{"id":"https://openalex.org/W3162037819","doi":"https://doi.org/10.1109/icassp39728.2021.9415058","title":"A General Multi-Task Learning Framework to Leverage Text Data for Speech to Text Tasks","display_name":"A General Multi-Task Learning Framework to Leverage Text Data for Speech to Text Tasks","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3162037819","doi":"https://doi.org/10.1109/icassp39728.2021.9415058","mag":"3162037819"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9415058","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9415058","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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/A5033437280","display_name":"Yun Tang","orcid":"https://orcid.org/0000-0002-3122-5881"},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yun Tang","raw_affiliation_strings":["Facebook AI,USA","Facebook AI, USA"],"affiliations":[{"raw_affiliation_string":"Facebook AI,USA","institution_ids":["https://openalex.org/I4210114444"]},{"raw_affiliation_string":"Facebook AI, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058915697","display_name":"Juan Pino","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Juan Pino","raw_affiliation_strings":["Facebook AI,USA","Facebook AI, USA"],"affiliations":[{"raw_affiliation_string":"Facebook AI,USA","institution_ids":["https://openalex.org/I4210114444"]},{"raw_affiliation_string":"Facebook AI, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087491225","display_name":"Changhan Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Changhan Wang","raw_affiliation_strings":["Facebook AI,USA","Facebook AI, USA"],"affiliations":[{"raw_affiliation_string":"Facebook AI,USA","institution_ids":["https://openalex.org/I4210114444"]},{"raw_affiliation_string":"Facebook AI, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054878003","display_name":"Xutai Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xutai Ma","raw_affiliation_strings":["Facebook AI,USA","Johns Hopkins University, USA","Facebook AI, USA"],"affiliations":[{"raw_affiliation_string":"Facebook AI,USA","institution_ids":["https://openalex.org/I4210114444"]},{"raw_affiliation_string":"Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Facebook AI, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048470138","display_name":"Dmitriy Genzel","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dmitriy Genzel","raw_affiliation_strings":["Facebook AI,USA","Facebook AI, USA"],"affiliations":[{"raw_affiliation_string":"Facebook AI,USA","institution_ids":["https://openalex.org/I4210114444"]},{"raw_affiliation_string":"Facebook AI, USA","institution_ids":["https://openalex.org/I4210114444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5033437280"],"corresponding_institution_ids":["https://openalex.org/I4210114444"],"apc_list":null,"apc_paid":null,"fwci":9.4343,"has_fulltext":false,"cited_by_count":75,"citation_normalized_percentile":{"value":0.98327326,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"6209","last_page":"6213"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9995999932289124,"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/T10028","display_name":"Topic Modeling","score":0.9990000128746033,"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":0.8275220990180969},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.7708593606948853},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.690956711769104},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.6309136748313904},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6273440718650818},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5791219472885132},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5752068161964417},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.530326783657074},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5176175832748413},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.44744616746902466},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.43867599964141846},{"id":"https://openalex.org/keywords/speech-translation","display_name":"Speech translation","score":0.43800637125968933},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4213985800743103},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.28893399238586426},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.2530409097671509}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8275220990180969},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7708593606948853},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.690956711769104},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.6309136748313904},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6273440718650818},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5791219472885132},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5752068161964417},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.530326783657074},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5176175832748413},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.44744616746902466},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.43867599964141846},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.43800637125968933},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4213985800743103},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.28893399238586426},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2530409097671509},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/icassp39728.2021.9415058","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9415058","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5299999713897705,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1494198834","https://openalex.org/W2327501763","https://openalex.org/W2577366047","https://openalex.org/W2605131327","https://openalex.org/W2696967604","https://openalex.org/W2888779557","https://openalex.org/W2901389167","https://openalex.org/W2936774411","https://openalex.org/W2944255943","https://openalex.org/W2945700568","https://openalex.org/W2949328740","https://openalex.org/W2963403868","https://openalex.org/W2963602293","https://openalex.org/W2963779652","https://openalex.org/W2964012862","https://openalex.org/W2964161387","https://openalex.org/W2972991710","https://openalex.org/W2991213871","https://openalex.org/W3007142233","https://openalex.org/W3008125272","https://openalex.org/W3008480565","https://openalex.org/W3015703505","https://openalex.org/W3016006013","https://openalex.org/W3034772996","https://openalex.org/W3034999214","https://openalex.org/W3035490255","https://openalex.org/W3037217258","https://openalex.org/W3092424727","https://openalex.org/W3096490862","https://openalex.org/W3103005696","https://openalex.org/W3118578889","https://openalex.org/W4298393544","https://openalex.org/W4385245566","https://openalex.org/W6623517193","https://openalex.org/W6732447497","https://openalex.org/W6732953234","https://openalex.org/W6739901393","https://openalex.org/W6743477263","https://openalex.org/W6745388339","https://openalex.org/W6756200954","https://openalex.org/W6757094361","https://openalex.org/W6769311223","https://openalex.org/W6770506093","https://openalex.org/W6772381481","https://openalex.org/W6775587661","https://openalex.org/W6784050962","https://openalex.org/W6898634591"],"related_works":["https://openalex.org/W2463396630","https://openalex.org/W2114483840","https://openalex.org/W2010917994","https://openalex.org/W2100475772","https://openalex.org/W4386590854","https://openalex.org/W3081187864","https://openalex.org/W2162999097","https://openalex.org/W4380605396","https://openalex.org/W2803306015","https://openalex.org/W3133352777"],"abstract_inverted_index":{"Attention-based":[0],"sequence-to-sequence":[1],"modeling":[2],"provides":[3],"a":[4,18,36,65,82,141],"powerful":[5],"and":[6,56,76,86,97,116,119,157],"elegant":[7],"solution":[8],"for":[9,38,74],"applications":[10,40],"that":[11,103,136],"need":[12],"to":[13,17,48,70,92,127,130],"map":[14],"one":[15],"sequence":[16],"different":[19],"sequence.":[20],"Its":[21],"success":[22],"heavily":[23],"relies":[24],"on":[25,148,163],"the":[26,112,121,128,137,149,159,164],"availability":[27],"of":[28,31],"large":[29],"amounts":[30],"training":[32],"data.":[33],"This":[34],"presents":[35],"challenge":[37],"speech":[39,43,53,57,115,129,160],"where":[41],"labelled":[42],"data":[44,73],"is":[45],"very":[46],"expensive":[47],"obtain,":[49],"such":[50],"as":[51,107],"automatic":[52],"recognition":[54],"(ASR)":[55],"translation":[58,88,161],"(ST).":[59],"In":[60],"this":[61],"study,":[62],"we":[63],"propose":[64],"general":[66],"multi-task":[67],"learning":[68],"framework":[69],"leverage":[71],"text":[72,105,117,125,131],"ASR":[75,96],"ST":[77,98],"tasks.":[78,132],"Two":[79],"auxiliary":[80],"tasks,":[81],"denoising":[83],"autoencoder":[84],"task":[85,152],"machine":[87],"task,":[89],"are":[90],"proposed":[91,138],"be":[93],"co-trained":[94],"with":[95,154],"tasks":[99,166],"respectively.":[100],"We":[101],"demonstrate":[102],"representing":[104],"input":[106],"phoneme":[108],"sequences":[109],"can":[110],"reduce":[111],"difference":[113],"between":[114],"inputs,":[118],"enhance":[120],"knowledge":[122],"transfer":[123],"from":[124],"corpora":[126],"Our":[133],"experiments":[134],"show":[135],"method":[139],"achieves":[140],"relative":[142],"10~15%":[143],"word":[144],"error":[145],"rate":[146],"reduction":[147],"English":[150],"LIBRISPEECH":[151],"compared":[153],"our":[155],"baseline,":[156],"improves":[158],"quality":[162],"MUST-C":[165],"by":[167],"3.6~9.2":[168],"BLEU.":[169]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":25},{"year":2022,"cited_by_count":14},{"year":2021,"cited_by_count":18},{"year":2020,"cited_by_count":1}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}