamizu","raw_affiliation_strings":["Gifu University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Gifu University, Japan","institution_ids":["https://openalex.org/I42405503"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.9294,"has_fulltext":false,"cited_by_count":49,"citation_normalized_percentile":{"value":0.95945713,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"575","last_page":"582"},"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/T11309","display_name":"Music and Audio Processing","score":0.9993000030517578,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9958999752998352,"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/speech-recognition","display_name":"Speech recognition","score":0.8225797414779663},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.7797525525093079},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7759283185005188},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.5807540416717529},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5446214079856873},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.467792809009552},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.44867584109306335},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3482508659362793},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.07845675945281982}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8225797414779663},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.7797525525093079},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7759283185005188},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.5807540416717529},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5446214079856873},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.467792809009552},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.44867584109306335},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3482508659362793},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.07845675945281982},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipa.2015.7415335","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipa.2015.7415335","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA)","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":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W1520736967","https://openalex.org/W1549662771","https://openalex.org/W1582624286","https://openalex.org/W1908325895","https://openalex.org/W1970088388","https://openalex.org/W1977821862","https://openalex.org/W1986861891","https://openalex.org/W1990353734","https://openalex.org/W1993882792","https://openalex.org/W2022799064","https://openalex.org/W2038359238","https://openalex.org/W2076462394","https://openalex.org/W2104263160","https://openalex.org/W2109434346","https://openalex.org/W2110798204","https://openalex.org/W2123237149","https://openalex.org/W2136922672","https://openalex.org/W2157190406","https://openalex.org/W2163288271","https://openalex.org/W2184188583","https://openalex.org/W2254457717","https://openalex.org/W2394553851","https://openalex.org/W2394932179","https://openalex.org/W2396239493","https://openalex.org/W2397904770","https://openalex.org/W2400811130","https://openalex.org/W2400967734","https://openalex.org/W2406846463","https://openalex.org/W2545925890","https://openalex.org/W2599757925","https://openalex.org/W6631338322","https://openalex.org/W6634774568","https://openalex.org/W6639968709","https://openalex.org/W6659808814","https://openalex.org/W6676481782","https://openalex.org/W6683616736","https://openalex.org/W6686207219","https://openalex.org/W6691901669","https://openalex.org/W6711879354","https://openalex.org/W6712206848","https://openalex.org/W6712444147","https://openalex.org/W6712911086","https://openalex.org/W6729650574","https://openalex.org/W6987407217","https://openalex.org/W7038555097"],"related_works":["https://openalex.org/W2595172197","https://openalex.org/W2084856301","https://openalex.org/W2127970246","https://openalex.org/W4382618745","https://openalex.org/W2885125400","https://openalex.org/W1001352512","https://openalex.org/W1989889224","https://openalex.org/W1973775000","https://openalex.org/W2748922771","https://openalex.org/W1987128138"],"abstract_inverted_index":{"This":[0],"paper":[1],"develops":[2],"an":[3],"Audio-Visual":[4],"Speech":[5],"Recognition":[6],"(AVSR)":[7],"method,":[8],"by":[9,54],"(1)":[10],"exploring":[11],"high-performance":[12],"visual":[13,19,37,45,89,105],"features,":[14,61,90],"(2)":[15],"applying":[16],"audio":[17,103],"and":[18,27,72,104,110],"deep":[20,55],"bottleneck":[21,52],"features":[22,46,53],"to":[23],"improve":[24],"AVSR":[25,75],"performance,":[26],"(3)":[28],"investigating":[29],"effectiveness":[30],"of":[31,44],"voice":[32],"activity":[33],"detection":[34],"in":[35,68,79,101],"a":[36],"modality.":[38],"In":[39,82],"our":[40],"approach,":[41],"many":[42],"kinds":[43],"are":[47],"incorporated,":[48],"subsequently":[49],"converted":[50],"into":[51],"learning":[56],"technology.":[57],"By":[58],"using":[59],"proposed":[60],"we":[62,84],"successfully":[63],"achieved":[64],"73.66%":[65],"lipreading":[66,93,109],"accuracy":[67,76],"speaker-independent":[69],"open":[70],"condition,":[71],"about":[73],"90%":[74],"on":[77],"average":[78],"noisy":[80],"environments.":[81],"addition,":[83],"extracted":[85],"speech":[86],"segments":[87],"from":[88],"resulting":[91],"77.80%":[92],"accuracy.":[94],"It":[95],"is":[96,99],"found":[97],"VAD":[98],"useful":[100],"both":[102],"modalities,":[106],"for":[107],"better":[108],"AVSR.":[111]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":8},{"year":2016,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}