{"id":"https://openalex.org/W4392902996","doi":"https://doi.org/10.1109/icassp48485.2024.10447838","title":"FastInject: Injecting Unpaired Text Data into CTC-Based ASR Training","display_name":"FastInject: Injecting Unpaired Text Data into CTC-Based ASR Training","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392902996","doi":"https://doi.org/10.1109/icassp48485.2024.10447838"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447838","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10447838","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5068367173","display_name":"Keqi Deng","orcid":"https://orcid.org/0000-0003-1490-963X"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Keqi Deng","raw_affiliation_strings":["University of Cambridge,Department of Engineering,Cambridge,UK","Department of Engineering, University of Cambridge, Cambridge, UK"],"affiliations":[{"raw_affiliation_string":"University of Cambridge,Department of Engineering,Cambridge,UK","institution_ids":["https://openalex.org/I241749"]},{"raw_affiliation_string":"Department of Engineering, University of Cambridge, Cambridge, UK","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002191410","display_name":"Philip C. Woodland","orcid":"https://orcid.org/0000-0001-9069-0225"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Philip C. Woodland","raw_affiliation_strings":["University of Cambridge,Department of Engineering,Cambridge,UK","Department of Engineering, University of Cambridge, Cambridge, UK"],"affiliations":[{"raw_affiliation_string":"University of Cambridge,Department of Engineering,Cambridge,UK","institution_ids":["https://openalex.org/I241749"]},{"raw_affiliation_string":"Department of Engineering, University of Cambridge, Cambridge, UK","institution_ids":["https://openalex.org/I241749"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5068367173"],"corresponding_institution_ids":["https://openalex.org/I241749"],"apc_list":null,"apc_paid":null,"fwci":0.3651,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.61746438,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"11836","last_page":"11840"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.994700014591217,"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":0.9882000088691711,"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":0.7952542304992676},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.6777467131614685},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5884041786193848},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5469115972518921},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5366837978363037},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5124300122261047},{"id":"https://openalex.org/keywords/bridge","display_name":"Bridge (graph theory)","score":0.4837186634540558},{"id":"https://openalex.org/keywords/test-data","display_name":"Test data","score":0.47047263383865356},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.45695188641548157},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4526599645614624},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.446774959564209},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.4366670846939087},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.41466110944747925},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3529963791370392},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.08033517003059387}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7952542304992676},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.6777467131614685},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5884041786193848},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5469115972518921},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5366837978363037},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5124300122261047},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.4837186634540558},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.47047263383865356},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.45695188641548157},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4526599645614624},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.446774959564209},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.4366670846939087},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.41466110944747925},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3529963791370392},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.08033517003059387},{"id":"https://openalex.org/C126322002","wikidata":"https://www.wikidata.org/wiki/Q11180","display_name":"Internal medicine","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447838","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10447838","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321848","display_name":"Cambridge Trust","ror":"https://ror.org/05sprqy15"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1586176709","https://openalex.org/W2127141656","https://openalex.org/W2144499799","https://openalex.org/W2515801922","https://openalex.org/W2936774411","https://openalex.org/W2962780374","https://openalex.org/W3008037978","https://openalex.org/W3160475509","https://openalex.org/W3162249256","https://openalex.org/W3197580070","https://openalex.org/W3197681820","https://openalex.org/W3198694222","https://openalex.org/W3205644108","https://openalex.org/W3207222250","https://openalex.org/W3209984917","https://openalex.org/W3212799896","https://openalex.org/W4210690962","https://openalex.org/W4225299129","https://openalex.org/W4226120743","https://openalex.org/W4283031490","https://openalex.org/W4319862474","https://openalex.org/W4372260307","https://openalex.org/W4372266510","https://openalex.org/W4372267353","https://openalex.org/W4383605108","https://openalex.org/W4385823441","https://openalex.org/W4392979802","https://openalex.org/W6623517193","https://openalex.org/W6691770337","https://openalex.org/W6780218876","https://openalex.org/W6795952400"],"related_works":["https://openalex.org/W209733029","https://openalex.org/W2891480213","https://openalex.org/W2991483587","https://openalex.org/W3118953353","https://openalex.org/W2158542502","https://openalex.org/W1997978958","https://openalex.org/W133774893","https://openalex.org/W2099971677","https://openalex.org/W2250522181","https://openalex.org/W2615667245"],"abstract_inverted_index":{"Recently,":[0],"connectionist":[1],"temporal":[2],"classification":[3],"(CTC)-based":[4],"end-to-end":[5],"(E2E)":[6],"automatic":[7],"speech":[8,85,93],"recognition":[9],"(ASR)":[10],"models":[11,26],"have":[12],"achieved":[13],"impressive":[14],"results,":[15],"especially":[16],"with":[17,84],"the":[18,80,89,106,113],"development":[19],"of":[20],"self-supervised":[21],"learning.":[22],"However,":[23],"E2E":[24,107],"ASR":[25,64],"trained":[27],"on":[28,131],"paired":[29],"speech-text":[30],"data":[31,61,126],"often":[32],"suffer":[33],"from":[34,37],"domain":[35],"shifts":[36],"training":[38,51,68],"to":[39],"testing.":[40],"To":[41,66,87],"alleviate":[42],"this":[43,45],"issue,":[44],"paper":[46],"proposes":[47],"a":[48,117],"flat-start":[49,108],"joint":[50],"method,":[52],"named":[53],"FastInject,":[54],"which":[55,104],"efficiently":[56],"injects":[57],"multi-domain":[58],"unpaired":[59],"text":[60,70],"into":[62,79],"CTC-based":[63],"training.":[65,109],"maintain":[67],"efficiency,":[69],"units":[71],"are":[72,77],"pre-upsampled,":[73],"and":[74,94,127],"their":[75],"representations":[76],"fed":[78],"CTC":[81],"model":[82],"along":[83],"features.":[86],"bridge":[88],"modality":[90,98],"gap":[91],"between":[92],"text,":[95],"an":[96],"attention-based":[97],"matching":[99],"mechanism":[100],"(AM3)":[101],"is":[102],"proposed,":[103],"retains":[105],"Experiments":[110],"show":[111],"that":[112],"proposed":[114],"FastInject":[115],"gave":[116],"22%":[118],"relative":[119,129],"WER":[120],"reduction":[121],"(WERR)":[122],"for":[123],"intra-domain":[124],"Librispeech-100h":[125],"20%":[128],"WERR":[130],"out-of-domain":[132],"test":[133],"sets.":[134]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-12-22T23:10:17.713674","created_date":"2025-10-10T00:00:00"}