{"id":"https://openalex.org/W2102262266","doi":"https://doi.org/10.1109/icassp.2011.5947475","title":"Leveraging the Web for automatically generating indexable and browsable keywords for speech files","display_name":"Leveraging the Web for automatically generating indexable and browsable keywords for speech files","publication_year":2011,"publication_date":"2011-05-01","ids":{"openalex":"https://openalex.org/W2102262266","doi":"https://doi.org/10.1109/icassp.2011.5947475","mag":"2102262266"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2011.5947475","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947475","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5109226002","display_name":"Kit Thambiratnam","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kit Thambiratnam","raw_affiliation_strings":["5F Sigma Center, Microsoft Research Asia, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"5F Sigma Center, Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100438769","display_name":"Gang Li","orcid":"https://orcid.org/0000-0003-1583-641X"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gang Li","raw_affiliation_strings":["5F Sigma Center, Microsoft Research Asia, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"5F Sigma Center, Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086853840","display_name":"Meng Sha","orcid":"https://orcid.org/0000-0003-4492-1189"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sha Meng","raw_affiliation_strings":["5F Sigma Center, Microsoft Research Asia, Beijing, China","Department of Electronic Engineering, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"5F Sigma Center, Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072932051","display_name":"Frank Seide","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Frank Seide","raw_affiliation_strings":["5F Sigma Center, Microsoft Research Asia, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"5F Sigma Center, Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]}],"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":0,"citation_normalized_percentile":{"value":0.17139532,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4984","last_page":"4987"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9998999834060669,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9998999834060669,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9715999960899353,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10028","display_name":"Topic Modeling","score":0.9465000033378601,"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":0.8827617168426514},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.7367181181907654},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.6817755699157715},{"id":"https://openalex.org/keywords/keyword-density","display_name":"Keyword density","score":0.6773971319198608},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.59232097864151},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.58582603931427},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5753992795944214},{"id":"https://openalex.org/keywords/keyword-extraction","display_name":"Keyword extraction","score":0.5341815948486328},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.48150476813316345},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.4535346031188965},{"id":"https://openalex.org/keywords/keyword-search","display_name":"Keyword search","score":0.4331439435482025},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3515969216823578}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8827617168426514},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.7367181181907654},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.6817755699157715},{"id":"https://openalex.org/C57560718","wikidata":"https://www.wikidata.org/wiki/Q125627","display_name":"Keyword density","level":3,"score":0.6773971319198608},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.59232097864151},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.58582603931427},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5753992795944214},{"id":"https://openalex.org/C2780288562","wikidata":"https://www.wikidata.org/wiki/Q25053353","display_name":"Keyword extraction","level":2,"score":0.5341815948486328},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.48150476813316345},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4535346031188965},{"id":"https://openalex.org/C2988412617","wikidata":"https://www.wikidata.org/wiki/Q7441656","display_name":"Keyword search","level":2,"score":0.4331439435482025},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3515969216823578},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2011.5947475","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947475","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7599999904632568,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W36558693","https://openalex.org/W46233444","https://openalex.org/W1525595230","https://openalex.org/W1612003148","https://openalex.org/W1831406492","https://openalex.org/W2001780484","https://openalex.org/W2035573568","https://openalex.org/W2097705305","https://openalex.org/W2132778990","https://openalex.org/W6674781836","https://openalex.org/W7015831105"],"related_works":["https://openalex.org/W2466354565","https://openalex.org/W2085130611","https://openalex.org/W2151491383","https://openalex.org/W1967461005","https://openalex.org/W3093477062","https://openalex.org/W2314592662","https://openalex.org/W2606928473","https://openalex.org/W190266872","https://openalex.org/W2095238631","https://openalex.org/W348400776"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,52,58,94,114],"method":[4,63],"for":[5,45,97,117],"generating":[6],"indexable":[7],"and":[8,28,70,110],"browsable":[9],"keyword":[10,38,59,68,105],"metadata":[11],"from":[12,24,34],"ASR":[13,26,80,86],"transcripts":[14],"by":[15],"leveraging":[16],"the":[17,35,79,83],"Web.":[18,36],"Search":[19],"engine":[20],"queries":[21],"are":[22],"built":[23],"an":[25,101],"transcript":[27],"used":[29],"to":[30,56,112,120],"retrieve":[31],"similar":[32],"text":[33],"The":[37,61],"meta":[39],"information":[40,54],"embedded":[41],"in":[42,78],"those":[43],"pages":[44],"search":[46],"engines":[47],"is":[48,64,108],"then":[49],"ranked":[50],"using":[51],"mutual":[53],"criteria":[55],"derive":[57],"set.":[60],"proposed":[62,109],"training-free,":[65],"allows":[66],"phrase":[67],"generation,":[69],"can":[71],"generate":[72],"words":[73],"that":[74],"were":[75],"not":[76],"spoken":[77],"transcript,":[81],"alleviating":[82],"impact":[84],"of":[85,104],"out-of-vocabulary.":[87],"Subjective":[88],"evaluations":[89],"on":[90],"technical":[91],"presentations":[92],"demonstrate":[93],"clear":[95],"preference":[96],"this":[98],"approach.":[99],"Additionally":[100],"objective":[102],"measure":[103],"generation":[106],"performance":[107],"shown":[111],"be":[113],"useful":[115],"guide":[116],"tuning":[118],"compared":[119],"more":[121],"onerous":[122],"subjective":[123],"evaluations.":[124]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}