{"id":"https://openalex.org/W3015766686","doi":"https://doi.org/10.1109/icassp40776.2020.9053499","title":"Frame-Level MMI as A Sequence Discriminative Training Criterion for LVCSR","display_name":"Frame-Level MMI as A Sequence Discriminative Training Criterion for LVCSR","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015766686","doi":"https://doi.org/10.1109/icassp40776.2020.9053499","mag":"3015766686"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053499","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053499","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5029547617","display_name":"Wilfried Michel","orcid":null},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Wilfried Michel","raw_affiliation_strings":["Human Language Technology and Pattern Recognition, RWTH Aachen University, Aachen, Germany"],"affiliations":[{"raw_affiliation_string":"Human Language Technology and Pattern Recognition, RWTH Aachen University, Aachen, Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088968292","display_name":"Ralf Schl\u00fcter","orcid":"https://orcid.org/0000-0003-2839-9247"},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ralf Schluter","raw_affiliation_strings":["Human Language Technology and Pattern Recognition, RWTH Aachen University, Aachen, Germany"],"affiliations":[{"raw_affiliation_string":"Human Language Technology and Pattern Recognition, RWTH Aachen University, Aachen, Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112501010","display_name":"Hermann Ney","orcid":null},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Hermann Ney","raw_affiliation_strings":["Human Language Technology and Pattern Recognition, RWTH Aachen University, Aachen, Germany"],"affiliations":[{"raw_affiliation_string":"Human Language Technology and Pattern Recognition, RWTH Aachen University, Aachen, Germany","institution_ids":["https://openalex.org/I887968799"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5029547617"],"corresponding_institution_ids":["https://openalex.org/I887968799"],"apc_list":null,"apc_paid":null,"fwci":0.3977,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.67323195,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"15","issue":null,"first_page":"6904","last_page":"6908"},"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":0.9997000098228455,"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":0.9991999864578247,"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":0.8186327219009399},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.6474584937095642},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5991979837417603},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5907425284385681},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5568912625312805},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48820406198501587},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46415480971336365},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.45368799567222595},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4308111369609833},{"id":"https://openalex.org/keywords/interpolation","display_name":"Interpolation (computer graphics)","score":0.4248323440551758},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.36974281072616577},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.10076794028282166}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8186327219009399},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.6474584937095642},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5991979837417603},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5907425284385681},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5568912625312805},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48820406198501587},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46415480971336365},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.45368799567222595},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4308111369609833},{"id":"https://openalex.org/C137800194","wikidata":"https://www.wikidata.org/wiki/Q11713455","display_name":"Interpolation (computer graphics)","level":3,"score":0.4248323440551758},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.36974281072616577},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.10076794028282166},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053499","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053499","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7699999809265137,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W38527073","https://openalex.org/W1542311097","https://openalex.org/W1920923476","https://openalex.org/W2095705004","https://openalex.org/W2112739286","https://openalex.org/W2131342762","https://openalex.org/W2158510249","https://openalex.org/W2263490141","https://openalex.org/W2891778781","https://openalex.org/W2905489173","https://openalex.org/W2963351448","https://openalex.org/W2963747784","https://openalex.org/W4297781872","https://openalex.org/W6601546718","https://openalex.org/W6632425951","https://openalex.org/W6674330103","https://openalex.org/W6676716484","https://openalex.org/W6692956712","https://openalex.org/W6746924902","https://openalex.org/W6755054617","https://openalex.org/W6757717501"],"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/W2053269318","https://openalex.org/W2110523656","https://openalex.org/W2364370872"],"abstract_inverted_index":{"In":[0],"this":[1,69],"work":[2],"we":[3,29,52],"present":[4],"frame-level":[5,32,121],"maximum":[6],"mutual":[7],"information":[8],"(MMI)":[9],"as":[10],"a":[11,91,111],"novel":[12],"sequence":[13],"discriminative":[14],"training":[15,64,80,115],"criterion":[16,28,70,88],"for":[17],"hybrid":[18],"HMM-DNN":[19],"acoustic":[20],"models.":[21],"Compared":[22],"to":[23,73,90],"the":[24,56,74,82,95],"standard,":[25],"sequence-level":[26],"MMI":[27,33,122],"show":[30,53],"that":[31,54,117],"has":[34],"increased":[35],"robustness":[36],"towards":[37],"missing":[38],"cross-entropy":[39],"(CE)":[40],"smoothing":[41],"and":[42,123],"can":[43],"converge":[44],"even":[45],"without":[46],"interpolation.":[47],"Using":[48],"model":[49],"free":[50],"optimization,":[51],"in":[55],"asymptotic":[57],"case":[58],"of":[59,63,94,114],"an":[60],"infinite":[61],"amount":[62],"data":[65],"models":[66],"trained":[67],"using":[68,81],"are":[71],"equal":[72],"true":[75,96],"class":[76,97,113],"posterior":[77,98],"distribution,":[78],"whereas":[79],"state-level":[83],"minimum":[84],"Bayes":[85],"risk":[86],"(sMBR)":[87],"leads":[89],"distorted":[92],"function":[93],"distribution.":[99],"This":[100],"analytical":[101],"result":[102],"is":[103],"backed":[104],"by":[105],"experimental":[106],"evidence.":[107],"We":[108],"further":[109],"propose":[110],"generalized":[112],"criteria,":[116],"continuously":[118],"interpolates":[119],"between":[120],"sMBR":[124],"criterion.":[125]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}