乐胖代购免代理版

{"id":"https://openalex.org/W4319862454","doi":"https://doi.org/10.1109/slt54892.2023.10022420","title":"Learning to Jointly Transcribe and Subtitle for End-To-End Spontaneous Speech Recognition","display_name":"Learning to Jointly Transcribe and Subtitle for End-To-End Spontaneous Speech Recognition","publication_year":2023,"publication_date":"2023-01-09","ids":{"openalex":"https://openalex.org/W4319862454","doi":"https://doi.org/10.1109/slt54892.2023.10022420"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10022420","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://lirias.kuleuven.be/bitstream/20.500.12942/703799/2/4726_arXiv.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009033650","display_name":"Jakob Poncelet","orcid":"https://orcid.org/0000-0002-5157-7577"},"institutions":[{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Jakob Poncelet","raw_affiliation_strings":["KU Leuven,Department Electrical Engineering ESAT-PSI,Leuven,Belgium,B-3001"],"affiliations":[{"raw_affiliation_string":"KU Leuven,Department Electrical Engineering ESAT-PSI,Leuven,Belgium,B-3001","institution_ids":["https://openalex.org/I99464096"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087514947","display_name":"Hugo Van hamme","orcid":"https://orcid.org/0000-0003-1331-5186"},"institutions":[{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Hugo Van Hamme","raw_affiliation_strings":["KU Leuven,Department Electrical Engineering ESAT-PSI,Leuven,Belgium,B-3001"],"affiliations":[{"raw_affiliation_string":"KU Leuven,Department Electrical Engineering ESAT-PSI,Leuven,Belgium,B-3001","institution_ids":["https://openalex.org/I99464096"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.412,"has_fulltext":true,"fulltext_origin":"pdf","cited_by_count":1,"citation_normalized_percentile":{"value":0.558059,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":67,"max":78},"biblio":{"volume":null,"issue":null,"first_page":"182","last_page":"189"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9999,"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":0.9999,"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":0.9994,"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":0.9969,"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/subtitle","display_name":"Subtitle","score":0.89715874}],"concepts":[{"id":"https://openalex.org/C2780364048","wikidata":"https://www.wikidata.org/wiki/Q204028","display_name":"Subtitle","level":2,"score":0.89715874},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8334005},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.71939784},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.58609444},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5394064},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.5226093},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40994748},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37864396},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.05757031},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10022420","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"https://lirias.kuleuven.be/handle/20.500.12942/703799","pdf_url":"https://lirias.kuleuven.be/bitstream/20.500.12942/703799/2/4726_arXiv.pdf","source":{"id":"https://openalex.org/S4306401954","display_name":"Lirias (KU Leuven)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I99464096","host_organization_name":"KU Leuven","host_organization_lineage":["https://openalex.org/I99464096"],"host_organization_lineage_names":["KU Leuven"],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true},{"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2210.07771","pdf_url":"http://arxiv.org/pdf/2210.07771","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://lirias.kuleuven.be/handle/20.500.12942/703799","pdf_url":"https://lirias.kuleuven.be/bitstream/20.500.12942/703799/2/4726_arXiv.pdf","source":{"id":"https://openalex.org/S4306401954","display_name":"Lirias (KU Leuven)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I99464096","host_organization_name":"KU Leuven","host_organization_lineage":["https://openalex.org/I99464096"],"host_organization_lineage_names":["KU Leuven"],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true},"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":35,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2101105183","https://openalex.org/W2127141656","https://openalex.org/W2288371874","https://openalex.org/W2288402171","https://openalex.org/W2288434812","https://openalex.org/W2586635866","https://openalex.org/W2612649659","https://openalex.org/W2624871570","https://openalex.org/W2744215503","https://openalex.org/W2745538008","https://openalex.org/W2766219058","https://openalex.org/W2805508463","https://openalex.org/W2936774411","https://openalex.org/W2962780374","https://openalex.org/W2963077089","https://openalex.org/W2963779652","https://openalex.org/W2963925437","https://openalex.org/W2998386507","https://openalex.org/W3003960098","https://openalex.org/W3015810689","https://openalex.org/W3036601975","https://openalex.org/W3038127439","https://openalex.org/W3100153294","https://openalex.org/W3102811925","https://openalex.org/W3160525311","https://openalex.org/W3161669994","https://openalex.org/W3204316016","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W3210615406","https://openalex.org/W3213029956","https://openalex.org/W4239943352","https://openalex.org/W4293363567","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W4362014186","https://openalex.org/W4221140906","https://openalex.org/W3208216439","https://openalex.org/W3207932232","https://openalex.org/W3042381743","https://openalex.org/W2995181833","https://openalex.org/W2963697731","https://openalex.org/W2909970382","https://openalex.org/W2892009249","https://openalex.org/W1585034923"],"abstract_inverted_index":{"TV":[0],"subtitles":[1,31],"are":[2,32],"a":[3,56,82],"rich":[4],"source":[5],"of":[6,8,11,38,140],"transcriptions":[7,37],"many":[9],"types":[10],"speech,":[12,39],"ranging":[13],"from":[14],"read":[15],"speech":[16,24],"in":[17,25],"news":[18],"reports":[19],"to":[20,46,100,108],"conversational":[21,123],"and":[22,28,65,77,105,119,122],"spontaneous":[23,121],"talk":[26],"shows":[27],"soaps.":[29],"However,":[30],"not":[33,134],"verbatim":[34,75],"(i.e.":[35],"exact)":[36],"so":[40],"they":[41],"cannot":[42],"be":[43,92],"used":[44],"directly":[45],"improve":[47],"an":[48],"Automatic":[49],"Speech":[50],"Recognition":[51],"(ASR)":[52],"model.":[53],"We":[54,113],"propose":[55],"multitask":[57],"dual-decoder":[58],"Transformer":[59],"model":[60,97],"that":[61],"jointly":[62],"performs":[63],"ASR":[64,69,118,124],"automatic":[66],"subtitling.":[67],"The":[68,88,96,131],"decoder":[70,80],"(possibly":[71],"pre-trained)":[72],"predicts":[73],"the":[74,78,86,127,141],"output":[76],"subtitle":[79,111,129],"generates":[81],"subtitle,":[83],"while":[84],"sharing":[85],"encoder.":[87],"two":[89],"decoders":[90],"can":[91],"independent":[93],"or":[94],"connected.":[95],"is":[98,106],"trained":[99],"perform":[101],"both":[102],"tasks":[103],"jointly,":[104],"able":[107],"effectively":[109],"use":[110],"data.":[112],"show":[114],"improvements":[115],"on":[116,120],"regular":[117],"by":[125],"incorporating":[126],"additional":[128],"decoder.":[130],"method":[132],"does":[133],"require":[135],"preprocessing":[136],"(aligning,":[137],"filtering,":[138],"pseudo-labeling,\u2026)":[139],"subtitles.":[142]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W4319862454","counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2025-01-02T11:21:44.693016","created_date":"2023-02-11"}