{"id":"https://openalex.org/W2129141326","doi":"https://doi.org/10.1109/icassp.2009.4960490","title":"Voice search of structured media data","display_name":"Voice search of structured media data","publication_year":2009,"publication_date":"2009-04-01","ids":{"openalex":"https://openalex.org/W2129141326","doi":"https://doi.org/10.1109/icassp.2009.4960490","mag":"2129141326"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2009.4960490","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960490","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Acoustics, Speech and Signal Processing","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/A5028145173","display_name":"Young-In Song","orcid":"https://orcid.org/0000-0003-0669-005X"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Young-In Song","raw_affiliation_strings":["Korea University, South Korea","Korea University, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea University, South Korea","institution_ids":["https://openalex.org/I197347611"]},{"raw_affiliation_string":"Korea University, Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056874223","display_name":"Ye\u2010Yi Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ye-Yi Wang","raw_affiliation_strings":["Microsoft Research Limited, USA","Microsoft Research,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Limited, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Research,USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108388457","display_name":"Yun\u2010Cheng Ju","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yun-Cheng Ju","raw_affiliation_strings":["Microsoft Research Limited, USA","Microsoft Research,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Limited, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Research,USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113773386","display_name":"Mike Seltzer","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mike Seltzer","raw_affiliation_strings":["Microsoft Research Limited, USA","Microsoft Research,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Limited, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Research,USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007425970","display_name":"Ivan Tashev","orcid":"https://orcid.org/0000-0002-2263-2047"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ivan Tashev","raw_affiliation_strings":["Microsoft Research Limited, USA","Microsoft Research,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Limited, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Research,USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111957484","display_name":"Alex Acero","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alex Acero","raw_affiliation_strings":["Microsoft Research Limited, USA","Microsoft Research,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Limited, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Research,USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.7149,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.96376764,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"3941","last_page":"3944"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9994999766349792,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9962000250816345,"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":0.8618568181991577},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.7866961359977722},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.7066394090652466},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5698468089103699},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.556455135345459},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5298331379890442},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45598673820495605},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.38960549235343933},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3777894973754883},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.07784822583198547}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8618568181991577},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.7866961359977722},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.7066394090652466},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5698468089103699},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.556455135345459},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5298331379890442},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45598673820495605},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38960549235343933},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3777894973754883},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.07784822583198547},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2009.4960490","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960490","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5699999928474426,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W73748647","https://openalex.org/W1956559956","https://openalex.org/W2095734449","https://openalex.org/W2109831181","https://openalex.org/W2151742940","https://openalex.org/W2152096275","https://openalex.org/W2159100590","https://openalex.org/W2166799778","https://openalex.org/W2169434751","https://openalex.org/W2325227998","https://openalex.org/W6603041686","https://openalex.org/W6674565674","https://openalex.org/W6676266797","https://openalex.org/W6683568067","https://openalex.org/W6685119187"],"related_works":["https://openalex.org/W1965294778","https://openalex.org/W1538155009","https://openalex.org/W1574295218","https://openalex.org/W2361349944","https://openalex.org/W2076264610","https://openalex.org/W2150890698","https://openalex.org/W2153783156","https://openalex.org/W3133710586","https://openalex.org/W2793122029","https://openalex.org/W2142303499"],"abstract_inverted_index":{"This":[0],"paper":[1],"addresses":[2],"the":[3,25,54,71,90],"problem":[4],"of":[5,98],"using":[6],"unstructured":[7],"queries":[8,36,61,68],"to":[9,39,64,70,82],"search":[10,16,27,92],"a":[11,75],"structured":[12],"database":[13],"in":[14,22],"voice":[15],"applications.":[17],"By":[18],"incorporating":[19],"structural":[20],"information":[21],"music":[23],"metadata,":[24],"end-to-end":[26,91],"error":[28,55],"has":[29,52,79,88],"been":[30,80],"reduced":[31,53],"by":[32,57],"15%":[33],"on":[34,41,45,59,66],"text":[35,60],"and":[37,62],"up":[38,63],"11%":[40],"spoken":[42,67],"queries.":[43],"Based":[44],"that,":[46],"an":[47],"HMM":[48],"sequential":[49],"rescoring":[50],"model":[51,78],"rate":[56],"28%":[58],"23%":[65],"compared":[69],"baseline":[72],"system.":[73],"Furthermore,":[74],"phonetic":[76],"similarity":[77],"introduced":[81],"compensate":[83],"speech":[84,99],"recognition":[85,100],"errors,":[86],"which":[87],"improved":[89],"accuracy":[93],"consistently":[94],"across":[95],"different":[96],"levels":[97],"accuracy.":[101]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
