{"id":"https://openalex.org/W2158592557","doi":"https://doi.org/10.1109/icassp.2002.5743667","title":"A dynamic in-search discriminative training approach for large vocabulary speech recognition","display_name":"A dynamic in-search discriminative training approach for large vocabulary speech recognition","publication_year":2002,"publication_date":"2002-05-01","ids":{"openalex":"https://openalex.org/W2158592557","doi":"https://doi.org/10.1109/icassp.2002.5743667","mag":"2158592557"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2002.5743667","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2002.5743667","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"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/A5101454723","display_name":"Hui Jiang","orcid":"https://orcid.org/0000-0003-4062-7206"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Hui Jiang","raw_affiliation_strings":["Dialogue Systems Research, Multimedia Communication Research Lab, Bell Laboratories, Lucent Technologies, Inc., Murray Hill, NJ, USA"],"affiliations":[{"raw_affiliation_string":"Dialogue Systems Research, Multimedia Communication Research Lab, Bell Laboratories, Lucent Technologies, Inc., Murray Hill, NJ, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005881531","display_name":"Olivier Siohan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Olivier Siohan","raw_affiliation_strings":["Dialogue Systems Research, Multimedia Communication Research Lab, Bell Laboratories, Lucent Technologies, Inc., Murray Hill, NJ, USA"],"affiliations":[{"raw_affiliation_string":"Dialogue Systems Research, Multimedia Communication Research Lab, Bell Laboratories, Lucent Technologies, Inc., Murray Hill, NJ, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065394791","display_name":"Frank K. Soong","orcid":"https://orcid.org/0000-0002-9088-3577"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Frank K. Soong","raw_affiliation_strings":["Dialogue Systems Research, Multimedia Communication Research Lab, Bell Laboratories, Lucent Technologies, Inc., Murray Hill, NJ, USA"],"affiliations":[{"raw_affiliation_string":"Dialogue Systems Research, Multimedia Communication Research Lab, Bell Laboratories, Lucent Technologies, Inc., Murray Hill, NJ, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066868860","display_name":"Chin\u2010Hui Lee","orcid":"https://orcid.org/0000-0002-1892-2551"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chin-Hui Lee","raw_affiliation_strings":["Dialogue Systems Research, Multimedia Communication Research Lab, Bell Laboratories, Lucent Technologies, Inc., Murray Hill, NJ, USA"],"affiliations":[{"raw_affiliation_string":"Dialogue Systems Research, Multimedia Communication Research Lab, Bell Laboratories, Lucent Technologies, Inc., Murray Hill, NJ, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101454723"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0652,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.78245501,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"I","last_page":"113"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9929999709129333,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9922999739646912,"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/discriminative-model","display_name":"Discriminative model","score":0.8884537220001221},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8144105672836304},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.8124799728393555},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.8109726905822754},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7195996046066284},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6377921104431152},{"id":"https://openalex.org/keywords/viterbi-algorithm","display_name":"Viterbi algorithm","score":0.6097401976585388},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5399470329284668},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.47566288709640503},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4349597692489624}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8884537220001221},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8144105672836304},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.8124799728393555},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8109726905822754},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7195996046066284},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6377921104431152},{"id":"https://openalex.org/C60582962","wikidata":"https://www.wikidata.org/wiki/Q83886","display_name":"Viterbi algorithm","level":3,"score":0.6097401976585388},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5399470329284668},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.47566288709640503},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4349597692489624},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2002.5743667","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2002.5743667","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE International Conference on Acoustics Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.7400000095367432}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W155109787","https://openalex.org/W1481751294","https://openalex.org/W1877570817","https://openalex.org/W2063541597","https://openalex.org/W2108672476","https://openalex.org/W2115678687","https://openalex.org/W2158289097","https://openalex.org/W6606294064","https://openalex.org/W6628832040"],"related_works":["https://openalex.org/W2136652457","https://openalex.org/W2169849734","https://openalex.org/W2167155152","https://openalex.org/W2116722627","https://openalex.org/W2129150969","https://openalex.org/W2236912844","https://openalex.org/W1975869217","https://openalex.org/W2401728283","https://openalex.org/W2383829109","https://openalex.org/W2379938888"],"abstract_inverted_index":{"In":[0,81],"this":[1,82],"paper,":[2],"we":[3],"propose":[4],"a":[5,12,106,127],"dynamic":[6],"in-search":[7],"discriminative":[8,66,147],"training":[9,67,91,123,148],"approach":[10,99],"of":[11,72,122],"large-scale":[13,128],"HMM":[14],"model":[15],"for":[16,55,132],"large":[17,120,133],"vocabulary":[18,134],"speech":[19],"recognition.":[20],"A":[21],"previously":[22],"proposed":[23,98],"data":[24,92,124],"selection":[25],"method":[26,113,149],"is":[27,100],"used":[28],"to":[29,51,68,103,118],"choose":[30],"competing":[31,53,79],"hypotheses":[32],"dynamically":[33],"during":[34,46],"Viterbi":[35],"beam":[36],"search":[37,47],"procedure.":[38],"Particularly,":[39],"all":[40,77],"active":[41],"word-ending":[42],"paths":[43],"are":[44,60],"examined":[45],"with":[48],"reference":[49],"transcription":[50],"identify":[52],"tokens":[54,75],"different":[56],"HMM's.":[57],"Then":[58],"HMMs":[59],"re-estimated":[61],"based":[62],"on":[63,140],"an":[64],"GPD-based":[65],"minimize":[69],"total":[70],"number":[71],"possible":[73],"error":[74,88],"among":[76],"collected":[78],"tokens.":[80],"way,":[83],"recognition":[84,135,152],"errors,":[85],"e.g.,":[86],"word":[87],"rate,":[89],"in":[90,105],"can":[93,114,150],"be":[94,116],"reduced":[95],"indirectly.":[96],"The":[97],"flexible":[101],"enough":[102],"run":[104],"batch":[107],"or":[108],"incremental":[109],"mode.":[110],"Also,":[111],"the":[112,145],"efficiently":[115],"implemented":[117],"process":[119],"amount":[121],"and":[125],"update":[126],"state-tied":[129],"HMM:":[130],"set":[131],"tasks.":[136],"Some":[137],"preliminary":[138],"results":[139],"DARPA":[141],"communicator":[142],"task":[143],"show":[144],"new":[146],"improve":[151],"performance":[153],"over":[154],"our":[155],"best":[156],"ML-trained":[157],"system.":[158]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}