{"id":"https://openalex.org/W2021343534","doi":"https://doi.org/10.1109/slt.2014.7078547","title":"Document-based Dirichlet class language model for speech recognition using document-based n-gram events","display_name":"Document-based Dirichlet class language model for speech recognition using document-based n-gram events","publication_year":2014,"publication_date":"2014-12-01","ids":{"openalex":"https://openalex.org/W2021343534","doi":"https://doi.org/10.1109/slt.2014.7078547","mag":"2021343534"},"language":"en","primary_location":{"id":"doi:10.1109/slt.2014.7078547","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2014.7078547","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE Spoken Language Technology Workshop (SLT)","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/A5003389639","display_name":"Md. Akmal Haidar","orcid":null},"institutions":[{"id":"https://openalex.org/I39481719","display_name":"Institut National de la Recherche Scientifique","ror":"https://ror.org/04td37d32","country_code":"CA","type":"education","lineage":["https://openalex.org/I39481719","https://openalex.org/I49663120"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Md. Akmal Haidar","raw_affiliation_strings":["INRS-EMT, Montreal, Quebec, Canada","INRS-EMT, 6900-800 De La Gauchetiere Ouest, Montreal (Quebec), H5A 1K6, Canada"],"affiliations":[{"raw_affiliation_string":"INRS-EMT, Montreal, Quebec, Canada","institution_ids":["https://openalex.org/I39481719"]},{"raw_affiliation_string":"INRS-EMT, 6900-800 De La Gauchetiere Ouest, Montreal (Quebec), H5A 1K6, Canada","institution_ids":["https://openalex.org/I39481719"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011489869","display_name":"Douglas O\u2019Shaughnessy","orcid":"https://orcid.org/0000-0002-0110-2346"},"institutions":[{"id":"https://openalex.org/I39481719","display_name":"Institut National de la Recherche Scientifique","ror":"https://ror.org/04td37d32","country_code":"CA","type":"education","lineage":["https://openalex.org/I39481719","https://openalex.org/I49663120"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Douglas O'Shaughnessy","raw_affiliation_strings":["INRS-EMT, Montreal, Quebec, Canada","INRS-EMT, 6900-800 De La Gauchetiere Ouest, Montreal (Quebec), H5A 1K6, Canada"],"affiliations":[{"raw_affiliation_string":"INRS-EMT, Montreal, Quebec, Canada","institution_ids":["https://openalex.org/I39481719"]},{"raw_affiliation_string":"INRS-EMT, 6900-800 De La Gauchetiere Ouest, Montreal (Quebec), H5A 1K6, Canada","institution_ids":["https://openalex.org/I39481719"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5003389639"],"corresponding_institution_ids":["https://openalex.org/I39481719"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.07514118,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"42","last_page":"47"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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/T10181","display_name":"Natural Language Processing Techniques","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/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":0.9991999864578247,"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/perplexity","display_name":"Perplexity","score":0.9232977628707886},{"id":"https://openalex.org/keywords/n-gram","display_name":"n-gram","score":0.8355802297592163},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.7536451816558838},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.708479106426239},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.610144317150116},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6098976731300354},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5695136785507202},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5689131021499634},{"id":"https://openalex.org/keywords/part-of-speech","display_name":"Part of speech","score":0.5640431046485901},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5515180826187134},{"id":"https://openalex.org/keywords/latent-dirichlet-allocation","display_name":"Latent Dirichlet allocation","score":0.5449205636978149},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5014019012451172},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.45895370841026306},{"id":"https://openalex.org/keywords/gram","display_name":"Gram","score":0.4459347724914551},{"id":"https://openalex.org/keywords/dirichlet-distribution","display_name":"Dirichlet distribution","score":0.4318516254425049},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.28530681133270264},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.15000909566879272},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14573094248771667}],"concepts":[{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.9232977628707886},{"id":"https://openalex.org/C117884012","wikidata":"https://www.wikidata.org/wiki/Q94489","display_name":"n-gram","level":3,"score":0.8355802297592163},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.7536451816558838},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.708479106426239},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.610144317150116},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6098976731300354},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5695136785507202},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5689131021499634},{"id":"https://openalex.org/C123406163","wikidata":"https://www.wikidata.org/wiki/Q82042","display_name":"Part of speech","level":2,"score":0.5640431046485901},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5515180826187134},{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.5449205636978149},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5014019012451172},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.45895370841026306},{"id":"https://openalex.org/C161369605","wikidata":"https://www.wikidata.org/wiki/Q41803","display_name":"Gram","level":3,"score":0.4459347724914551},{"id":"https://openalex.org/C169214877","wikidata":"https://www.wikidata.org/wiki/Q981016","display_name":"Dirichlet distribution","level":3,"score":0.4318516254425049},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.28530681133270264},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.15000909566879272},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14573094248771667},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C523546767","wikidata":"https://www.wikidata.org/wiki/Q10876","display_name":"Bacteria","level":2,"score":0.0},{"id":"https://openalex.org/C182310444","wikidata":"https://www.wikidata.org/wiki/Q1332643","display_name":"Boundary value problem","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt.2014.7078547","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2014.7078547","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.5099999904632568,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W21664255","https://openalex.org/W179875071","https://openalex.org/W1612003148","https://openalex.org/W1631260214","https://openalex.org/W1644652583","https://openalex.org/W1880262756","https://openalex.org/W1934041838","https://openalex.org/W1970689298","https://openalex.org/W1974515274","https://openalex.org/W1991696363","https://openalex.org/W1992196410","https://openalex.org/W2024490156","https://openalex.org/W2031284124","https://openalex.org/W2071315630","https://openalex.org/W2106901945","https://openalex.org/W2114062410","https://openalex.org/W2118714763","https://openalex.org/W2121227244","https://openalex.org/W2122028591","https://openalex.org/W2127836646","https://openalex.org/W2132551194","https://openalex.org/W2134237567","https://openalex.org/W2145989470","https://openalex.org/W2147152072","https://openalex.org/W2159382562","https://openalex.org/W2171928131","https://openalex.org/W2998704965","https://openalex.org/W3127686677","https://openalex.org/W4231510805","https://openalex.org/W4285719527","https://openalex.org/W6636440780","https://openalex.org/W6636811518","https://openalex.org/W6639619044","https://openalex.org/W6643925177","https://openalex.org/W6677041336","https://openalex.org/W6678277124","https://openalex.org/W6680532216","https://openalex.org/W6681846153","https://openalex.org/W6789826613"],"related_works":["https://openalex.org/W4206967254","https://openalex.org/W4293734197","https://openalex.org/W2761847515","https://openalex.org/W2131689821","https://openalex.org/W2250993361","https://openalex.org/W2132221452","https://openalex.org/W2393111077","https://openalex.org/W2787311093","https://openalex.org/W2151348424","https://openalex.org/W2153295945"],"abstract_inverted_index":{"We":[0,127,160],"propose":[1,136],"a":[2,66,137,165],"document-based":[3,13,152,157],"Dirichlet":[4],"class":[5,20,39,53,122,148],"language":[6],"model":[7,71,134,139],"(DDCLM)":[8],"for":[9,124,150],"speech":[10,167],"recognition":[11,168],"using":[12,155,171],"n-gram":[14,63,97,112,158],"events.":[15,159],"In":[16,48],"this":[17,129],"model,":[18,51],"the":[19,24,29,32,37,38,41,44,49,52,58,70,73,76,80,85,88,93,96,111,115,120,125,132,142,147,151,156,172,182,195],"is":[21,34],"conditioned":[22,35],"on":[23,36,164],"immediate":[25],"history":[26,60,153],"context":[27,154],"and":[28,31,40,135,178,188],"document,":[30],"word":[33,189],"document":[42],"in":[43,87,99,131],"original":[45],"DCLM":[46,50,133],"model.":[47],"information":[54,123,149],"was":[55],"obtained":[56],"from":[57],"(n-1)":[59],"words":[61],"of":[62,65,75,82,84,95,114],"events":[64],"training":[67],"corpus.":[68,89],"Here,":[69],"uses":[72],"count":[74],"n-grams,":[77],"which":[78],"are":[79,92],"number":[81],"appearances":[83],"n-grams":[86],"These":[90],"counts":[91,98,113],"sum":[94],"different":[100,108],"documents":[101],"where":[102],"they":[103],"could":[104],"appear":[105],"to":[106],"describe":[107],"topics.":[109],"Therefore,":[110],"corpus":[116,177],"may":[117],"not":[118],"yield":[119],"proper":[121],"histories.":[126],"encounter":[128],"problem":[130,144],"DDCLM":[138],"that":[140,181],"overcomes":[141],"above":[143],"by":[145],"finding":[146],"carried":[161],"out":[162],"experiments":[163],"continuous":[166],"(CSR)":[169],"task":[170],"Wall":[173],"Street":[174],"Journal":[175],"(WSJ)":[176],"have":[179],"seen":[180],"proposed":[183],"approach":[184],"shows":[185],"significant":[186],"perplexity":[187],"error":[190],"rate":[191],"(WER)":[192],"reductions":[193],"over":[194],"other":[196],"approach.":[197]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}