{"id":"https://openalex.org/W4372260556","doi":"https://doi.org/10.1109/icassp49357.2023.10094660","title":"Iterative Shallow Fusion of Backward Language Model for End-To-End Speech Recognition","display_name":"Iterative Shallow Fusion of Backward Language Model for End-To-End Speech Recognition","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372260556","doi":"https://doi.org/10.1109/icassp49357.2023.10094660"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10094660","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10094660","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":"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/A5101949937","display_name":"Atsunori Ogawa","orcid":"https://orcid.org/0000-0002-2888-101X"},"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":true,"raw_author_name":"Atsunori Ogawa","raw_affiliation_strings":["NTT Corporation,Japan","NTT Corporation, Japan"],"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/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"],"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/A5034382743","display_name":"Naoyuki Kamo","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":"Naoyuki Kamo","raw_affiliation_strings":["NTT Corporation,Japan","NTT Corporation, Japan"],"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/A5073111123","display_name":"Naohiro Tawara","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":"Naohiro Tawara","raw_affiliation_strings":["NTT Corporation,Japan","NTT Corporation, Japan"],"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/A5023868166","display_name":"Marc Delcroix","orcid":"https://orcid.org/0000-0002-5175-7834"},"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":"Marc Delcroix","raw_affiliation_strings":["NTT Corporation,Japan","NTT Corporation, Japan"],"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":5,"corresponding_author_ids":["https://openalex.org/A5101949937"],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":0.1738,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.53391041,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"11","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":0.9983999729156494,"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":0.996999979019165,"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/computer-science","display_name":"Computer science","score":0.7479188442230225},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.6959133148193359},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.6511259078979492},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6023401021957397},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.5939262509346008},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5688396692276001},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5192896723747253},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44079482555389404},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.22519820928573608}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7479188442230225},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.6959133148193359},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6511259078979492},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6023401021957397},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.5939262509346008},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5688396692276001},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5192896723747253},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44079482555389404},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.22519820928573608},{"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10094660","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10094660","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":45,"referenced_works":["https://openalex.org/W1828163288","https://openalex.org/W1901465009","https://openalex.org/W1915251500","https://openalex.org/W2064675550","https://openalex.org/W2127141656","https://openalex.org/W2251321385","https://openalex.org/W2402268235","https://openalex.org/W2407080277","https://openalex.org/W2533523411","https://openalex.org/W2577366047","https://openalex.org/W2627092829","https://openalex.org/W2759071281","https://openalex.org/W2766219058","https://openalex.org/W2888779557","https://openalex.org/W2889177077","https://openalex.org/W2900440209","https://openalex.org/W2936774411","https://openalex.org/W2939111082","https://openalex.org/W2962780374","https://openalex.org/W2962826786","https://openalex.org/W2963240019","https://openalex.org/W2963250244","https://openalex.org/W2963266252","https://openalex.org/W2963362078","https://openalex.org/W3002595344","https://openalex.org/W3008037978","https://openalex.org/W3015190365","https://openalex.org/W3097747488","https://openalex.org/W3097777922","https://openalex.org/W3128293163","https://openalex.org/W3152221657","https://openalex.org/W3157428800","https://openalex.org/W3163793923","https://openalex.org/W3198654230","https://openalex.org/W3204434311","https://openalex.org/W4224920108","https://openalex.org/W4225311996","https://openalex.org/W4295312788","https://openalex.org/W4385245566","https://openalex.org/W6638749077","https://openalex.org/W6691770337","https://openalex.org/W6739901393","https://openalex.org/W6744898515","https://openalex.org/W6766978945","https://openalex.org/W6802155578"],"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/W3179968364","https://openalex.org/W4389471172","https://openalex.org/W2916997151","https://openalex.org/W2949174760"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,28,102,159],"new":[3],"shallow":[4],"fusion":[5],"(SF)":[6],"method":[7],"to":[8,57,71,163,185],"exploit":[9],"an":[10,122],"external":[11],"backward":[12,63],"language":[13,30],"model":[14,31],"(BLM)":[15],"for":[16,83],"end-to-end":[17],"automatic":[18],"speech":[19],"recognition":[20],"(ASR).":[21],"The":[22],"BLM":[23,56,81,105],"has":[24,39],"complementary":[25],"characteristics":[26],"with":[27,137],"forward":[29],"(FLM),":[32],"and":[33,155,176,191],"the":[34,49,55,62,67,72,78,84,88,93,115,132,140,165,186,189],"effectiveness":[35,94],"of":[36,95,117,147,188],"their":[37],"combination":[38],"been":[40],"confirmed":[41,128,171],"by":[42,173],"rescoring":[43],"ASR":[44,59,125],"hypotheses":[45,60,149],"as":[46,167],"post-processing.":[47,168],"In":[48,119],"proposed":[50],"SF,":[51],"we":[52,100,127,156,170],"iteratively":[53],"apply":[54],"partial":[58,103,112],"in":[61],"direction":[64],"(i.e.,":[65],"from":[66],"possible":[68],"next":[69],"token":[70],"start":[73],"symbol)":[74],"during":[75,153],"decoding,":[76,154],"substituting":[77],"newly":[79],"calculated":[80,86],"scores":[82,85],"at":[87],"last":[89],"iteration.":[90],"To":[91],"enhance":[92],"this":[96],"iterative":[97],"SF":[98,138,175],"(ISF),":[99],"train":[101],"sentence-aware":[104],"(PBLM)":[106],"using":[107,121,131,139],"reversed":[108],"text":[109],"data":[110],"including":[111],"sentences,":[113],"considering":[114],"framework":[116],"ISF.":[118],"experiments":[120],"attention-based":[123],"encoder-decoder":[124],"system,":[126],"that":[129],"ISF":[130],"PBLM":[133,166],"shows":[134],"comparable":[135],"performance":[136,160,179],"FLM.":[141],"By":[142],"performing":[143],"ISF,":[144,177],"early":[145],"pruning":[146],"prospective":[148],"can":[150,157,181],"be":[151,182],"prevented":[152],"obtain":[158],"improvement":[161,180],"compared":[162],"applying":[164],"Finally,":[169],"that,":[172],"combining":[174],"further":[178],"obtained":[183],"thanks":[184],"complementarity":[187],"FLM":[190],"PBLM.":[192]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}