{"id":"https://openalex.org/W2131964822","doi":"https://doi.org/10.1109/icassp.2009.4960470","title":"A flat direct model for speech recognition","display_name":"A flat direct model for speech recognition","publication_year":2009,"publication_date":"2009-04-01","ids":{"openalex":"https://openalex.org/W2131964822","doi":"https://doi.org/10.1109/icassp.2009.4960470","mag":"2131964822"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2009.4960470","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960470","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/A5071956319","display_name":"Georg Heigold","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"]},{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE","US"],"is_corresponding":true,"raw_author_name":"G. Heigold","raw_affiliation_strings":["Chair of Computer Science 6, RWTH Aachen University, Aachen, Germany","Microsoft Research Limited, USA"],"affiliations":[{"raw_affiliation_string":"Chair of Computer Science 6, RWTH Aachen University, Aachen, Germany","institution_ids":["https://openalex.org/I887968799"]},{"raw_affiliation_string":"Microsoft Research Limited, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","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":false,"raw_author_name":"G. Zweig","raw_affiliation_strings":["Microsoft Research Limited, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Limited, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000910355","display_name":"Xinran Li","orcid":"https://orcid.org/0000-0001-5701-1876"},"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":"X. Li","raw_affiliation_strings":["Microsoft Research Limited, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Limited, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083465496","display_name":"P. Nguyen","orcid":"https://orcid.org/0009-0007-9117-3570"},"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":"P. Nguyen","raw_affiliation_strings":["Microsoft Research Limited, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Limited, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5071956319"],"corresponding_institution_ids":["https://openalex.org/I1290206253","https://openalex.org/I887968799"],"apc_list":null,"apc_paid":null,"fwci":9.4607,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.9803264,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"15","issue":null,"first_page":"3861","last_page":"3864"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9995999932289124,"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":0.996999979019165,"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":0.9968000054359436,"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/hidden-markov-model","display_name":"Hidden Markov model","score":0.8138841390609741},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7774332165718079},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7549169063568115},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.709977924823761},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6269257068634033},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6114082336425781},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4547310769557953},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43505072593688965},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37666165828704834},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3238675594329834},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08794155716896057}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8138841390609741},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7774332165718079},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7549169063568115},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.709977924823761},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6269257068634033},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6114082336425781},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4547310769557953},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43505072593688965},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37666165828704834},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3238675594329834},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08794155716896057},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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/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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp.2009.4960470","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960470","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"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.149.9418","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.149.9418","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/80679/flat.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.895.3433","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.895.3433","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://mirlab.org/conference_papers/International_Conference/ICASSP%202009/pdfs/0003861.pdf","raw_type":"text"},{"id":"pmh:oai:publications.rwth-aachen.de:125765","is_oa":false,"landing_page_url":"https://publications.rwth-aachen.de/record/125765","pdf_url":null,"source":{"id":"https://openalex.org/S4306401362","display_name":"RWTH Publications (RWTH Aachen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887968799","host_organization_name":"RWTH Aachen University","host_organization_lineage":["https://openalex.org/I887968799"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE International Conference on Acoustics, Speech and Signal Processing, 2009 : ICASSP 2009 ; 19 - 24 April 2009, Taipei International Convention Center, Taipei, Taiwan ; proceedings / sponsored by the Institute of Electrical and Electronics Engineers Signal Processing Society. - Vol. 7<br/>IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2009, Taipei, Taiwan, 2009-04-19 - 2009-04-24","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.46000000834465027}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W44928787","https://openalex.org/W1996903695","https://openalex.org/W2040681044","https://openalex.org/W2095959744","https://openalex.org/W2097207027","https://openalex.org/W2099832642","https://openalex.org/W2143908786","https://openalex.org/W2156615793","https://openalex.org/W2158148237","https://openalex.org/W6601891056","https://openalex.org/W6660627308","https://openalex.org/W6683422774"],"related_works":["https://openalex.org/W2136763963","https://openalex.org/W2109705048","https://openalex.org/W2940588515","https://openalex.org/W1521297879","https://openalex.org/W2036150633","https://openalex.org/W3184123547","https://openalex.org/W1909151225","https://openalex.org/W2160030256","https://openalex.org/W2536059291","https://openalex.org/W4253235840"],"abstract_inverted_index":{"We":[0],"introduce":[1],"a":[2,87,122],"direct":[3,124],"model":[4,18,22,125],"for":[5,38,65,81],"speech":[6,39,69],"recognition":[7],"that":[8,90],"assumes":[9],"an":[10,119],"unstructured,":[11],"i.e.,":[12,115],"flat":[13,17,123],"text":[14],"output.":[15,29],"The":[16],"allows":[19,91],"us":[20],"to":[21,60,93,128],"arbitrary":[23],"attributes":[24],"and":[25,50,63,110,138,141,148],"dependences":[26,139],"of":[27,103,134],"the":[28,34,55,77,101,132,154],"This":[30,41,85],"is":[31,45,76,86],"different":[32,135],"from":[33],"HMMs":[35,57],"typically":[36],"used":[37],"recognition.":[40,70],"conventional":[42,155],"modeling":[43],"approach":[44],"based":[46],"on":[47,54],"sequential":[48],"data":[49],"makes":[51],"rigid":[52],"assumptions":[53],"dependences.":[56],"have":[58],"proven":[59],"be":[61,107],"convenient":[62],"appropriate":[64],"large":[66],"vocabulary":[67],"continuous":[68],"Our":[71],"task":[72],"under":[73],"consideration,":[74],"however,":[75],"Windows":[78],"Live":[79],"Search":[80],"Mobile":[82],"(WLS4M)":[83],"task.":[84],"cellphone":[88],"application":[89],"users":[92],"interact":[94],"with":[95],"web-based":[96],"information":[97],"portals.":[98],"In":[99],"particular,":[100],"set":[102],"valid":[104],"outputs":[105],"can":[106],"considered":[108],"discrete":[109],"finite":[111],"(although":[112],"probably":[113],"large,":[114],"unseen":[116],"events":[117],"are":[118],"issue).":[120],"Hence,":[121],"lends":[126],"itself":[127],"this":[129],"task,":[130],"making":[131],"adding":[133],"knowledge":[136],"sources":[137],"straightforward":[140],"cheap.":[142],"Using":[143],"e.g.":[144],"HMM":[145,156],"posterior,":[146],"m-gram,":[147],"spotter":[149],"features,":[150],"significant":[151],"improvements":[152],"over":[153],"system":[157],"were":[158],"observed.":[159]},"counts_by_year":[{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":5}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}