{"id":"https://openalex.org/W2131033001","doi":"https://doi.org/10.1109/asru.2009.5372916","title":"A segmental CRF approach to large vocabulary continuous speech recognition","display_name":"A segmental CRF approach to large vocabulary continuous speech recognition","publication_year":2009,"publication_date":"2009-12-01","ids":{"openalex":"https://openalex.org/W2131033001","doi":"https://doi.org/10.1109/asru.2009.5372916","mag":"2131033001"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2009.5372916","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2009.5372916","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE Workshop on Automatic Speech Recognition & Understanding","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/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":true,"raw_author_name":"Geoffrey Zweig","raw_affiliation_strings":["Microsoft Research Limited, Redmond, WA, USA","[Microsoft Research,Redmond,WA,USA]"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Limited, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"[Microsoft Research,Redmond,WA,USA]","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111455517","display_name":"Patrick Nguyen","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":"Patrick Nguyen","raw_affiliation_strings":["Microsoft Research Limited, Redmond, WA, USA","[Microsoft Research,Redmond,WA,USA]"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Limited, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"[Microsoft Research,Redmond,WA,USA]","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5069954850"],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":null,"apc_paid":null,"fwci":19.8717,"has_fulltext":false,"cited_by_count":115,"citation_normalized_percentile":{"value":0.99441166,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"152","last_page":"157"},"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":0.9994000196456909,"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":0.9983999729156494,"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":0.8004406094551086},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.744226336479187},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7393524050712585},{"id":"https://openalex.org/keywords/conditional-random-field","display_name":"Conditional random field","score":0.605004608631134},{"id":"https://openalex.org/keywords/syllable","display_name":"Syllable","score":0.5880061388015747},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5525597333908081},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5397964119911194},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5364857912063599},{"id":"https://openalex.org/keywords/formant","display_name":"Formant","score":0.4509427845478058},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44507843255996704},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.41057994961738586},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.40556231141090393},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10390263795852661}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8004406094551086},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.744226336479187},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7393524050712585},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.605004608631134},{"id":"https://openalex.org/C109089402","wikidata":"https://www.wikidata.org/wiki/Q8188","display_name":"Syllable","level":2,"score":0.5880061388015747},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5525597333908081},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5397964119911194},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5364857912063599},{"id":"https://openalex.org/C158215666","wikidata":"https://www.wikidata.org/wiki/Q1414685","display_name":"Formant","level":3,"score":0.4509427845478058},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44507843255996704},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.41057994961738586},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40556231141090393},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10390263795852661},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/asru.2009.5372916","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2009.5372916","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE Workshop on Automatic Speech Recognition & Understanding","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.149.9015","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.149.9015","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/pubs/102642/scarf_asru09.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.7300000190734863}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W155708904","https://openalex.org/W177307080","https://openalex.org/W2005076803","https://openalex.org/W2056845660","https://openalex.org/W2083393647","https://openalex.org/W2099832642","https://openalex.org/W2106404689","https://openalex.org/W2111732304","https://openalex.org/W2116986994","https://openalex.org/W2119155265","https://openalex.org/W2127217706","https://openalex.org/W2131964822","https://openalex.org/W2134193990","https://openalex.org/W2147880316","https://openalex.org/W2154075111","https://openalex.org/W2156615793","https://openalex.org/W2158148237","https://openalex.org/W2158188757","https://openalex.org/W2163314930","https://openalex.org/W2165712214","https://openalex.org/W2166339243","https://openalex.org/W6674940356","https://openalex.org/W6682082992","https://openalex.org/W6682449347","https://openalex.org/W6683226453","https://openalex.org/W6683795702","https://openalex.org/W6959124532"],"related_works":["https://openalex.org/W2046217390","https://openalex.org/W4365503437","https://openalex.org/W2362995206","https://openalex.org/W2004825552","https://openalex.org/W1986672430","https://openalex.org/W2033234713","https://openalex.org/W2163278254","https://openalex.org/W155708904","https://openalex.org/W1574213390","https://openalex.org/W2095972591"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,34,149],"segmental":[4],"conditional":[5],"random":[6],"field":[7],"framework":[8,116,136],"for":[9,118],"large":[10],"vocabulary":[11],"continuous":[12],"speech":[13],"recognition.":[14],"Fundamental":[15],"to":[16,87,102],"this":[17,135],"approach":[18,73],"is":[19,74,105],"the":[20,26,30,58,62,80,108,119,126,142],"use":[21,109],"of":[22,33,37,71,110,125,134],"acoustic":[23,127],"detectors":[24],"as":[25,93],"basic":[27],"input,":[28],"and":[29,54,65,83,97,114,128],"automatic":[31],"construction":[32],"versatile":[35],"set":[36],"segment-level":[38],"features.":[39],"The":[40],"detector":[41],"streams":[42],"operate":[43],"at":[44,57,79],"multiple":[45],"time":[46],"scales":[47],"(frame,":[48],"phone,":[49],"multi-phone,":[50],"syllable":[51,98],"or":[52,121],"word)":[53],"are":[55,77,84],"combined":[56],"word":[59,81],"level":[60],"in":[61,148],"CRF":[63],"training":[64,124],"decoding":[66],"processes.":[67],"A":[68],"key":[69],"aspect":[70],"our":[72,115],"that":[75],"features":[76,113],"defined":[78],"level,":[82],"naturally":[85],"geared":[86],"explain":[88],"long":[89],"span":[90],"phenomena":[91],"such":[92],"formant":[94],"trajectories,":[95],"duration,":[96],"stress":[99],"patterns.":[100],"Generalization":[101],"unseen":[103],"words":[104],"possible":[106],"through":[107],"decomposable":[111],"consistency":[112],"allows":[117],"joint":[120],"separate":[122],"discriminative":[123],"language":[129],"models.":[130],"An":[131],"initial":[132],"evaluation":[133],"with":[137],"voice":[138],"search":[139],"data":[140],"from":[141],"Bing":[143],"Mobile":[144],"(BM)":[145],"application":[146],"results":[147],"2%":[150],"absolute":[151],"improvement":[152],"over":[153],"an":[154],"HMM":[155],"baseline.":[156]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":14},{"year":2015,"cited_by_count":12},{"year":2014,"cited_by_count":8},{"year":2013,"cited_by_count":14},{"year":2012,"cited_by_count":17}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}