{"id":"https://openalex.org/W2080758042","doi":"https://doi.org/10.1109/icassp.2002.5743864","title":"Towards knowledge-based features for HMM based large vocabulary automatic speech recognition","display_name":"Towards knowledge-based features for HMM based large vocabulary automatic speech recognition","publication_year":2002,"publication_date":"2002-05-01","ids":{"openalex":"https://openalex.org/W2080758042","doi":"https://doi.org/10.1109/icassp.2002.5743864","mag":"2080758042"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2002.5743864","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2002.5743864","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/A5041198797","display_name":"Benoit Launay","orcid":null},"institutions":[{"id":"https://openalex.org/I1322087612","display_name":"Alcatel Lucent (Germany)","ror":"https://ror.org/00c5mwp75","country_code":"DE","type":"company","lineage":["https://openalex.org/I1322087612"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Benoit Launay","raw_affiliation_strings":["Multimedia Communications Research Lab, Bell Laboratories, Lucent Technologies, Inc., Murray Hill, NJ, USA","Multimedia Communications Research Lab, Bell Laboratories - Lucent Technologies, 600 Mountain Ave., Murray Hill, NJ 07974, USA"],"affiliations":[{"raw_affiliation_string":"Multimedia Communications Research Lab, Bell Laboratories, Lucent Technologies, Inc., Murray Hill, NJ, USA","institution_ids":[]},{"raw_affiliation_string":"Multimedia Communications Research Lab, Bell Laboratories - Lucent Technologies, 600 Mountain Ave., Murray Hill, NJ 07974, USA","institution_ids":["https://openalex.org/I1322087612"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005881531","display_name":"Olivier Siohan","orcid":null},"institutions":[{"id":"https://openalex.org/I1322087612","display_name":"Alcatel Lucent (Germany)","ror":"https://ror.org/00c5mwp75","country_code":"DE","type":"company","lineage":["https://openalex.org/I1322087612"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Olivier Siohan","raw_affiliation_strings":["Multimedia Communications Research Lab, Bell Laboratories, Lucent Technologies, Inc., Murray Hill, NJ, USA","Multimedia Communications Research Lab, Bell Laboratories - Lucent Technologies, 600 Mountain Ave., Murray Hill, NJ 07974, USA"],"affiliations":[{"raw_affiliation_string":"Multimedia Communications Research Lab, Bell Laboratories, Lucent Technologies, Inc., Murray Hill, NJ, USA","institution_ids":[]},{"raw_affiliation_string":"Multimedia Communications Research Lab, Bell Laboratories - Lucent Technologies, 600 Mountain Ave., Murray Hill, NJ 07974, USA","institution_ids":["https://openalex.org/I1322087612"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104102129","display_name":"Arun C. Surendran","orcid":null},"institutions":[{"id":"https://openalex.org/I1322087612","display_name":"Alcatel Lucent (Germany)","ror":"https://ror.org/00c5mwp75","country_code":"DE","type":"company","lineage":["https://openalex.org/I1322087612"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Arun Surendran","raw_affiliation_strings":["Multimedia Communications Research Lab, Bell Laboratories, Lucent Technologies, Inc., Murray Hill, NJ, USA","Multimedia Communications Research Lab, Bell Laboratories - Lucent Technologies, 600 Mountain Ave., Murray Hill, NJ 07974, USA"],"affiliations":[{"raw_affiliation_string":"Multimedia Communications Research Lab, Bell Laboratories, Lucent Technologies, Inc., Murray Hill, NJ, USA","institution_ids":[]},{"raw_affiliation_string":"Multimedia Communications Research Lab, Bell Laboratories - Lucent Technologies, 600 Mountain Ave., Murray Hill, NJ 07974, USA","institution_ids":["https://openalex.org/I1322087612"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066868860","display_name":"Chin\u2010Hui Lee","orcid":"https://orcid.org/0000-0002-1892-2551"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Chin-Hui Lee","raw_affiliation_strings":["Department of Computer Science, National University of Singapore, Singapore","Department of Computer Science, National University of Singapore, Singapore,"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"Department of Computer Science, National University of Singapore, Singapore,","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5041198797"],"corresponding_institution_ids":["https://openalex.org/I1322087612"],"apc_list":null,"apc_paid":null,"fwci":2.7843,"has_fulltext":false,"cited_by_count":32,"citation_normalized_percentile":{"value":0.92483444,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"I","last_page":"817"},"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/T11309","display_name":"Music and Audio Processing","score":0.9970999956130981,"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":0.9959999918937683,"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/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.9154423475265503},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8283334970474243},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7962144613265991},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.7749379873275757},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7666319608688354},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5313820242881775},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5307457447052002},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.49723532795906067},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.4901622235774994},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4389336407184601},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.43137550354003906},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.4229670763015747},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.37211519479751587},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06905984878540039}],"concepts":[{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.9154423475265503},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8283334970474243},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7962144613265991},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.7749379873275757},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7666319608688354},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5313820242881775},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5307457447052002},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.49723532795906067},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.4901622235774994},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4389336407184601},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.43137550354003906},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.4229670763015747},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.37211519479751587},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06905984878540039},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2002.5743864","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2002.5743864","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"},{"id":"pmh:oai:scholarbank.nus.edu.sg:10635/40246","is_oa":false,"landing_page_url":"http://scholarbank.nus.edu.sg/handle/10635/40246","pdf_url":null,"source":{"id":"https://openalex.org/S7407052290","display_name":"National University of Singapore","issn_l":null,"issn":[],"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":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Scopus","raw_type":"Conference Paper"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5199999809265137,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W45736138","https://openalex.org/W1484387534","https://openalex.org/W1490506669","https://openalex.org/W1505035441","https://openalex.org/W1536990986","https://openalex.org/W1598851216","https://openalex.org/W1904457459","https://openalex.org/W1985836220","https://openalex.org/W2000100543","https://openalex.org/W2117647530","https://openalex.org/W2140356185","https://openalex.org/W2152134037","https://openalex.org/W2160017196","https://openalex.org/W6629271487","https://openalex.org/W6682467914"],"related_works":["https://openalex.org/W2018086531","https://openalex.org/W1980297060","https://openalex.org/W2387604097","https://openalex.org/W4385672897","https://openalex.org/W2373675101","https://openalex.org/W106160982","https://openalex.org/W2359140082","https://openalex.org/W1556565948","https://openalex.org/W4245698648","https://openalex.org/W2405257913"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"an":[3,60],"attempt":[4],"to":[5,17,49,67,72,141],"design":[6],"a":[7,88,105,110,123],"knowledge-based":[8],"large":[9,89],"vocabulary":[10,90],"speech":[11,43],"recognition":[12],"system.":[13],"Our":[14],"motivation":[15],"is":[16],"replace":[18],"features":[19,32,40,71,86],"based":[20,133],"on":[21,96,134,153],"the":[22,38,42,73,97,120,128,135,154],"short-term":[23,69],"spectra,":[24],"such":[25,104],"as":[26,85],"Mel-frequency":[27],"cepstral":[28],"coefficients":[29],"(MFCC),":[30],"by":[31],"that":[33,103],"explicitly":[34],"represent":[35],"some":[36,77],"of":[37,41,53,76,122,130,148],"distinctive":[39,55,78],"signal.":[44],"However,":[45],"rather":[46],"than":[47],"attempting":[48],"compute":[50],"acoustic":[51],"correlates":[52],"these":[54],"features,":[56],"we":[57,138],"have":[58],"engineered":[59],"approach":[61],"where":[62],"neural":[63],"networks":[64],"are":[65,82],"trained":[66],"map":[68],"spectral":[70],"posterior":[74],"probability":[75],"features.":[79],"These":[80],"probabilities":[81],"then":[83],"used":[84],"in":[87,144],"tied-state":[91],"HMM-based":[92],"recognizer.":[93],"Experimental":[94],"results":[95,121,129],"Wall":[98],"Street":[99],"Journal":[100],"Task":[101],"show":[102],"system,":[106,112],"while":[107],"not":[108],"outperforming":[109],"MFCC-based":[111,163],"generates":[113],"very":[114],"different":[115],"error":[116,146],"patterns.":[117],"After":[118],"combining":[119],"base-line":[124],"MFCC":[125],"system":[126],"with":[127],"several":[131],"systems":[132],"proposed":[136],"approach,":[137],"were":[139],"able":[140],"obtain":[142],"reductions":[143],"word":[145],"rates":[147],"19%":[149],"and":[150,156],"10":[151],"%":[152],"5K":[155],"20K":[157],"tasks":[158],"respectively":[159],"over":[160],"our":[161],"best":[162],"systems.":[164]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}