{"id":"https://openalex.org/W4233470118","doi":"https://doi.org/10.21437/interspeech.2012-69","title":"On-the-fly topic adaptation for YouTube video transcription","display_name":"On-the-fly topic adaptation for YouTube video transcription","publication_year":2012,"publication_date":"2012-09-09","ids":{"openalex":"https://openalex.org/W4233470118","doi":"https://doi.org/10.21437/interspeech.2012-69"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2012-69","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2012-69","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2012","raw_type":"proceedings-article"},"type":"conference-paper","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/A5005163929","display_name":"Kapil Thadani","orcid":null},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kapil Thadani","raw_affiliation_strings":["Department of Computer Science, Columbia University, New York, NY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Columbia University, New York, NY","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055592425","display_name":"Fadi Biadsy","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fadi Biadsy","raw_affiliation_strings":["Google Inc., New York, NY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., New York, NY","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061376608","display_name":"Dan Bikel","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dan Bikel","raw_affiliation_strings":["Google Inc., New York, NY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., New York, NY","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.32830639,"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":"210","last_page":"213"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9977999925613403,"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":0.9977999925613403,"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/T11439","display_name":"Video Analysis and Summarization","score":0.996999979019165,"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":0.9965000152587891,"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/closed-captioning","display_name":"Closed captioning","score":0.8916687369346619},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8738288879394531},{"id":"https://openalex.org/keywords/upload","display_name":"Upload","score":0.812343955039978},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5349107384681702},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4915066659450531},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.4847961962223053},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.48151859641075134},{"id":"https://openalex.org/keywords/video-browsing","display_name":"Video browsing","score":0.4503997564315796},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.44250521063804626},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.4321572482585907},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3986503481864929},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3425378203392029},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33707481622695923},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.2676258683204651},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.26097577810287476},{"id":"https://openalex.org/keywords/video-processing","display_name":"Video processing","score":0.24799934029579163},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.1158515214920044}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8916687369346619},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8738288879394531},{"id":"https://openalex.org/C71901391","wikidata":"https://www.wikidata.org/wiki/Q7126699","display_name":"Upload","level":2,"score":0.812343955039978},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5349107384681702},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4915066659450531},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.4847961962223053},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.48151859641075134},{"id":"https://openalex.org/C2775856596","wikidata":"https://www.wikidata.org/wiki/Q25141683","display_name":"Video browsing","level":4,"score":0.4503997564315796},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.44250521063804626},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.4321572482585907},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3986503481864929},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3425378203392029},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33707481622695923},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2676258683204651},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.26097577810287476},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.24799934029579163},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.1158515214920044},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2012-69","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2012-69","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2012","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W85801758","https://openalex.org/W170853248","https://openalex.org/W1644652583","https://openalex.org/W1994694952","https://openalex.org/W2035108077","https://openalex.org/W2038276547","https://openalex.org/W2092062917","https://openalex.org/W2099253838","https://openalex.org/W2112874453","https://openalex.org/W2114858359","https://openalex.org/W2116236039","https://openalex.org/W2130696866","https://openalex.org/W2137206888","https://openalex.org/W2141645663","https://openalex.org/W2146871184","https://openalex.org/W2159382562","https://openalex.org/W2427881153"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W4290852288","https://openalex.org/W2949362007","https://openalex.org/W4388893791","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W2949522393"],"abstract_inverted_index":{"Automatic":[0],"closed-captioning":[1],"of":[2,8,67,75],"video":[3,38,43,56,103],"is":[4],"a":[5,31,45,72,95,101,106,119,128],"useful":[6],"application":[7],"speech":[9],"recognition":[10],"technology":[11],"but":[12],"poses":[13],"numerous":[14],"challenges":[15],"when":[16],"applied":[17],"to":[18,33,51,62,70],"open-domain":[19],"user-uploaded":[20],"videos":[21,68],"such":[22],"as":[23,116,118],"those":[24],"on":[25,100],"YouTube.In":[26],"this":[27],"work,":[28],"we":[29],"explore":[30],"strategy":[32],"improve":[34],"decoding":[35,41],"accuracy":[36],"for":[37,83],"transcription":[39],"by":[40],"each":[42],"with":[44,127],"language":[46],"model":[47],"(LM)":[48],"adapted":[49],"specifically":[50],"the":[52,55,64,136],"topics":[53],"that":[54],"covers.Taxonomic":[57],"topic":[58,65],"classifiers":[59],"are":[60],"used":[61],"determine":[63],"content":[66],"and":[69,85,91],"build":[71],"large":[73,130],"set":[74],"topic-specific":[76],"LMs":[77,87],"from":[78,134],"web":[79],"documents.We":[80],"consider":[81],"strategies":[82],"selecting":[84],"interpolating":[86],"in":[88,94,110],"both":[89],"supervised":[90],"unsupervised":[92],"scenarios":[93],"two-pass":[96],"lattice":[97],"rescoring":[98,126],"framework.Experiments":[99],"YouTube":[102],"corpus":[104],"show":[105],"3.6":[107],"absolute":[108,123],"reduction":[109],"WER":[111],"over":[112,125],"generic":[113],"single-pass":[114],"transcriptions":[115],"well":[117],"statistically":[120],"significant":[121],"0.8":[122],"improvement":[124],"very":[129],"non-adapted":[131],"LM":[132],"built":[133],"all":[135],"documents.":[137]},"counts_by_year":[{"year":2016,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
