{"id":"https://openalex.org/W3146505093","doi":"https://doi.org/10.1109/slt48900.2021.9383623","title":"Benchmarking LF-MMI, CTC And RNN-T Criteria For Streaming ASR","display_name":"Benchmarking LF-MMI, CTC And RNN-T Criteria For Streaming ASR","publication_year":2021,"publication_date":"2021-01-19","ids":{"openalex":"https://openalex.org/W3146505093","doi":"https://doi.org/10.1109/slt48900.2021.9383623","mag":"3146505093"},"language":"en","primary_location":{"id":"doi:10.1109/slt48900.2021.9383623","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383623","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Spoken Language Technology Workshop (SLT)","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/A5088378499","display_name":"Xiaohui Zhang","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":true,"raw_author_name":"Xiaohui Zhang","raw_affiliation_strings":["Facebook AI, USA"],"affiliations":[{"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"],"affiliations":[{"raw_affiliation_string":"Facebook AI, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069296252","display_name":"Chunxi Liu","orcid":"https://orcid.org/0000-0001-5441-9374"},"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":"Chunxi Liu","raw_affiliation_strings":["Facebook AI, USA"],"affiliations":[{"raw_affiliation_string":"Facebook AI, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071330839","display_name":"Kjell Schubert","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":"Kjell Schubert","raw_affiliation_strings":["Facebook AI, USA"],"affiliations":[{"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"],"affiliations":[{"raw_affiliation_string":"Facebook AI, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109295048","display_name":"Pradyot Prakash","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":"Pradyot Prakash","raw_affiliation_strings":["Facebook AI, USA"],"affiliations":[{"raw_affiliation_string":"Facebook AI, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100361857","display_name":"Jun Liu","orcid":"https://orcid.org/0000-0002-4365-4165"},"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":"Jun Liu","raw_affiliation_strings":["Facebook AI, USA"],"affiliations":[{"raw_affiliation_string":"Facebook AI, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087421101","display_name":"Ching-Feng Yeh","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":"Ching-Feng Yeh","raw_affiliation_strings":["Facebook AI, USA"],"affiliations":[{"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"],"affiliations":[{"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"],"affiliations":[{"raw_affiliation_string":"Facebook AI, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069954850","display_name":"Geoffrey Zweig","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":"Geoffrey Zweig","raw_affiliation_strings":["Facebook AI, USA"],"affiliations":[{"raw_affiliation_string":"Facebook AI, USA","institution_ids":["https://openalex.org/I4210114444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":11,"corresponding_author_ids":["https://openalex.org/A5088378499"],"corresponding_institution_ids":["https://openalex.org/I4210114444"],"apc_list":null,"apc_paid":null,"fwci":2.3115,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.90087898,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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":0.9994000196456909,"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":0.9993000030517578,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.854905366897583},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8416776657104492},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7349860668182373},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.7003357410430908},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6468541622161865},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5520145297050476},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5138207077980042},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.4943974018096924},{"id":"https://openalex.org/keywords/low-latency","display_name":"Low latency (capital markets)","score":0.48528334498405457},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4445127248764038},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4439942538738251},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4154480993747711},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3538598418235779},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.1972743570804596}],"concepts":[{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.854905366897583},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8416776657104492},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7349860668182373},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.7003357410430908},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6468541622161865},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5520145297050476},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5138207077980042},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.4943974018096924},{"id":"https://openalex.org/C46637626","wikidata":"https://www.wikidata.org/wiki/Q6693015","display_name":"Low latency (capital markets)","level":2,"score":0.48528334498405457},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4445127248764038},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4439942538738251},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4154480993747711},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3538598418235779},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.1972743570804596},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt48900.2021.9383623","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383623","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.8199999928474426,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1494198834","https://openalex.org/W1828163288","https://openalex.org/W2033256038","https://openalex.org/W2127141656","https://openalex.org/W2327501763","https://openalex.org/W2407080277","https://openalex.org/W2514741789","https://openalex.org/W2545177271","https://openalex.org/W2936774411","https://openalex.org/W2963240019","https://openalex.org/W2963827914","https://openalex.org/W2966163367","https://openalex.org/W2972630480","https://openalex.org/W2981436362","https://openalex.org/W2981857663","https://openalex.org/W2987019345","https://openalex.org/W3001899777","https://openalex.org/W3007227084","https://openalex.org/W3008525923","https://openalex.org/W3008870153","https://openalex.org/W3008898571","https://openalex.org/W3014408449","https://openalex.org/W3015654466","https://openalex.org/W3015960524","https://openalex.org/W3029982911","https://openalex.org/W3095311338","https://openalex.org/W3095962459","https://openalex.org/W3096104971","https://openalex.org/W3097558625","https://openalex.org/W3142252347","https://openalex.org/W3144557079","https://openalex.org/W3149509723","https://openalex.org/W6623517193","https://openalex.org/W6638749077","https://openalex.org/W6713762819","https://openalex.org/W6741807409","https://openalex.org/W6757793448","https://openalex.org/W6769067932","https://openalex.org/W6770245836","https://openalex.org/W6775557069","https://openalex.org/W6775822104","https://openalex.org/W6785229415","https://openalex.org/W6785660780","https://openalex.org/W6786300550"],"related_works":["https://openalex.org/W4238897586","https://openalex.org/W435179959","https://openalex.org/W2619091065","https://openalex.org/W2341842940","https://openalex.org/W1490753184","https://openalex.org/W2284465472","https://openalex.org/W2291782699","https://openalex.org/W1993948687","https://openalex.org/W2160451571","https://openalex.org/W2914172742"],"abstract_inverted_index":{"In":[0,31],"this":[1],"work,":[2],"to":[3,103],"measure":[4],"the":[5,109],"accuracy":[6],"and":[7,29,57],"efficiency":[8],"for":[9,85],"a":[10,121],"latency-controlled":[11],"streaming":[12,100],"automatic":[13],"speech":[14],"recognition":[15],"(ASR)":[16],"application,":[17,102],"we":[18,46,79,107],"perform":[19],"comprehensive":[20,111],"evaluations":[21],"on":[22,113],"three":[23,115],"popular":[24],"training":[25,40,87,118],"criteria:":[26],"LF-MMI,":[27],"CTC":[28,72],"RNN-T.":[30],"transcribing":[32],"social":[33],"media":[34],"videos":[35],"of":[36],"7":[37],"languages":[38],"with":[39],"data":[41],"3K":[42],"-":[43],"14K":[44],"hours,":[45],"conduct":[47],"large-scale":[48,98],"controlled":[49],"experimentation":[50],"across":[51,120],"each":[52],"criterion":[53],"using":[54],"identical":[55],"datasets":[56],"encoder":[58,92],"model":[59],"architecture.":[60],"We":[61],"find":[62],"that":[63],"RNN-T":[64],"has":[65],"consistent":[66],"wins":[67],"in":[68],"ASR":[69,101],"accuracy,":[70],"while":[71],"models":[73],"excel":[74],"at":[75],"inference":[76],"efficiency.":[77],"Moreover,":[78],"selectively":[80],"examine":[81],"various":[82],"modeling":[83,90],"strategies":[84],"different":[86],"criteria,":[88],"including":[89],"units,":[91],"architectures,":[93],"pre-training,":[94],"etc.":[95],"Given":[96],"such":[97],"real-world":[99],"our":[104],"best":[105],"knowledge,":[106],"present":[108],"first":[110],"benchmark":[112],"these":[114],"widely":[116],"used":[117],"criteria":[119],"great":[122],"many":[123],"languages.":[124]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}