{"id":"https://openalex.org/W2808939837","doi":"https://doi.org/10.1109/taslp.2018.2848701","title":"Flat-Start Single-Stage Discriminatively Trained HMM-Based Models for ASR","display_name":"Flat-Start Single-Stage Discriminatively Trained HMM-Based Models for ASR","publication_year":2018,"publication_date":"2018-06-18","ids":{"openalex":"https://openalex.org/W2808939837","doi":"https://doi.org/10.1109/taslp.2018.2848701","mag":"2808939837"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2018.2848701","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2018.2848701","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5041855151","display_name":"Hossein Hadian","orcid":"https://orcid.org/0000-0002-1083-6026"},"institutions":[{"id":"https://openalex.org/I133529467","display_name":"Sharif University of Technology","ror":"https://ror.org/024c2fq17","country_code":"IR","type":"education","lineage":["https://openalex.org/I133529467"]}],"countries":["IR"],"is_corresponding":true,"raw_author_name":"Hossein Hadian","raw_affiliation_strings":["Department of Computer Engineering, Sharif University of Technology, Tehran, Iran"],"affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, Sharif University of Technology, Tehran, Iran","institution_ids":["https://openalex.org/I133529467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024773257","display_name":"Hossein Sameti","orcid":"https://orcid.org/0000-0002-8087-8889"},"institutions":[{"id":"https://openalex.org/I133529467","display_name":"Sharif University of Technology","ror":"https://ror.org/024c2fq17","country_code":"IR","type":"education","lineage":["https://openalex.org/I133529467"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Hossein Sameti","raw_affiliation_strings":["Department of Computer Engineering, Sharif University of Technology, Tehran, Iran"],"affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, Sharif University of Technology, Tehran, Iran","institution_ids":["https://openalex.org/I133529467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084286453","display_name":"Daniel Povey","orcid":"https://orcid.org/0000-0002-0611-3634"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Povey","raw_affiliation_strings":["Johns Hopkins University, Baltimore, MD, USA"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014580424","display_name":"Sanjeev Khudanpur","orcid":"https://orcid.org/0000-0001-5976-0897"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sanjeev Khudanpur","raw_affiliation_strings":["Johns Hopkins University, Baltimore, MD, USA"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5041855151"],"corresponding_institution_ids":["https://openalex.org/I133529467"],"apc_list":null,"apc_paid":null,"fwci":4.8865,"has_fulltext":false,"cited_by_count":47,"citation_normalized_percentile":{"value":0.96050039,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":"26","issue":"11","first_page":"1949","last_page":"1961"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9990000128746033,"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/T10860","display_name":"Speech and Audio Processing","score":0.9987999796867371,"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/hidden-markov-model","display_name":"Hidden Markov model","score":0.9048441052436829},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8087068796157837},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7253924608230591},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6384947896003723},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5633291602134705},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5555962920188904},{"id":"https://openalex.org/keywords/mutual-information","display_name":"Mutual information","score":0.5251566767692566},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48260343074798584},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4791280925273895},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4602585732936859},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.451294869184494},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.44785597920417786},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.4460328221321106},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.41010528802871704},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3326255679130554},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0751003623008728}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.9048441052436829},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8087068796157837},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7253924608230591},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6384947896003723},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5633291602134705},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5555962920188904},{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.5251566767692566},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48260343074798584},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4791280925273895},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4602585732936859},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.451294869184494},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.44785597920417786},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.4460328221321106},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.41010528802871704},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3326255679130554},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0751003623008728},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2018.2848701","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2018.2848701","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6899999976158142,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":92,"referenced_works":["https://openalex.org/W811578723","https://openalex.org/W1489125746","https://openalex.org/W1524333225","https://openalex.org/W1553004968","https://openalex.org/W1586532344","https://openalex.org/W1736701665","https://openalex.org/W1828163288","https://openalex.org/W1877570817","https://openalex.org/W1922655562","https://openalex.org/W1986184096","https://openalex.org/W1987238397","https://openalex.org/W2002342963","https://openalex.org/W2003123121","https://openalex.org/W2019973879","https://openalex.org/W2024490156","https://openalex.org/W2064675550","https://openalex.org/W2079623482","https://openalex.org/W2098318492","https://openalex.org/W2102113734","https://openalex.org/W2107223151","https://openalex.org/W2117671523","https://openalex.org/W2125838338","https://openalex.org/W2126002878","https://openalex.org/W2127141656","https://openalex.org/W2130942839","https://openalex.org/W2131342762","https://openalex.org/W2131702393","https://openalex.org/W2133564696","https://openalex.org/W2147768505","https://openalex.org/W2150769028","https://openalex.org/W2156373089","https://openalex.org/W2158069733","https://openalex.org/W2160815625","https://openalex.org/W2166637769","https://openalex.org/W2171244697","https://openalex.org/W2173629880","https://openalex.org/W2193413348","https://openalex.org/W2251321385","https://openalex.org/W2291513470","https://openalex.org/W2293858598","https://openalex.org/W2404568753","https://openalex.org/W2407080277","https://openalex.org/W2514741789","https://openalex.org/W2545177271","https://openalex.org/W2577366047","https://openalex.org/W2597757402","https://openalex.org/W2729190387","https://openalex.org/W2739427748","https://openalex.org/W2748816379","https://openalex.org/W2749066063","https://openalex.org/W2766219058","https://openalex.org/W2802422770","https://openalex.org/W2962824709","https://openalex.org/W2962826786","https://openalex.org/W2962962542","https://openalex.org/W2963211739","https://openalex.org/W2963403868","https://openalex.org/W2963414781","https://openalex.org/W2963483399","https://openalex.org/W2963747784","https://openalex.org/W2963827914","https://openalex.org/W2963920996","https://openalex.org/W2963970535","https://openalex.org/W2964038834","https://openalex.org/W4385245566","https://openalex.org/W6629052376","https://openalex.org/W6631362777","https://openalex.org/W6635078382","https://openalex.org/W6638749077","https://openalex.org/W6640090968","https://openalex.org/W6675365184","https://openalex.org/W6679434410","https://openalex.org/W6679436768","https://openalex.org/W6687566353","https://openalex.org/W6691770337","https://openalex.org/W6713570806","https://openalex.org/W6713762819","https://openalex.org/W6726109732","https://openalex.org/W6728910023","https://openalex.org/W6732447497","https://openalex.org/W6735390525","https://openalex.org/W6739901393","https://openalex.org/W6741807409","https://openalex.org/W6743049199","https://openalex.org/W6743100949","https://openalex.org/W6745801839","https://openalex.org/W6746892368","https://openalex.org/W6746924902","https://openalex.org/W6747398299","https://openalex.org/W6749557976","https://openalex.org/W6749566584","https://openalex.org/W6751267225"],"related_works":["https://openalex.org/W2150890698","https://openalex.org/W3133710586","https://openalex.org/W2401394187","https://openalex.org/W4245698648","https://openalex.org/W2405257913","https://openalex.org/W2125964738","https://openalex.org/W2098529290","https://openalex.org/W2026402306","https://openalex.org/W1566315437","https://openalex.org/W2151348424"],"abstract_inverted_index":{"In":[0,50],"recent":[1],"years,":[2],"end-to-end":[3,170],"approaches":[4],"to":[5,112,116,120,161,168],"automatic":[6],"speech":[7,75],"recognition":[8],"have":[9],"received":[10],"considerable":[11],"attention":[12],"as":[13,138,140],"they":[14],"are":[15,177],"much":[16,110],"faster":[17,111],"in":[18,85],"terms":[19],"of":[20,32,58,103],"preparing":[21],"resources.":[22],"However,":[23],"conventional":[24],"multistage":[25],"approaches,":[26],"which":[27,94],"rely":[28],"on":[29,47,172],"a":[30,87,91],"pipeline":[31],"training":[33,57],"hidden":[34],"Markov":[35],"models":[36,38],"(HMM)-GMM":[37],"and":[39,89,126],"tree-building":[40],"steps":[41],"still":[42],"give":[43],"the":[44,104],"state-of-the-art":[45,105],"results":[46],"most":[48],"databases.":[49,174,181],"this":[51,154],"study,":[52],"we":[53],"investigate":[54],"flat-start":[55,122,149],"one-stage":[56],"neural":[59],"networks":[60],"using":[61],"lattice-free":[62],"maximum":[63],"mutual":[64],"information":[65],"(LF-MMI)":[66],"objective":[67],"function":[68],"with":[69,101,153],"HMM":[70],"for":[71,179],"large":[72],"vocabulary":[73],"continuous":[74],"recognition.":[76],"We":[77,114,145],"thoroughly":[78],"look":[79],"into":[80],"different":[81],"issues":[82],"that":[83,102,130,147],"arise":[84],"such":[86],"setup":[88,151],"propose":[90,115],"standalone":[92],"system,":[93],"achieves":[95,159],"word":[96],"error":[97],"rates":[98],"(WER)":[99],"comparable":[100],"multi-stage":[106],"systems":[107],"while":[108],"being":[109],"prepare.":[113],"use":[117],"full":[118],"biphones":[119],"enable":[121],"context-dependent":[123],"(CD)":[124],"modeling":[125,133,157],"show":[127,146],"through":[128],"experiments":[129],"our":[131,148],"CD":[132,143,156],"approach":[134],"can":[135],"be":[136],"almost":[137],"effective":[139],"regular":[141],"tree-based":[142],"modeling.":[144],"LF-MMI":[150],"together":[152],"tree-free":[155],"technique":[158],"10":[160],"25":[162],"%":[163],"relative":[164],"WER":[165],"reduction":[166],"compared":[167],"other":[169],"methods":[171],"well-known":[173],"The":[175],"improvements":[176],"larger":[178],"smaller":[180]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}