{"id":"https://openalex.org/W2158333293","doi":"https://doi.org/10.1109/icassp.2002.5743661","title":"Direct models for phoneme recognition","display_name":"Direct models for phoneme recognition","publication_year":2002,"publication_date":"2002-05-01","ids":{"openalex":"https://openalex.org/W2158333293","doi":"https://doi.org/10.1109/icassp.2002.5743661","mag":"2158333293"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2002.5743661","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2002.5743661","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":"conference-paper","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/A5021425348","display_name":"Anton Lilchododev","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anton Lilchododev","raw_affiliation_strings":["School of Computer Science, Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074146436","display_name":"Yuqing Gao","orcid":"https://orcid.org/0000-0001-8709-8378"},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuqing Gao","raw_affiliation_strings":["IBM T. J. Watson Research Center, Yorktown Heights, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM T. J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"77","issue":null,"first_page":"I","last_page":"89"},"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":0.9993000030517578,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9991000294685364,"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":0.8406722545623779},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.774362325668335},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7044453620910645},{"id":"https://openalex.org/keywords/maximum-entropy-markov-model","display_name":"Maximum-entropy Markov model","score":0.6772186756134033},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.6504021883010864},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5749173760414124},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5536283254623413},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5249583721160889},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.5041772127151489},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.37243789434432983},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3216410279273987},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.2765350341796875},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.22078874707221985},{"id":"https://openalex.org/keywords/variable-order-markov-model","display_name":"Variable-order Markov model","score":0.17041534185409546}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8406722545623779},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.774362325668335},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7044453620910645},{"id":"https://openalex.org/C196956702","wikidata":"https://www.wikidata.org/wiki/Q6795829","display_name":"Maximum-entropy Markov model","level":5,"score":0.6772186756134033},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.6504021883010864},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5749173760414124},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5536283254623413},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5249583721160889},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.5041772127151489},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.37243789434432983},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3216410279273987},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.2765350341796875},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.22078874707221985},{"id":"https://openalex.org/C54907487","wikidata":"https://www.wikidata.org/wiki/Q7915688","display_name":"Variable-order Markov model","level":4,"score":0.17041534185409546},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2002.5743661","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2002.5743661","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/1","score":0.6100000143051147,"display_name":"No poverty"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W100642011","https://openalex.org/W1550597138","https://openalex.org/W1934019294","https://openalex.org/W1966812932","https://openalex.org/W2096175520","https://openalex.org/W2125838338","https://openalex.org/W2147880316","https://openalex.org/W2160842254","https://openalex.org/W6633101056","https://openalex.org/W6640267182","https://openalex.org/W6674650171","https://openalex.org/W6682082992"],"related_works":["https://openalex.org/W2134386692","https://openalex.org/W2379938888","https://openalex.org/W1510894296","https://openalex.org/W2116722627","https://openalex.org/W2176285001","https://openalex.org/W4233405330","https://openalex.org/W2082284720","https://openalex.org/W2194396582","https://openalex.org/W2799426416","https://openalex.org/W4246505579"],"abstract_inverted_index":{"This":[0],"paper":[1,41],"presents":[2],"the":[3,19,34,55,72,88,91,110,113],"theoretical":[4],"framework":[5],"of":[6,22,39,54,57,67,81,90,93,96,101,112],"a":[7,23,52],"new":[8,35,114],"statistical":[9],"model":[10,84,103],"for":[11],"phoneme":[12,104],"recognition.":[13],"In":[14],"contrast":[15],"with":[16,33,106],"traditional":[17],"HMMs,":[18],"posterior":[20],"probability":[21],"state":[24],"sequence":[25,29],"given":[26],"an":[27],"observation":[28],"is":[30,42],"computed":[31],"directly":[32],"model.":[36],"The":[37,64],"development":[38],"this":[40],"based":[43],"on":[44,117],"Maximum":[45,58],"Entropy":[46,59],"Markov":[47],"Models":[48],"(MEMMs[5]),":[49],"appearing":[50],"as":[51],"result":[53],"application":[56],"principle":[60],"to":[61,74],"sequential":[62],"processes.":[63],"main":[65],"contributions":[66],"our":[68],"work":[69],"include":[70],"modifying":[71],"MEMM":[73,92],"large-scale":[75],"speech":[76],"recognition":[77],"problem":[78],"and":[79],"introduction":[80],"another":[82],"direct":[83,102],"(NOM),":[85],"which":[86],"overcomes":[87],"shortcome":[89],"poor":[94],"representation":[95],"contextual":[97],"information.":[98],"Direct":[99],"comparison":[100],"recognizers":[105,108],"HMM-based":[107],"demonstrates":[109],"superiority":[111],"models,":[115],"particularly":[116],"smaller":[118],"training":[119],"sets.":[120]},"counts_by_year":[{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}