{"id":"https://openalex.org/W158384662","doi":"https://doi.org/10.21437/interspeech.2010-306","title":"Continuous speech recognition with a TF-IDF acoustic model","display_name":"Continuous speech recognition with a TF-IDF acoustic model","publication_year":2010,"publication_date":"2010-09-26","ids":{"openalex":"https://openalex.org/W158384662","doi":"https://doi.org/10.21437/interspeech.2010-306","mag":"158384662"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2010-306","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2010-306","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2010","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/A5069954850","display_name":"Geoffrey Zweig","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Geoffrey Zweig","raw_affiliation_strings":["Microsoft"],"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111455517","display_name":"Patrick Nguyen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Patrick Nguyen","raw_affiliation_strings":["Microsoft"],"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012153296","display_name":"Jasha Droppo","orcid":"https://orcid.org/0000-0001-6097-0090"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jasha Droppo","raw_affiliation_strings":["Microsoft"],"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111957484","display_name":"Alex Acero","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Alex Acero","raw_affiliation_strings":["Microsoft"],"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5069954850"],"corresponding_institution_ids":["https://openalex.org/I4210164937"],"apc_list":null,"apc_paid":null,"fwci":1.3965,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.83635441,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"2854","last_page":"2857"},"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/T11309","display_name":"Music 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/T10860","display_name":"Speech and Audio Processing","score":0.9986000061035156,"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/computer-science","display_name":"Computer science","score":0.8592568635940552},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7565627694129944},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.6330317258834839},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6045685410499573},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5877404808998108},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5717880725860596},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.5597131252288818},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5330578088760376},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.5272171497344971},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5179740190505981},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48783043026924133},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.48526307940483093},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.45809441804885864},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4093148708343506},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3613848090171814}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8592568635940552},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7565627694129944},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.6330317258834839},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6045685410499573},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5877404808998108},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5717880725860596},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.5597131252288818},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5330578088760376},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.5272171497344971},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5179740190505981},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48783043026924133},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.48526307940483093},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.45809441804885864},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4093148708343506},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3613848090171814},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2010-306","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2010-306","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2010","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.174.7609","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.174.7609","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/en-us/um/people/gzweig/Pubs/interspeech2010_tfidf_am.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6499999761581421,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W178496478","https://openalex.org/W193502577","https://openalex.org/W1532325895","https://openalex.org/W2024490156","https://openalex.org/W2054293315","https://openalex.org/W2099832642","https://openalex.org/W2101890023","https://openalex.org/W2106284094","https://openalex.org/W2117987986","https://openalex.org/W2118835780","https://openalex.org/W2131033001","https://openalex.org/W2165612380","https://openalex.org/W2166339243","https://openalex.org/W2949468472","https://openalex.org/W2952387069"],"related_works":["https://openalex.org/W2131156500","https://openalex.org/W2118916824","https://openalex.org/W2157598242","https://openalex.org/W1479881079","https://openalex.org/W2092406870","https://openalex.org/W3159882232","https://openalex.org/W2964829415","https://openalex.org/W2131711534","https://openalex.org/W642007152","https://openalex.org/W2341426843"],"abstract_inverted_index":{"Information":[0],"retrieval":[1],"methods":[2,34],"are":[3],"frequently":[4],"used":[5,37],"for":[6,18,84],"indexing":[7],"and":[8,12,57,80,105,124],"retrieving":[9],"spoken":[10],"documents,":[11],"more":[13,41],"recently":[14],"have":[15],"been":[16],"proposed":[17],"voice-search":[19],"amongst":[20],"a":[21,49,60,86,89,120],"pre-defined":[22],"set":[23],"of":[24,62,132,151],"business":[25],"entries.":[26],"In":[27],"this":[28,74,133],"paper,":[29],"we":[30],"show":[31],"that":[32],"these":[33],"can":[35],"be":[36],"in":[38,48,102,109],"an":[39],"even":[40],"fundamental":[42],"way,":[43],"as":[44,59],"the":[45,81,94,98,103,112,125,149],"core":[46],"component":[47],"continuous":[50],"speech":[51,145],"recognizer.":[52],"Speech":[53],"is":[54,78,91],"initially":[55],"processed":[56],"represented":[58],"sequence":[61],"discrete":[63],"symbols,":[64],"specifically":[65],"phoneme":[66],"or":[67],"multi-phone":[68],"units.":[69],"Recognition":[70],"then":[71],"operates":[72],"on":[73,93,118,148],"sequence.":[75],"The":[76,130],"recognizer":[77],"segment-based,":[79],"acoustic":[82],"score":[83],"labeling":[85],"segment":[87],"with":[88,111],"word":[90],"based":[92,147],"TF-IDF":[95],"similarity":[96],"between":[97],"subword":[99],"units":[100],"detected":[101],"segment,":[104],"those":[106],"typically":[107],"seen":[108],"association":[110],"word.":[113],"We":[114],"present":[115],"promising":[116],"results":[117],"both":[119],"voice":[121],"search":[122],"task":[123],"Wall":[126],"Street":[127],"Journal":[128],"task.":[129],"development":[131],"method":[134],"brings":[135],"us":[136],"one":[137],"step":[138],"closer":[139],"to":[140,143],"being":[141],"able":[142],"do":[144],"recognition":[146],"detection":[150],"sub-word":[152],"audio":[153],"attributes.":[154]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}