{"id":"https://openalex.org/W3162444624","doi":"https://doi.org/10.1109/icassp39728.2021.9413741","title":"Simpleflat: A Simple Whole-Network Pre-Training Approach for RNN Transducer-Based End-to-End Speech Recognition","display_name":"Simpleflat: A Simple Whole-Network Pre-Training Approach for RNN Transducer-Based End-to-End Speech Recognition","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3162444624","doi":"https://doi.org/10.1109/icassp39728.2021.9413741","mag":"3162444624"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9413741","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413741","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5087290011","display_name":"Takafumi Moriya","orcid":"https://orcid.org/0000-0003-1942-7250"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takafumi Moriya","raw_affiliation_strings":["NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033975068","display_name":"Takanori Ashihara","orcid":"https://orcid.org/0009-0003-4322-4127"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takanori Ashihara","raw_affiliation_strings":["NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101463708","display_name":"Tomohiro Tanaka","orcid":"https://orcid.org/0000-0002-9741-5573"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomohiro Tanaka","raw_affiliation_strings":["NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103151157","display_name":"Tsubasa Ochiai","orcid":"https://orcid.org/0000-0002-5422-6617"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tsubasa Ochiai","raw_affiliation_strings":["NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101739550","display_name":"Hiroshi Sato","orcid":"https://orcid.org/0000-0001-6575-0396"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroshi Sato","raw_affiliation_strings":["NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061074419","display_name":"Atsushi Ando","orcid":"https://orcid.org/0000-0002-3971-0654"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Atsushi Ando","raw_affiliation_strings":["NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068604686","display_name":"Yusuke Ijima","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yusuke Ijima","raw_affiliation_strings":["NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060644399","display_name":"Ryo Masumura","orcid":"https://orcid.org/0000-0002-2415-4149"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryo Masumura","raw_affiliation_strings":["NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109365728","display_name":"Yusuke Shinohara","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yusuke Shinohara","raw_affiliation_strings":["NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5664","last_page":"5668"},"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":0.9983999729156494,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9958000183105469,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.9008008241653442},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8150299787521362},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.6680881381034851},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6139836311340332},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.6039970517158508},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5650322437286377},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.5384867191314697},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4872135519981384},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4572543501853943},{"id":"https://openalex.org/keywords/cross-entropy","display_name":"Cross entropy","score":0.4141582250595093},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.4127407371997833},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3060606122016907},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.07558465003967285}],"concepts":[{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.9008008241653442},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8150299787521362},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.6680881381034851},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6139836311340332},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.6039970517158508},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5650322437286377},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.5384867191314697},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4872135519981384},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4572543501853943},{"id":"https://openalex.org/C167981619","wikidata":"https://www.wikidata.org/wiki/Q1685498","display_name":"Cross entropy","level":3,"score":0.4141582250595093},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.4127407371997833},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3060606122016907},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.07558465003967285},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","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},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9413741","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413741","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W6908809","https://openalex.org/W854541894","https://openalex.org/W1489125746","https://openalex.org/W1524333225","https://openalex.org/W1586532344","https://openalex.org/W1677182931","https://openalex.org/W1828163288","https://openalex.org/W2064675550","https://openalex.org/W2095705004","https://openalex.org/W2102113734","https://openalex.org/W2127141656","https://openalex.org/W2143612262","https://openalex.org/W2250357346","https://openalex.org/W2407080277","https://openalex.org/W2515439472","https://openalex.org/W2631415506","https://openalex.org/W2899771611","https://openalex.org/W2936774411","https://openalex.org/W2962780374","https://openalex.org/W2963250244","https://openalex.org/W2963403868","https://openalex.org/W2963414781","https://openalex.org/W2963920996","https://openalex.org/W2964038834","https://openalex.org/W2964084166","https://openalex.org/W2972818416","https://openalex.org/W3007328579","https://openalex.org/W3015190365","https://openalex.org/W3015194534","https://openalex.org/W3015315932","https://openalex.org/W3015686596","https://openalex.org/W4385245566","https://openalex.org/W6600284362","https://openalex.org/W6623517193","https://openalex.org/W6629052376","https://openalex.org/W6631362777","https://openalex.org/W6635078382","https://openalex.org/W6638749077","https://openalex.org/W6674330103","https://openalex.org/W6675365184","https://openalex.org/W6691509046","https://openalex.org/W6713762819","https://openalex.org/W6739901393","https://openalex.org/W6747398299","https://openalex.org/W6756040250"],"related_works":["https://openalex.org/W2970530566","https://openalex.org/W2967478618","https://openalex.org/W2997152889","https://openalex.org/W3179968364","https://openalex.org/W4385572700","https://openalex.org/W4388335561","https://openalex.org/W4307309205","https://openalex.org/W3015162217","https://openalex.org/W3034892578","https://openalex.org/W3161425572"],"abstract_inverted_index":{"Recurrent":[0],"neural":[1],"network-transducer":[2],"(RNN-T)":[3],"is":[4,38,63],"promising":[5],"for":[6,73],"building":[7],"time-synchronous":[8],"end-to-end":[9],"automatic":[10],"speech":[11],"recognition":[12],"(ASR)":[13],"systems,":[14],"in":[15,30,56,136],"part":[16],"because":[17],"it":[18,40,42],"does":[19,85],"not":[20,86],"need":[21],"frame-wise":[22,77,111],"alignment":[23,37],"between":[24,48],"input":[25,49],"features":[26,50],"and":[27,51,68,84,117,143],"target":[28,96],"labels":[29],"the":[31,46,81,121],"training":[32,35,82],"step.":[33],"Although":[34],"without":[36],"beneficial,":[39],"makes":[41],"difficult":[43],"to":[44,98],"discern":[45],"relation":[47],"output":[52,104],"token":[53],"sequences.":[54],"This,":[55],"effect,":[57],"degrades":[58],"RNN-T":[59,102,154],"performance.":[60],"Our":[61],"solution":[62],"SimpleFlat":[64],"(SF),":[65],"a":[66],"novel":[67],"simple":[69],"whole-network":[70],"pretraining":[71],"approach":[72],"RNN-T.":[74],"SF":[75,126,149],"extracts":[76],"alignments":[78],"on-the-fly":[79],"from":[80],"dataset,":[83],"require":[87],"any":[88],"external":[89],"resources.":[90],"We":[91],"distribute":[92],"equal":[93],"numbers":[94],"of":[95],"tokens":[97,112],"each":[99,108],"frame":[100],"following":[101],"encoder":[103],"lengths":[105],"by":[106,130],"repeating":[107],"token.":[109],"The":[110],"so":[113],"created":[114],"are":[115],"shifted,":[116],"also":[118],"used":[119],"as":[120,135],"prediction":[122],"network":[123],"inputs.":[124],"Therefore,":[125],"can":[127,150],"be":[128],"implemented":[129],"cross":[131],"entropy":[132],"loss":[133],"computation":[134],"autoregressive":[137],"model":[138],"training.":[139],"Experiments":[140],"on":[141],"Japanese":[142],"English":[144],"ASR":[145],"tasks":[146],"demonstrate":[147],"that":[148],"effectively":[151],"improve":[152],"various":[153],"architectures.":[155]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}