{"id":"https://openalex.org/W4375868904","doi":"https://doi.org/10.1109/icassp49357.2023.10096387","title":"UFO2: A Unified Pre-Training Framework for Online and Offline Speech Recognition","display_name":"UFO2: A Unified Pre-Training Framework for Online and Offline Speech Recognition","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375868904","doi":"https://doi.org/10.1109/icassp49357.2023.10096387"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096387","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096387","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/A5101865288","display_name":"Li Fu","orcid":"https://orcid.org/0000-0002-7533-692X"},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Li Fu","raw_affiliation_strings":["JD AI Research,Beijing,China","JD AI Research, Beijing, China"],"affiliations":[{"raw_affiliation_string":"JD AI Research,Beijing,China","institution_ids":["https://openalex.org/I4210103986"]},{"raw_affiliation_string":"JD AI Research, Beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100336560","display_name":"Siqi Li","orcid":"https://orcid.org/0000-0003-2085-4938"},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siqi Li","raw_affiliation_strings":["JD AI Research,Beijing,China","JD AI Research, Beijing, China"],"affiliations":[{"raw_affiliation_string":"JD AI Research,Beijing,China","institution_ids":["https://openalex.org/I4210103986"]},{"raw_affiliation_string":"JD AI Research, Beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101833760","display_name":"Qingtao Li","orcid":"https://orcid.org/0000-0003-4376-3078"},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingtao Li","raw_affiliation_strings":["JD AI Research,Beijing,China","JD AI Research, Beijing, China"],"affiliations":[{"raw_affiliation_string":"JD AI Research,Beijing,China","institution_ids":["https://openalex.org/I4210103986"]},{"raw_affiliation_string":"JD AI Research, Beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006353150","display_name":"Liping Deng","orcid":"https://orcid.org/0000-0001-6903-3239"},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liping Deng","raw_affiliation_strings":["JD AI Research,Beijing,China","JD AI Research, Beijing, China"],"affiliations":[{"raw_affiliation_string":"JD AI Research,Beijing,China","institution_ids":["https://openalex.org/I4210103986"]},{"raw_affiliation_string":"JD AI Research, Beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069636203","display_name":"Fangzhu Li","orcid":null},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fangzhu Li","raw_affiliation_strings":["JD AI Research,Beijing,China","JD AI Research, Beijing, China"],"affiliations":[{"raw_affiliation_string":"JD AI Research,Beijing,China","institution_ids":["https://openalex.org/I4210103986"]},{"raw_affiliation_string":"JD AI Research, Beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100371061","display_name":"Lu Fan","orcid":"https://orcid.org/0009-0002-9253-0019"},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lu Fan","raw_affiliation_strings":["JD AI Research,Beijing,China","JD AI Research, Beijing, China"],"affiliations":[{"raw_affiliation_string":"JD AI Research,Beijing,China","institution_ids":["https://openalex.org/I4210103986"]},{"raw_affiliation_string":"JD AI Research, Beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106541035","display_name":"Meng Chen","orcid":"https://orcid.org/0009-0009-8899-038X"},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meng Chen","raw_affiliation_strings":["JD AI Research,Beijing,China","JD AI Research, Beijing, China"],"affiliations":[{"raw_affiliation_string":"JD AI Research,Beijing,China","institution_ids":["https://openalex.org/I4210103986"]},{"raw_affiliation_string":"JD AI Research, Beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006367043","display_name":"Xiaodong He","orcid":"https://orcid.org/0000-0002-6682-2926"},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaodong He","raw_affiliation_strings":["JD AI Research,Beijing,China","JD AI Research, Beijing, China"],"affiliations":[{"raw_affiliation_string":"JD AI Research,Beijing,China","institution_ids":["https://openalex.org/I4210103986"]},{"raw_affiliation_string":"JD AI Research, Beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5101865288"],"corresponding_institution_ids":["https://openalex.org/I4210103986"],"apc_list":null,"apc_paid":null,"fwci":0.3497,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.63106918,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"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":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":0.9987000226974487,"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":0.9970999956130981,"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":0.8372890949249268},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.6184068918228149},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.5668696165084839},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5665518641471863},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5652403831481934},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5364435911178589},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5186940431594849},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.47454556822776794},{"id":"https://openalex.org/keywords/mode","display_name":"Mode (computer interface)","score":0.46253493428230286},{"id":"https://openalex.org/keywords/online-and-offline","display_name":"Online and offline","score":0.46101537346839905},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43312638998031616},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4182592034339905},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.12660405039787292},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.08628454804420471}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8372890949249268},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6184068918228149},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.5668696165084839},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5665518641471863},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5652403831481934},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5364435911178589},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5186940431594849},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.47454556822776794},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.46253493428230286},{"id":"https://openalex.org/C2780102126","wikidata":"https://www.wikidata.org/wiki/Q10928179","display_name":"Online and offline","level":2,"score":0.46101537346839905},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43312638998031616},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4182592034339905},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.12660405039787292},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.08628454804420471},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096387","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096387","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,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2127141656","https://openalex.org/W2766219058","https://openalex.org/W2936774411","https://openalex.org/W2962760690","https://openalex.org/W2972426539","https://openalex.org/W2973049979","https://openalex.org/W3015213852","https://openalex.org/W3015457435","https://openalex.org/W3015560358","https://openalex.org/W3015927303","https://openalex.org/W3023953056","https://openalex.org/W3095311338","https://openalex.org/W3097777922","https://openalex.org/W3160628828","https://openalex.org/W3161873870","https://openalex.org/W3197478142","https://openalex.org/W3197580070","https://openalex.org/W3198039885","https://openalex.org/W3198694222","https://openalex.org/W3207629995","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W3213029956","https://openalex.org/W4280644286","https://openalex.org/W4281492411","https://openalex.org/W4285203343","https://openalex.org/W4286908208","https://openalex.org/W4319862425","https://openalex.org/W6638523607","https://openalex.org/W6691770337","https://openalex.org/W6769196770","https://openalex.org/W6780218876","https://openalex.org/W6784614252","https://openalex.org/W6790121257","https://openalex.org/W6810673746","https://openalex.org/W6838637163"],"related_works":["https://openalex.org/W2529301793","https://openalex.org/W2384121599","https://openalex.org/W2038083449","https://openalex.org/W3177678247","https://openalex.org/W1999617572","https://openalex.org/W2944572343","https://openalex.org/W2333799855","https://openalex.org/W2351687372","https://openalex.org/W2004087835","https://openalex.org/W2944691285"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,48],"propose":[4],"a":[5,59],"Unified":[6],"pre-training":[7,98],"Framework":[8],"for":[9,26,116],"Online":[10],"and":[11,28,34,72,99,136,143],"Offline":[12],"(UFO2)":[13],"Automatic":[14],"Speech":[15],"Recognition":[16],"(ASR),":[17],"which":[18],"1)":[19],"simplifies":[20],"the":[21,37,50,63,70,78,88,92,97,100,110,117,123,130],"two":[22,118],"separate":[23],"training":[24,65],"workflows":[25],"online":[27,144],"offline":[29,142],"modes":[30],"into":[31],"one":[32],"process,":[33],"2)":[35],"improves":[36],"Word":[38],"Error":[39],"Rate":[40],"(WER)":[41],"performance":[42],"with":[43,113],"limited":[44],"utterance":[45],"annotating.":[46],"Specifically,":[47],"extend":[49],"conventional":[51],"offline-mode":[52],"Self-Supervised":[53],"Learning":[54],"(SSL)-based":[55],"ASR":[56],"approach":[57],"to":[58,86,91,108],"unified":[60,111],"manner,":[61],"where":[62],"model":[64,112],"is":[66,84],"conditioned":[67],"on":[68,122],"both":[69,96],"full-context":[71],"dynamic-":[73],"chunked":[74],"inputs.":[75],"To":[76],"enhance":[77],"pre-trained":[79],"representation":[80],"model,":[81],"stop-gradient":[82],"operation":[83],"applied":[85],"decouple":[87],"online-mode":[89],"objectives":[90],"quantizer.":[93],"Moreover,":[94],"in":[95,141],"downstream":[101],"fine-tuning":[102],"stages,":[103],"joint":[104],"losses":[105],"are":[106],"proposed":[107],"train":[109],"full-weight":[114],"sharing":[115],"modes.":[119],"Experimental":[120],"results":[121],"LibriSpeech":[124],"dataset":[125],"show":[126],"that":[127],"UFO2":[128],"outperforms":[129],"SSL-based":[131],"baseline":[132],"method":[133],"by":[134],"29.7%":[135],"18.2%":[137],"relative":[138],"WER":[139],"reduction":[140],"modes,":[145],"respectively.":[146]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}