{"id":"https://openalex.org/W4225741214","doi":"https://doi.org/10.1109/asru51503.2021.9688056","title":"On Lattice-Free Boosted MMI Training of HMM and CTC-Based Full-Context ASR Models","display_name":"On Lattice-Free Boosted MMI Training of HMM and CTC-Based Full-Context ASR Models","publication_year":2021,"publication_date":"2021-12-13","ids":{"openalex":"https://openalex.org/W4225741214","doi":"https://doi.org/10.1109/asru51503.2021.9688056"},"language":"en","primary_location":{"id":"doi:10.1109/asru51503.2021.9688056","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9688056","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5100400244","display_name":"Xiaohui Zhang","orcid":"https://orcid.org/0000-0002-9075-0336"},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xiaohui Zhang","raw_affiliation_strings":["Facebook AI,USA","Facebook AI, USA"],"affiliations":[{"raw_affiliation_string":"Facebook AI,USA","institution_ids":["https://openalex.org/I4210114444"]},{"raw_affiliation_string":"Facebook AI, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028956985","display_name":"Vimal Manohar","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vimal Manohar","raw_affiliation_strings":["Facebook AI,USA","Facebook AI, USA"],"affiliations":[{"raw_affiliation_string":"Facebook AI,USA","institution_ids":["https://openalex.org/I4210114444"]},{"raw_affiliation_string":"Facebook AI, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100325058","display_name":"David Zhang","orcid":"https://orcid.org/0000-0002-5027-5286"},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Zhang","raw_affiliation_strings":["Facebook AI,USA","Facebook AI, USA"],"affiliations":[{"raw_affiliation_string":"Facebook AI,USA","institution_ids":["https://openalex.org/I4210114444"]},{"raw_affiliation_string":"Facebook AI, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101984914","display_name":"Frank Zhang","orcid":"https://orcid.org/0000-0001-9946-6502"},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Frank Zhang","raw_affiliation_strings":["Facebook AI,USA","Facebook AI, USA"],"affiliations":[{"raw_affiliation_string":"Facebook AI,USA","institution_ids":["https://openalex.org/I4210114444"]},{"raw_affiliation_string":"Facebook AI, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103247973","display_name":"Yangyang Shi","orcid":"https://orcid.org/0000-0001-5297-4155"},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yangyang Shi","raw_affiliation_strings":["Facebook AI,USA","Facebook AI, USA"],"affiliations":[{"raw_affiliation_string":"Facebook AI,USA","institution_ids":["https://openalex.org/I4210114444"]},{"raw_affiliation_string":"Facebook AI, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038170826","display_name":"Nayan Singhal","orcid":"https://orcid.org/0000-0002-3189-6693"},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nayan Singhal","raw_affiliation_strings":["Facebook AI,USA","Facebook AI, USA"],"affiliations":[{"raw_affiliation_string":"Facebook AI,USA","institution_ids":["https://openalex.org/I4210114444"]},{"raw_affiliation_string":"Facebook AI, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051075420","display_name":"Julian Chan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Julian Chan","raw_affiliation_strings":["Facebook AI,USA","Facebook AI, USA"],"affiliations":[{"raw_affiliation_string":"Facebook AI,USA","institution_ids":["https://openalex.org/I4210114444"]},{"raw_affiliation_string":"Facebook AI, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047400593","display_name":"Fuchun Peng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fuchun Peng","raw_affiliation_strings":["Facebook AI,USA","Facebook AI, USA"],"affiliations":[{"raw_affiliation_string":"Facebook AI,USA","institution_ids":["https://openalex.org/I4210114444"]},{"raw_affiliation_string":"Facebook AI, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051165898","display_name":"Yatharth Saraf","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yatharth Saraf","raw_affiliation_strings":["Facebook AI,USA","Facebook AI, USA"],"affiliations":[{"raw_affiliation_string":"Facebook AI,USA","institution_ids":["https://openalex.org/I4210114444"]},{"raw_affiliation_string":"Facebook AI, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113773386","display_name":"Mike Seltzer","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mike Seltzer","raw_affiliation_strings":["Facebook AI,USA","Facebook AI, USA"],"affiliations":[{"raw_affiliation_string":"Facebook AI,USA","institution_ids":["https://openalex.org/I4210114444"]},{"raw_affiliation_string":"Facebook AI, USA","institution_ids":["https://openalex.org/I4210114444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5100400244"],"corresponding_institution_ids":["https://openalex.org/I4210114444"],"apc_list":null,"apc_paid":null,"fwci":1.2566,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.83968966,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1026","last_page":"1033"},"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":0.9979000091552734,"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":0.9961000084877014,"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":0.808677077293396},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7113338112831116},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.7037606239318848},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5992357730865479},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4994490146636963},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4971671402454376},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.4772738814353943},{"id":"https://openalex.org/keywords/network-topology","display_name":"Network topology","score":0.434301495552063},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42948126792907715},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3690912127494812},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3544950485229492},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.23276370763778687}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.808677077293396},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7113338112831116},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.7037606239318848},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5992357730865479},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4994490146636963},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4971671402454376},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.4772738814353943},{"id":"https://openalex.org/C199845137","wikidata":"https://www.wikidata.org/wiki/Q145490","display_name":"Network topology","level":2,"score":0.434301495552063},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42948126792907715},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3690912127494812},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3544950485229492},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.23276370763778687},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru51503.2021.9688056","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9688056","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8500000238418579,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1524333225","https://openalex.org/W1533416326","https://openalex.org/W1828163288","https://openalex.org/W1877570817","https://openalex.org/W2048060899","https://openalex.org/W2064675550","https://openalex.org/W2124558353","https://openalex.org/W2125234026","https://openalex.org/W2143612262","https://openalex.org/W2147768505","https://openalex.org/W2158069733","https://openalex.org/W2327501763","https://openalex.org/W2400997536","https://openalex.org/W2402146185","https://openalex.org/W2404463488","https://openalex.org/W2406513788","https://openalex.org/W2514741789","https://openalex.org/W2802248956","https://openalex.org/W2808939837","https://openalex.org/W2886949521","https://openalex.org/W2900209846","https://openalex.org/W2936774411","https://openalex.org/W2939297570","https://openalex.org/W2962824709","https://openalex.org/W2962826786","https://openalex.org/W2963164596","https://openalex.org/W2963250244","https://openalex.org/W3003285202","https://openalex.org/W3008525923","https://openalex.org/W3028545098","https://openalex.org/W3097558625","https://openalex.org/W3097777922","https://openalex.org/W3144557079","https://openalex.org/W3146505093","https://openalex.org/W3149509723","https://openalex.org/W3162665866","https://openalex.org/W3198004110","https://openalex.org/W6629717138","https://openalex.org/W6631362777","https://openalex.org/W6638749077","https://openalex.org/W6761305474","https://openalex.org/W6762146994","https://openalex.org/W6778184438","https://openalex.org/W6793540458","https://openalex.org/W7027429494"],"related_works":["https://openalex.org/W2136763963","https://openalex.org/W2109705048","https://openalex.org/W2940588515","https://openalex.org/W1521297879","https://openalex.org/W2036150633","https://openalex.org/W3184123547","https://openalex.org/W1909151225","https://openalex.org/W1987783679","https://openalex.org/W2160030256","https://openalex.org/W2536059291"],"abstract_inverted_index":{"Hybrid":[0],"automatic":[1],"speech":[2],"recognition":[3],"(ASR)":[4],"models":[5,140,146],"are":[6,22,113,122],"typically":[7],"sequentially":[8],"trained":[9],"with":[10,79,95],"CTC":[11],"or":[12],"LF-MMI":[13,63],"criteria.":[14],"However,":[15],"they":[16],"have":[17],"vastly":[18],"different":[19,26,96,110],"legacies":[20],"and":[21,38,41,73,93,103,118,120],"usually":[23],"implemented":[24],"in":[25,98],"frameworks.":[27],"In":[28,57],"this":[29,58,84],"paper,":[30],"by":[31],"decoupling":[32],"the":[33],"concepts":[34],"of":[35,109],"modeling":[36,55],"units":[37],"label":[39],"topologies":[40],"building":[42],"proper":[43],"numerator/denominator":[44],"graphs":[45],"accordingly,":[46],"we":[47,60,86,135],"establish":[48],"a":[49,65],"generalized":[50],"framework":[51],"for":[52,76],"hybrid":[53],"acoustic":[54],"(AM).":[56],"framework,":[59,85],"show":[61,131,137],"that":[62],"is":[64],"powerful":[66],"training":[67,90,99,111],"criterion":[68],"applicable":[69],"to":[70,130],"both":[71,80],"limited-context":[72],"full-context":[74],"models,":[75],"wordpiece/mono-char/bi-char/chenone":[77],"units,":[78],"HMM/CTC":[81],"topologies.":[82],"From":[83],"propose":[87],"three":[88],"novel":[89],"schemes:":[91],"chenone(ch)/wordpiece(wp)-CTC-bMMI,":[92],"wordpiece(wp)-HMM-bMMI":[94],"advantages":[97,108],"performance,":[100],"decoding":[101,104],"efficiency":[102],"time-stamp":[105],"accuracy.":[106],"The":[107],"schemes":[112],"evaluated":[114,123],"comprehensively":[115],"on":[116,124],"Librispeech,":[117],"wp-CTC-bMMI":[119],"ch-CTC-bMMI":[121],"two":[125],"real":[126],"world":[127],"ASR":[128],"tasks":[129],"their":[132],"effectiveness.":[133],"Besides,":[134],"also":[136],"bi-char(bc)":[138],"HMM-MMI":[139],"can":[141],"serve":[142],"as":[143],"better":[144],"alignment":[145],"than":[147],"traditional":[148],"non-neural":[149],"GMM-HMMs.":[150]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}