{"id":"https://openalex.org/W4372266855","doi":"https://doi.org/10.1109/icassp49357.2023.10095826","title":"Improving Scheduled Sampling for Neural Transducer-Based ASR","display_name":"Improving Scheduled Sampling for Neural Transducer-Based ASR","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372266855","doi":"https://doi.org/10.1109/icassp49357.2023.10095826"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095826","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095826","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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","NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]},{"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","NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059753087","display_name":"Hiroshi Sato","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":"Hiroshi Sato","raw_affiliation_strings":["NTT Corporation,Japan","NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014468963","display_name":"Kohei Matsuura","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":"Kohei Matsuura","raw_affiliation_strings":["NTT Corporation,Japan","NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007415728","display_name":"Tomohiro Tanaka","orcid":"https://orcid.org/0000-0002-8884-9089"},"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","NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","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","NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]},{"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":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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":0.9987999796867371,"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":0.9972000122070312,"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/security-token","display_name":"Security token","score":0.8369650840759277},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8345831036567688},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7332618236541748},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.7246153354644775},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6742775440216064},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.6704902648925781},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.5357519388198853},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5091843008995056},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.49849963188171387},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.47822684049606323},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.456339031457901},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4412020146846771},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.4162524342536926},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35164517164230347},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.19949784874916077},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.11690914630889893},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.07629168033599854},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.0717799961566925}],"concepts":[{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.8369650840759277},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8345831036567688},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7332618236541748},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.7246153354644775},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6742775440216064},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.6704902648925781},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.5357519388198853},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5091843008995056},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.49849963188171387},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.47822684049606323},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.456339031457901},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4412020146846771},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.4162524342536926},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35164517164230347},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.19949784874916077},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.11690914630889893},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.07629168033599854},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0717799961566925},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095826","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095826","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W37526647","https://openalex.org/W648786980","https://openalex.org/W1586532344","https://openalex.org/W1828163288","https://openalex.org/W2127141656","https://openalex.org/W2166637769","https://openalex.org/W2250357346","https://openalex.org/W2407080277","https://openalex.org/W2936774411","https://openalex.org/W2962780374","https://openalex.org/W2972991710","https://openalex.org/W3008037978","https://openalex.org/W3015190365","https://openalex.org/W3015726069","https://openalex.org/W3016234571","https://openalex.org/W3096318498","https://openalex.org/W3096518646","https://openalex.org/W3097777922","https://openalex.org/W3152221657","https://openalex.org/W3160551958","https://openalex.org/W3162444624","https://openalex.org/W3163560333","https://openalex.org/W3197202691","https://openalex.org/W3197267207","https://openalex.org/W3197507772","https://openalex.org/W3198254488","https://openalex.org/W3198654230","https://openalex.org/W4224518768","https://openalex.org/W4224916448","https://openalex.org/W4224920108","https://openalex.org/W4297841877","https://openalex.org/W4385245566","https://openalex.org/W6601563604","https://openalex.org/W6621543089","https://openalex.org/W6635078382","https://openalex.org/W6638749077","https://openalex.org/W6691509046","https://openalex.org/W6739901393","https://openalex.org/W6810174810"],"related_works":["https://openalex.org/W4388335561","https://openalex.org/W2970530566","https://openalex.org/W4288261899","https://openalex.org/W4307309205","https://openalex.org/W2967478618","https://openalex.org/W4385009901","https://openalex.org/W4385572700","https://openalex.org/W2997152889","https://openalex.org/W4387768015","https://openalex.org/W2171218219"],"abstract_inverted_index":{"The":[0],"recurrent":[1],"neural":[2],"network-transducer":[3],"(RNNT)":[4],"is":[5,65,104],"a":[6,18,52,66,87,186],"promising":[7],"approach":[8,177],"for":[9,38,107,118,144],"automatic":[10],"speech":[11],"recognition":[12,53],"(ASR)":[13],"with":[14,82,174],"the":[15,28,31,39,56,91,122,131,150,154,179,194],"introduction":[16],"of":[17,121,156],"prediction":[19],"network":[20],"that":[21,171],"autoregressively":[22],"considers":[23],"linguistic":[24],"aspects.":[25],"To":[26],"train":[27,69],"autoregressive":[29,70],"part,":[30],"ground-truth":[32,80],"tokens":[33,81,151],"are":[34],"used":[35,106],"as":[36,99],"substitutions":[37],"previous":[40,195],"output":[41,134],"token,":[42],"which":[43],"leads":[44,58],"to":[45,48,59,68,73,127,130],"insufficient":[46],"robustness":[47],"incorrect":[49],"past":[50,74],"tokens;":[51],"error":[54],"in":[55,124,167],"decoding":[57,96],"further":[60],"errors.":[61],"Scheduled":[62],"sampling":[63],"(SS)":[64],"technique":[67],"model":[71,162],"robustly":[72],"errors":[75],"by":[76],"randomly":[77],"replacing":[78],"some":[79],"actual":[83],"outputs":[84],"generated":[85,152],"from":[86,153],"model.":[88],"SS":[89,112,126,141,147,176],"mitigates":[90],"gaps":[92],"between":[93],"training":[94],"and":[95,102],"steps,":[97],"known":[98],"exposure":[100],"bias,":[101],"it":[103],"often":[105],"attentional":[108],"encoder-decoder":[109],"training.":[110],"However":[111],"has":[113],"not":[114],"been":[115],"fully":[116],"examined":[117],"RNNT":[119,128,133,157,164,172],"because":[120],"difficulty":[123],"applying":[125],"due":[129],"complicated":[132],"form.":[135],"In":[136,183],"this":[137],"paper":[138],"we":[139],"propose":[140],"approaches":[142,148],"suited":[143],"RNNT.":[145],"Our":[146],"sample":[149],"distiribution":[155],"itself,":[158],"i.e.":[159],"internal":[160],"language":[161],"or":[163],"outputs.":[165],"Experiments":[166],"three":[168],"datasets":[169],"confirm":[170],"trained":[173],"our":[175,190],"achieves":[178],"best":[180,191],"ASR":[181,188],"performance.":[182],"particular,":[184],"on":[185],"Japanese":[187],"task,":[189],"system":[192],"outperforms":[193],"state-of-the-art":[196],"alternative.":[197]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}