{"id":"https://openalex.org/W2126336864","doi":"https://doi.org/10.1109/icassp.2011.5947491","title":"Integrating meta-information into exemplar-based speech recognition with segmental conditional random fields","display_name":"Integrating meta-information into exemplar-based speech recognition with segmental conditional random fields","publication_year":2011,"publication_date":"2011-05-01","ids":{"openalex":"https://openalex.org/W2126336864","doi":"https://doi.org/10.1109/icassp.2011.5947491","mag":"2126336864"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2011.5947491","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947491","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5046536366","display_name":"Kris Demuynck","orcid":"https://orcid.org/0000-0001-8525-7160"},"institutions":[{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Kris Demuynck","raw_affiliation_strings":["ESAT, Katholieke Universiteit Leuven, Leuven, Belgium","Katholieke Universiteit Leuven - ESAT, Kasteelpark Arenberg 10, B-3001, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ESAT, Katholieke Universiteit Leuven, Leuven, Belgium","institution_ids":["https://openalex.org/I99464096"]},{"raw_affiliation_string":"Katholieke Universiteit Leuven - ESAT, Kasteelpark Arenberg 10, B-3001, Belgium","institution_ids":["https://openalex.org/I99464096"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113821007","display_name":"Dino Seppi","orcid":null},"institutions":[{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Dino Seppi","raw_affiliation_strings":["ESAT, Katholieke Universiteit Leuven, Leuven, Belgium","Katholieke Universiteit Leuven - ESAT, Kasteelpark Arenberg 10, B-3001, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ESAT, Katholieke Universiteit Leuven, Leuven, Belgium","institution_ids":["https://openalex.org/I99464096"]},{"raw_affiliation_string":"Katholieke Universiteit Leuven - ESAT, Kasteelpark Arenberg 10, B-3001, Belgium","institution_ids":["https://openalex.org/I99464096"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041039488","display_name":"Dirk Van Compernolle","orcid":"https://orcid.org/0000-0003-0075-848X"},"institutions":[{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Dirk Van Compernolle","raw_affiliation_strings":["ESAT, Katholieke Universiteit Leuven, Leuven, Belgium","Katholieke Universiteit Leuven - ESAT, Kasteelpark Arenberg 10, B-3001, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ESAT, Katholieke Universiteit Leuven, Leuven, Belgium","institution_ids":["https://openalex.org/I99464096"]},{"raw_affiliation_string":"Katholieke Universiteit Leuven - ESAT, Kasteelpark Arenberg 10, B-3001, Belgium","institution_ids":["https://openalex.org/I99464096"]}]},{"author_position":"middle","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]"],"raw_orcid":null,"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/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":"Geoffrey Zweig","raw_affiliation_strings":["Microsoft Research Limited, Redmond, WA, USA","[Microsoft Research,Redmond,WA,USA]"],"raw_orcid":null,"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":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.3965,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.94582344,"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":"5048","last_page":"5051"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9995999932289124,"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":0.9976999759674072,"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":0.7875411510467529},{"id":"https://openalex.org/keywords/conditional-random-field","display_name":"Conditional random field","score":0.7627449035644531},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6788346767425537},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.658222496509552},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6325918436050415},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.5744064450263977},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5513786673545837},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5215856432914734},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.4843248128890991},{"id":"https://openalex.org/keywords/conditional-entropy","display_name":"Conditional entropy","score":0.4587571620941162},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4300321042537689},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3675568699836731},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.3607632517814636},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0922245979309082}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7875411510467529},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.7627449035644531},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6788346767425537},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.658222496509552},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6325918436050415},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.5744064450263977},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5513786673545837},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5215856432914734},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.4843248128890991},{"id":"https://openalex.org/C101721835","wikidata":"https://www.wikidata.org/wiki/Q813908","display_name":"Conditional entropy","level":3,"score":0.4587571620941162},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4300321042537689},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3675568699836731},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.3607632517814636},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0922245979309082},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp.2011.5947491","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947491","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.228.3585","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.228.3585","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/icassp11_wsj_scarf.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.691.1296","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.691.1296","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+2011/pdfs/0005048.pdf","raw_type":"text"},{"id":"pmh:oai:lirias2repo.kuleuven.be:123456789/322568","is_oa":false,"landing_page_url":"https://lirias.kuleuven.be/bitstream/123456789/322568/1/3292.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306401954","display_name":"Lirias (KU Leuven)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I99464096","host_organization_name":"KU Leuven","host_organization_lineage":["https://openalex.org/I99464096"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"International conference on acoustics, speech and signal processing - ICASSP\u20192011, Prague, Czech Republic, 22-27 May 2011","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W75173072","https://openalex.org/W125657975","https://openalex.org/W143396524","https://openalex.org/W154225146","https://openalex.org/W157668738","https://openalex.org/W178496478","https://openalex.org/W1746705224","https://openalex.org/W2096303239","https://openalex.org/W2097207027","https://openalex.org/W2113601991","https://openalex.org/W2117809880","https://openalex.org/W2131033001","https://openalex.org/W2137089646","https://openalex.org/W2886038965","https://openalex.org/W6605843052","https://openalex.org/W6637710448"],"related_works":["https://openalex.org/W2011251309","https://openalex.org/W2150969560","https://openalex.org/W65845428","https://openalex.org/W2344132714","https://openalex.org/W2385117199","https://openalex.org/W4245698648","https://openalex.org/W1993729825","https://openalex.org/W2401394187","https://openalex.org/W2405257913","https://openalex.org/W3133710586"],"abstract_inverted_index":{"Exemplar":[0],"based":[1,49,126],"recognition":[2,99,113],"systems":[3,50],"are":[4],"characterized":[5],"by":[6,35],"the":[7,22,33,41,57,72,85,98,112,121,124,129,139,150],"fact":[8],"that,":[9],"instead":[10],"of":[11,15,47,69,74,87,123],"abstracting":[12],"large":[13],"amounts":[14],"data":[16,24,34],"into":[17,111],"compact":[18],"models,":[19],"they":[20],"store":[21],"observed":[23],"enriched":[25],"with":[26],"some":[27],"annotations":[28],"and":[29,105,141],"infer":[30],"on-the-fly":[31],"from":[32,84,134],"finding":[36],"those":[37],"exemplars":[38],"that":[39,52,91],"resemble":[40],"input":[42],"speech":[43],"best.":[44],"One":[45],"advantage":[46],"exemplar":[48,125],"is":[51,92],"next":[53],"to":[54,94,136,153],"deriving":[55],"what":[56],"current":[58],"phone":[59,144],"or":[60],"word":[61,102],"is,":[62],"one":[63],"can":[64],"easily":[65],"derive":[66],"a":[67],"wealth":[68],"meta-information":[70,83,110],"concerning":[71],"chunk":[73],"audio":[75],"under":[76],"investigation.":[77],"In":[78],"this":[79,109],"work":[80],"we":[81],"harvest":[82],"set":[86],"best":[88],"matching":[89],"exemplars,":[90],"thought":[93],"be":[95],"relevant":[96],"for":[97],"such":[100],"as":[101,146],"boundary":[103],"predictions":[104],"speaker":[106],"entropy.":[107],"Integrating":[108],"framework":[114],"using":[115],"segmental":[116],"conditional":[117],"random":[118],"fields,":[119],"reduced":[120,149],"WER":[122],"system":[127],"on":[128],"WSJ":[130],"Nov92":[131],"20k":[132],"task":[133],"8.2%":[135],"7.6%.":[137],"Adding":[138],"HMM-score":[140],"multiple":[142],"HMM":[143],"detectors":[145],"features":[147],"further":[148],"error":[151],"rate":[152],"6.6%.":[154]},"counts_by_year":[{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}