{"id":"https://openalex.org/W4372346361","doi":"https://doi.org/10.1109/icassp49357.2023.10095937","title":"Factorized AED: Factorized Attention-Based Encoder-Decoder for Text-Only Domain Adaptive ASR","display_name":"Factorized AED: Factorized Attention-Based Encoder-Decoder for Text-Only Domain Adaptive ASR","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372346361","doi":"https://doi.org/10.1109/icassp49357.2023.10095937"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095937","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095937","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/A5086338661","display_name":"Xun Gong","orcid":"https://orcid.org/0000-0002-3364-8407"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xun Gong","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100392097","display_name":"Wei Wang","orcid":"https://orcid.org/0009-0000-5702-3009"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Wang","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080901723","display_name":"Hang Shao","orcid":"https://orcid.org/0000-0002-1322-4789"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hang Shao","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101293966","display_name":"Xie Chen","orcid":"https://orcid.org/0000-0001-7423-617X"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xie Chen","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100341993","display_name":"Yanmin Qian","orcid":"https://orcid.org/0000-0002-0314-3790"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanmin Qian","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I183067930"],"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":"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":0.9948999881744385,"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/T12031","display_name":"Speech and dialogue systems","score":0.9943000078201294,"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/computer-science","display_name":"Computer science","score":0.7600587606430054},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.657076358795166},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5439685583114624},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5428057909011841},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.53916996717453},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4459885060787201},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.43047934770584106},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.42016202211380005},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.4175082743167877},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3279770016670227},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12571457028388977}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7600587606430054},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.657076358795166},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5439685583114624},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5428057909011841},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.53916996717453},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4459885060787201},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.43047934770584106},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.42016202211380005},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.4175082743167877},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3279770016670227},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12571457028388977},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","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},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","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},{"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095937","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095937","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":[{"score":0.6299999952316284,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1513820424","https://openalex.org/W1828163288","https://openalex.org/W1915251500","https://openalex.org/W1989549063","https://openalex.org/W2127141656","https://openalex.org/W2739883972","https://openalex.org/W2795867901","https://openalex.org/W2888779557","https://openalex.org/W2911629330","https://openalex.org/W2936774411","https://openalex.org/W2939111082","https://openalex.org/W2962699523","https://openalex.org/W2962780374","https://openalex.org/W2963240019","https://openalex.org/W2963250244","https://openalex.org/W2972889948","https://openalex.org/W3008037978","https://openalex.org/W3015686596","https://openalex.org/W3015915933","https://openalex.org/W3016234571","https://openalex.org/W3096122506","https://openalex.org/W3097777922","https://openalex.org/W3112702554","https://openalex.org/W3147900189","https://openalex.org/W3152221657","https://openalex.org/W3193461931","https://openalex.org/W3197242296","https://openalex.org/W3198694222","https://openalex.org/W3202419788","https://openalex.org/W3211278025","https://openalex.org/W4385245566","https://openalex.org/W6638749077","https://openalex.org/W6640059789","https://openalex.org/W6739901393","https://openalex.org/W6743477263","https://openalex.org/W6792680588"],"related_works":["https://openalex.org/W2594897229","https://openalex.org/W2151348424","https://openalex.org/W4221142855","https://openalex.org/W2050138804","https://openalex.org/W2129812225","https://openalex.org/W4290708361","https://openalex.org/W2523799048","https://openalex.org/W2155620340","https://openalex.org/W1494910745","https://openalex.org/W2114358883"],"abstract_inverted_index":{"End-to-end":[0],"automatic":[1],"speech":[2,36],"recognition":[3],"(ASR)":[4],"systems":[5],"have":[6],"gained":[7],"popularity":[8],"given":[9],"their":[10],"simplified":[11],"architecture":[12],"and":[13,122,160],"promising":[14],"results.":[15],"However,":[16],"text-only":[17],"domain":[18,101,104],"adaptation":[19],"remains":[20],"a":[21,92,109,113,129],"big":[22],"challenge":[23],"for":[24,112,156,166],"E2E":[25],"systems.":[26],"Text-to-speech":[27],"(TTS)":[28],"based":[29,50],"approaches":[30,51],"fine-tune":[31],"ASR":[32],"models":[33],"by":[34],"synthesized":[35],"with":[37],"an":[38],"auxiliary":[39],"TTS":[40],"model,":[41,73],"thus":[42],"increase":[43],"deployment":[44],"costs.":[45],"Language":[46],"model":[47,82],"(LM)":[48],"fusion":[49],"can":[52],"achieve":[53],"good":[54],"performance":[55],"but":[56],"are":[57,135],"sensitive":[58],"to":[59,64,128,137,174],"interpolation":[60],"parameters.":[61],"In":[62],"order":[63],"factorize":[65],"out":[66],"the":[67,71,76,88,98,103,139,175],"language":[68],"component":[69,111],"in":[70,97,133],"AED":[72,116,176],"we":[74],"propose":[75],"factorized":[77,115],"attention-based":[78],"encoder-decoder":[79],"(Factorized":[80],"AED)":[81],"whose":[83],"decoder":[84],"takes":[85],"as":[86,108],"input":[87],"posterior":[89],"probabilities":[90],"of":[91,100,131,141],"jointly":[93],"trained":[94],"LM.":[95],"Moreover,":[96],"context":[99],"adaptation,":[102],"specific":[105],"LM":[106],"serves":[107],"plug-and-play":[110],"well-trained":[114],"model.":[117],"In-domain":[118],"experiments":[119,124],"on":[120],"LibriSpeech":[121,127,157],"out-of-domain":[123],"adapting":[125],"from":[126],"variety":[130],"domains":[132,170],"GigaSpeech":[134,168],"conducted":[136],"validate":[138],"effectiveness":[140],"our":[142],"proposed":[143],"methods.":[144],"Results":[145],"show":[146],"20%":[147],"/":[148],"24%":[149],"relative":[150,163],"word":[151],"error":[152],"rate":[153],"(WER)":[154],"reduction":[155,165],"test":[158,171],"sets":[159,172],"8":[161,167],"\u223c34%":[162],"WER":[164],"target":[169],"compared":[173],"baseline.":[177]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}