{"id":"https://openalex.org/W4292347840","doi":"https://doi.org/10.1109/taslp.2022.3198555","title":"Integrating Lattice-Free MMI Into End-to-End Speech Recognition","display_name":"Integrating Lattice-Free MMI Into End-to-End Speech Recognition","publication_year":2022,"publication_date":"2022-08-19","ids":{"openalex":"https://openalex.org/W4292347840","doi":"https://doi.org/10.1109/taslp.2022.3198555"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2022.3198555","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3198555","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":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2203.15614","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068192693","display_name":"Jinchuan Tian","orcid":"https://orcid.org/0000-0002-2129-471X"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]},{"id":"https://openalex.org/I4210108985","display_name":"Bellevue Hospital Center","ror":"https://ror.org/01ky34z31","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1283621791","https://openalex.org/I4210086933","https://openalex.org/I4210108985"]}],"countries":["CN","US"],"is_corresponding":true,"raw_author_name":"Jinchuan Tian","raw_affiliation_strings":["Tencent AI Lab, Bellevue, WA, USA","Advanced data and signal processing laboratory, School of Electric and Computer Science, Peking University, Shenzhen Graduate School, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Bellevue, WA, USA","institution_ids":["https://openalex.org/I4210108985"]},{"raw_affiliation_string":"Advanced data and signal processing laboratory, School of Electric and Computer Science, Peking University, Shenzhen Graduate School, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004643540","display_name":"Jianwei Yu","orcid":"https://orcid.org/0000-0002-2449-1436"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]},{"id":"https://openalex.org/I4210108985","display_name":"Bellevue Hospital Center","ror":"https://ror.org/01ky34z31","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1283621791","https://openalex.org/I4210086933","https://openalex.org/I4210108985"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Jianwei Yu","raw_affiliation_strings":["Tencent AI Lab, Bellevue, WA, USA","Advanced data and signal processing laboratory, School of Electric and Computer Science, Peking University, Shenzhen Graduate School, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Bellevue, WA, USA","institution_ids":["https://openalex.org/I4210108985"]},{"raw_affiliation_string":"Advanced data and signal processing laboratory, School of Electric and Computer Science, Peking University, Shenzhen Graduate School, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106404246","display_name":"Chao Weng","orcid":null},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]},{"id":"https://openalex.org/I4210108985","display_name":"Bellevue Hospital Center","ror":"https://ror.org/01ky34z31","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1283621791","https://openalex.org/I4210086933","https://openalex.org/I4210108985"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Chao Weng","raw_affiliation_strings":["Tencent AI Lab, Bellevue, WA, USA","Advanced data and signal processing laboratory, School of Electric and Computer Science, Peking University, Shenzhen Graduate School, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Bellevue, WA, USA","institution_ids":["https://openalex.org/I4210108985"]},{"raw_affiliation_string":"Advanced data and signal processing laboratory, School of Electric and Computer Science, Peking University, Shenzhen Graduate School, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002795838","display_name":"Yuexian Zou","orcid":"https://orcid.org/0000-0001-9999-6140"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]},{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuexian Zou","raw_affiliation_strings":["Advanced Data and Signal Processing Laboratory, School of Electric and Computer Science, Peking University Shenzhen Graduate School, Shenzhen, China","Advanced data and signal processing laboratory, School of Electric and Computer Science, Peking University, Shenzhen Graduate School, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Advanced Data and Signal Processing Laboratory, School of Electric and Computer Science, Peking University Shenzhen Graduate School, Shenzhen, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Advanced data and signal processing laboratory, School of Electric and Computer Science, Peking University, Shenzhen Graduate School, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034476404","display_name":"Dong Yu","orcid":"https://orcid.org/0000-0003-0520-6844"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]},{"id":"https://openalex.org/I4210108985","display_name":"Bellevue Hospital Center","ror":"https://ror.org/01ky34z31","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1283621791","https://openalex.org/I4210086933","https://openalex.org/I4210108985"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Dong Yu","raw_affiliation_strings":["Tencent AI Lab, Bellevue, WA, USA","Advanced data and signal processing laboratory, School of Electric and Computer Science, Peking University, Shenzhen Graduate School, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Bellevue, WA, USA","institution_ids":["https://openalex.org/I4210108985"]},{"raw_affiliation_string":"Advanced data and signal processing laboratory, School of Electric and Computer Science, Peking University, Shenzhen Graduate School, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5068192693"],"corresponding_institution_ids":["https://openalex.org/I180726961","https://openalex.org/I4210108985"],"apc_list":null,"apc_paid":null,"fwci":1.379,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.84159915,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"31","issue":null,"first_page":"25","last_page":"38"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9995999932289124,"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/T11309","display_name":"Music and Audio Processing","score":0.9977999925613403,"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":0.8750175833702087},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.7985894680023193},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7400716543197632},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5542991757392883},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5183616280555725},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4606509208679199},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.41636621952056885},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.339580774307251},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.18994084000587463}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8750175833702087},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.7985894680023193},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7400716543197632},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5542991757392883},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5183616280555725},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4606509208679199},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.41636621952056885},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.339580774307251},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.18994084000587463},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/taslp.2022.3198555","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3198555","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"},{"id":"pmh:oai:arXiv.org:2203.15614","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2203.15614","pdf_url":"https://arxiv.org/pdf/2203.15614","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2203.15614","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2203.15614","pdf_url":"https://arxiv.org/pdf/2203.15614","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.6800000071525574}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":69,"referenced_works":["https://openalex.org/W38527073","https://openalex.org/W1522301498","https://openalex.org/W1828163288","https://openalex.org/W1836465849","https://openalex.org/W1993721840","https://openalex.org/W1994216910","https://openalex.org/W2070737455","https://openalex.org/W2104036986","https://openalex.org/W2114016253","https://openalex.org/W2125234026","https://openalex.org/W2127141656","https://openalex.org/W2131342762","https://openalex.org/W2150907703","https://openalex.org/W2154887136","https://openalex.org/W2327501763","https://openalex.org/W2514741789","https://openalex.org/W2746192915","https://openalex.org/W2766219058","https://openalex.org/W2786459654","https://openalex.org/W2802248956","https://openalex.org/W2806471111","https://openalex.org/W2889048668","https://openalex.org/W2889163603","https://openalex.org/W2889282842","https://openalex.org/W2914018192","https://openalex.org/W2936774411","https://openalex.org/W2962780374","https://openalex.org/W2963242190","https://openalex.org/W2963308316","https://openalex.org/W2963747784","https://openalex.org/W3015190365","https://openalex.org/W3015470971","https://openalex.org/W3094979069","https://openalex.org/W3095376166","https://openalex.org/W3095697114","https://openalex.org/W3097777922","https://openalex.org/W3097798370","https://openalex.org/W3100732527","https://openalex.org/W3118026775","https://openalex.org/W3162665866","https://openalex.org/W3163793923","https://openalex.org/W3167533889","https://openalex.org/W3184976814","https://openalex.org/W3185108477","https://openalex.org/W3196321886","https://openalex.org/W3197478142","https://openalex.org/W3207936122","https://openalex.org/W4200629210","https://openalex.org/W4213423981","https://openalex.org/W4223954171","https://openalex.org/W4225741214","https://openalex.org/W4253573210","https://openalex.org/W4287634420","https://openalex.org/W4287647128","https://openalex.org/W4294619417","https://openalex.org/W4299649720","https://openalex.org/W4310658830","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6638667902","https://openalex.org/W6638749077","https://openalex.org/W6682398751","https://openalex.org/W6739901393","https://openalex.org/W6749954789","https://openalex.org/W6754473786","https://openalex.org/W6783314596","https://openalex.org/W6785131635","https://openalex.org/W6802929645","https://openalex.org/W6847376785"],"related_works":["https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W259157601","https://openalex.org/W4205463238","https://openalex.org/W2761785940","https://openalex.org/W1482209366","https://openalex.org/W2404514746","https://openalex.org/W1652783584","https://openalex.org/W2082783427"],"abstract_inverted_index":{"In":[0],"automatic":[1],"speech":[2],"recognition":[3],"(ASR)":[4],"research,":[5],"discriminative":[6,21,49,116],"criteria":[7,22],"have":[8,39],"achieved":[9],"superior":[10,188],"performance":[11,28,207],"in":[12,72,87,91,108,129,135],"DNN-HMM":[13],"systems.":[14,33,54],"Given":[15],"this":[16,35,102,109],"success,":[17],"the":[18,27,41,48,56,61,66,83,92,130,136,166,171,178,194],"adoption":[19],"of":[20,29,47,60],"is":[23,69,238],"promising":[24],"to":[25,111,204,217],"boost":[26],"end-to-end":[30],"(E2E)":[31],"ASR":[32,53,125],"With":[34],"motivation,":[36],"previous":[37],"works":[38],"introduced":[40],"minimum":[42],"Bayesian":[43],"risk":[44],"(MBR,":[45],"one":[46],"criteria)":[50],"into":[51,123],"E2E":[52,124,153],"However,":[55],"effectiveness":[57,148],"and":[58,81,97,143,158,175,201,212,232],"efficiency":[59],"MBR-based":[62,88,164],"methods":[63,89,145],"are":[64,106],"compromised:":[65],"MBR":[67,199],"criterion":[68],"only":[70,128],"used":[71,115,152],"system":[73],"training,":[74],"which":[75],"creates":[76],"a":[77],"mismatch":[78],"between":[79,173],"training":[80,99,131,142,174,189],"decoding;":[82,176],"on-the-fly":[84,179],"decoding":[85,137,144,180],"process":[86],"results":[90,227],"need":[93],"for":[94],"pre-trained":[95],"models":[96,186],"slow":[98],"speeds.":[100],"To":[101],"end,":[103],"novel":[104],"algorithms":[105],"proposed":[107,140,167,222],"work":[110],"integrate":[112],"another":[113],"widely":[114,151],"criterion,":[117],"lattice-free":[118],"maximum":[119],"mutual":[120],"information":[121],"(LF-MMI),":[122],"systems":[126],"not":[127],"stage":[132],"but":[133],"also":[134],"process.":[138],"The":[139,221],"LF-MMI":[141,168,195],"show":[146],"their":[147],"on":[149,209,228],"two":[150],"frameworks:":[154],"Attention-Based":[155],"Encoder-Decoders":[156],"(AEDs)":[157],"Neural":[159],"Transducers":[160],"(NTs).":[161],"Compared":[162],"with":[163,187],"methods,":[165],"method:":[169],"maintains":[170],"consistency":[172],"eschews":[177],"process;":[181],"trains":[182],"from":[183,214],"randomly":[184],"initialized":[185],"efficiency.":[190],"Experiments":[191],"suggest":[192],"that":[193],"method":[196,223],"outperforms":[197],"its":[198],"counterparts":[200],"consistently":[202],"leads":[203],"statistically":[205],"significant":[206],"improvements":[208],"various":[210],"frameworks":[211],"datasets":[213],"30":[215],"hours":[216],"14.3":[218],"k":[219],"hours.":[220],"achieves":[224],"state-of-the-art":[225],"(SOTA)":[226],"Aishell-1":[229],"(CER":[230,234],"4.10%)":[231],"Aishell-2":[233],"5.02%)":[235],"datasets.":[236],"Code":[237],"released":[239],"<sup":[240],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[241],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[242],".":[243]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}