{"id":"https://openalex.org/W2972730581","doi":"https://doi.org/10.1145/3341162.3344861","title":"Audio-visual TED corpus","display_name":"Audio-visual TED corpus","publication_year":2019,"publication_date":"2019-09-09","ids":{"openalex":"https://openalex.org/W2972730581","doi":"https://doi.org/10.1145/3341162.3344861","mag":"2972730581"},"language":"en","primary_location":{"id":"doi:10.1145/3341162.3344861","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3341162.3344861","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3341162.3344861","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Adjunct Proceedings of the 2019 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2019 ACM International Symposium on Wearable Computers","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3341162.3344861","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069665298","display_name":"Guan-Lin Chao","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Guan-Lin Chao","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108816435","display_name":"Chih Chi Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chih Chi Hu","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100339921","display_name":"Bing Liu","orcid":"https://orcid.org/0000-0002-2365-6606"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bing Liu","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102751221","display_name":"John Paul Shen","orcid":"https://orcid.org/0000-0002-7225-0629"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John Paul Shen","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028182466","display_name":"Ian Lane","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ian Lane","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":0.3823,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.51153013,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"468","last_page":"473"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech 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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech 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/T11309","display_name":"Music and Audio Processing","score":0.9988999962806702,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9987000226974487,"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/computer-science","display_name":"Computer science","score":0.8339704275131226},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6357913017272949},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6321916580200195},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.5850087404251099},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5708173513412476},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.49115702509880066},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.46847596764564514},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.46053552627563477},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.07744264602661133},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07709804177284241}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8339704275131226},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6357913017272949},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6321916580200195},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.5850087404251099},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5708173513412476},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.49115702509880066},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.46847596764564514},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.46053552627563477},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.07744264602661133},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07709804177284241},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3341162.3344861","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3341162.3344861","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3341162.3344861","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Adjunct Proceedings of the 2019 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2019 ACM International Symposium on Wearable Computers","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3341162.3344861","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3341162.3344861","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3341162.3344861","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Adjunct Proceedings of the 2019 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2019 ACM International Symposium on Wearable Computers","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7400000095367432}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2972730581.pdf","grobid_xml":"https://content.openalex.org/works/W2972730581.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W142945732","https://openalex.org/W1527240141","https://openalex.org/W1997121481","https://openalex.org/W1998294030","https://openalex.org/W2001642682","https://openalex.org/W2012885984","https://openalex.org/W2015143272","https://openalex.org/W2024922353","https://openalex.org/W2037227137","https://openalex.org/W2064675550","https://openalex.org/W2070115136","https://openalex.org/W2096733369","https://openalex.org/W2098923380","https://openalex.org/W2115252128","https://openalex.org/W2117539524","https://openalex.org/W2122702209","https://openalex.org/W2142518644","https://openalex.org/W2250357346","https://openalex.org/W2251321385","https://openalex.org/W2284800790","https://openalex.org/W2325939864","https://openalex.org/W2515770085","https://openalex.org/W2570343428","https://openalex.org/W2570575067","https://openalex.org/W2963566548","https://openalex.org/W3099206234","https://openalex.org/W3163547718","https://openalex.org/W3210232381"],"related_works":["https://openalex.org/W2053269318","https://openalex.org/W2364370872","https://openalex.org/W2271369634","https://openalex.org/W2025614924","https://openalex.org/W3147472394","https://openalex.org/W2047100085","https://openalex.org/W2350550760","https://openalex.org/W2294335174","https://openalex.org/W2097963413","https://openalex.org/W3145575561"],"abstract_inverted_index":{"We":[0,14],"present":[1],"a":[2],"variety":[3],"of":[4,125,131],"new":[5,46],"visual":[6,47,88,127],"features":[7,48,92,128,133],"in":[8,67,78,93,106,137],"extension":[9],"to":[10,115],"the":[11,16,68,87,107,123],"TED-LIUM":[12],"corpus.":[13],"re-aligned":[15],"original":[17],"TED":[18],"talk":[19],"audio":[20,81],"transcriptions":[21],"with":[22,80],"official":[23],"TED.com":[24],"videos.":[25],"By":[26],"utilizing":[27],"state-of-the-art":[28],"models":[29],"for":[30,53,82,134],"face":[31],"and":[32,41,65,73,103],"facial":[33,61,71],"landmarks":[34,74],"detection,":[35],"optical":[36],"character":[37],"recognition,":[38],"object":[39],"detection":[40],"classification,":[42],"we":[43],"extract":[44],"four":[45],"that":[49],"can":[50,75,109],"be":[51,76,110],"used":[52,77,111],"Large-Vocabulary":[54],"Continuous":[55],"Speech":[56],"Recognition":[57],"(LVCSR)":[58],"systems,":[59],"including":[60],"images,":[62],"landmarks,":[63],"text,":[64],"objects":[66,105],"scenes.":[69],"The":[70,97],"images":[72],"combination":[79],"audio-visual":[83],"acoustic":[84,95,132],"modeling":[85],"where":[86],"modality":[89],"provides":[90],"robust":[91],"adverse":[94],"environments.":[96],"contextual":[98,117],"information,":[99],"i.e.":[100],"extracted":[101],"text":[102],"detected":[104],"scene":[108],"as":[112],"prior":[113],"knowledge":[114],"create":[116],"language":[118],"models.":[119],"Experimental":[120],"results":[121],"showed":[122],"efficacy":[124],"using":[126],"on":[129],"top":[130],"speech":[135,139],"recognition":[136],"overlapping":[138],"scenarios.":[140]},"counts_by_year":[{"year":2021,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
