{"id":"https://openalex.org/W2111338354","doi":"https://doi.org/10.1109/icassp.2004.1325970","title":"Vocabulary-independent search in spontaneous speech","display_name":"Vocabulary-independent search in spontaneous speech","publication_year":2004,"publication_date":"2004-09-28","ids":{"openalex":"https://openalex.org/W2111338354","doi":"https://doi.org/10.1109/icassp.2004.1325970","mag":"2111338354"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2004.1325970","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2004.1325970","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Conference on Acoustics, Speech, and Signal Processing","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/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":"F. Seide","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China","Microsoft research Asia, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103088416","display_name":"Peng Yu","orcid":"https://orcid.org/0000-0002-4446-4427"},"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":"Peng Yu","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China","Microsoft research Asia, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102725787","display_name":"Chengyuan Ma","orcid":"https://orcid.org/0000-0001-5126-5883"},"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":"Chengyuan Ma","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China","Microsoft research Asia, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087298985","display_name":"Eric Chang","orcid":"https://orcid.org/0000-0002-9678-5994"},"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":"E. Chang","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China","Microsoft research Asia, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210113369"],"apc_list":null,"apc_paid":null,"fwci":4.6308,"has_fulltext":false,"cited_by_count":69,"citation_normalized_percentile":{"value":0.95790402,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"1","issue":null,"first_page":"I","last_page":"253"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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/T10201","display_name":"Speech Recognition and Synthesis","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/T10181","display_name":"Natural Language Processing Techniques","score":0.9990000128746033,"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/T10028","display_name":"Topic Modeling","score":0.9983000159263611,"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":0.8237718939781189},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.8032793998718262},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7003571391105652},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5948176980018616},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5721646547317505},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5542303919792175},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5356724858283997},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.47759056091308594},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.4362601041793823},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4180225431919098},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4120737612247467},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.22006356716156006},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07711046934127808}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8237718939781189},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.8032793998718262},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7003571391105652},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5948176980018616},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5721646547317505},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5542303919792175},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5356724858283997},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.47759056091308594},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.4362601041793823},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4180225431919098},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4120737612247467},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.22006356716156006},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07711046934127808},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2004.1325970","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2004.1325970","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Conference on Acoustics, Speech, and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.138.7187","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.138.7187","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://research.microsoft.com/asia/dload_files/group/speech/2007upload/0100253.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6499999761581421}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320273","display_name":"University of Cambridge","ror":"https://ror.org/013meh722"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W49437105","https://openalex.org/W72804518","https://openalex.org/W972441279","https://openalex.org/W1591237756","https://openalex.org/W1878610756","https://openalex.org/W1888768218","https://openalex.org/W2006994648","https://openalex.org/W2022951240","https://openalex.org/W2057728687","https://openalex.org/W2074642696","https://openalex.org/W2074932712","https://openalex.org/W2095059939","https://openalex.org/W2095593458","https://openalex.org/W2096421062","https://openalex.org/W2097048430","https://openalex.org/W2129334286","https://openalex.org/W2131111393","https://openalex.org/W2136440675","https://openalex.org/W2186490579","https://openalex.org/W2397798422","https://openalex.org/W2789663420","https://openalex.org/W6602326401","https://openalex.org/W6635391832","https://openalex.org/W6679446661"],"related_works":["https://openalex.org/W1997182898","https://openalex.org/W1566315437","https://openalex.org/W4221142855","https://openalex.org/W2594897229","https://openalex.org/W2151348424","https://openalex.org/W2050138804","https://openalex.org/W767271433","https://openalex.org/W4290708361","https://openalex.org/W2129812225","https://openalex.org/W2944691285"],"abstract_inverted_index":{"For":[0,32],"efficient":[1],"organization":[2],"of":[3,68,102,158],"speech":[4,64],"recordings":[5],"-":[6,12],"meetings,":[7],"interviews,":[8],"voice":[9,135],"mails,":[10],"lectures":[11],"the":[13,33,41,81,122,133],"ability":[14],"to":[15,55,58,83,120,124],"search":[16,59,143],"for":[17,154,166],"spoken":[18],"keywords":[19,74,156],"is":[20,144],"an":[21],"essential":[22],"capability.":[23],"Today,":[24],"most":[25],"spoken-document":[26],"retrieval":[27],"systems":[28,37],"use":[29,84],"large-vocabulary":[30],"recognition.":[31],"above":[34],"scenarios,":[35],"such":[36],"suffer":[38],"from":[39],"both":[40],"unpredictable":[42],"vocabulary/domain":[43],"and":[44,57],"generally":[45],"high":[46],"word-error":[47],"rates":[48],"(WER).":[49],"We":[50,78],"present":[51],"a":[52,89,93,113,148],"vocabulary-independent":[53],"system":[54,153],"index":[56],"rapidly":[60],"spontaneous":[61],"speech.":[62],"A":[63],"recognizer":[65],"generates":[66],"lattices":[67,123],"phonetic":[69,103,142],"word":[70],"fragments,":[71],"against":[72],"which":[73,107],"are":[75],"matched":[76],"phonetically.":[77],"first":[79],"show":[80,139],"need":[82],"recognition":[85],"alternatives":[86],"(lattices)":[87],"in":[88],"high-WER":[90],"context,":[91],"on":[92],"word-based":[94],"baseline.":[95],"Then":[96],"we":[97,117,138],"introduce":[98,118],"our":[99],"new":[100],"method":[101],"word-fragment":[104],"lattice":[105],"generation,":[106],"uses":[108],"longer-span":[109],"language":[110],"knowledge":[111],"than":[112],"phoneme":[114],"recognizer.":[115],"Last":[116],"heuristics":[119],"compact":[121],"feasible":[125],"sizes":[126],"that":[127,140],"can":[128],"be":[129],"searched":[130],"efficiently.":[131],"On":[132],"LDC":[134],"mail":[136],"corpus,":[137],"vocabulary/domain-independent":[141],"as":[145,147],"accurate":[146],"vocabulary/domain-dependent":[149],"word-lattice":[150],"based":[151],"baseline":[152],"in-vocabulary":[155],"(FOMs":[157],"74-75%),":[159],"but":[160],"nearly":[161],"maintains":[162],"this":[163],"accuracy":[164],"also":[165],"out-of-vocabulary":[167],"keywords.":[168]},"counts_by_year":[{"year":2019,"cited_by_count":2},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":6}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}