{"id":"https://openalex.org/W2884975363","doi":"https://doi.org/10.1109/slt.2018.8639530","title":"Hierarchical Multitask Learning With CTC","display_name":"Hierarchical Multitask Learning With CTC","publication_year":2018,"publication_date":"2018-12-01","ids":{"openalex":"https://openalex.org/W2884975363","doi":"https://doi.org/10.1109/slt.2018.8639530","mag":"2884975363"},"language":"en","primary_location":{"id":"doi:10.1109/slt.2018.8639530","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2018.8639530","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Spoken Language Technology Workshop (SLT)","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/A5053704856","display_name":"Ramon Sanabria","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ramon Sanabria","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, U.S.A","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085262529","display_name":"Florian Metze","orcid":"https://orcid.org/0000-0002-6663-8600"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Florian Metze","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, U.S.A","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.0824,"has_fulltext":false,"cited_by_count":55,"citation_normalized_percentile":{"value":0.97000944,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"485","last_page":"490"},"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/T11309","display_name":"Music and Audio Processing","score":0.9994000196456909,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9993000030517578,"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":0.8440439701080322},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.7138315439224243},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5814495086669922},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5711432695388794},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.5682592988014221},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"Multi-task learning","score":0.5564541816711426},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.531509280204773},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.523398220539093},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.49959564208984375},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4877372682094574},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.45043376088142395},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3847426176071167},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3821004629135132},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.34388595819473267},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.29089057445526123}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8440439701080322},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.7138315439224243},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5814495086669922},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5711432695388794},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.5682592988014221},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.5564541816711426},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.531509280204773},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.523398220539093},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.49959564208984375},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4877372682094574},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.45043376088142395},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3847426176071167},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3821004629135132},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.34388595819473267},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.29089057445526123},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt.2018.8639530","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2018.8639530","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.75}],"awards":[],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W46679369","https://openalex.org/W1524333225","https://openalex.org/W1526990717","https://openalex.org/W1904457459","https://openalex.org/W2064675550","https://openalex.org/W2105594594","https://openalex.org/W2127141656","https://openalex.org/W2263232528","https://openalex.org/W2516255829","https://openalex.org/W2526425061","https://openalex.org/W2530486890","https://openalex.org/W2545177271","https://openalex.org/W2597757402","https://openalex.org/W2787663903","https://openalex.org/W2799800213","https://openalex.org/W2884254529","https://openalex.org/W2913340405","https://openalex.org/W2952288254","https://openalex.org/W2962784628","https://openalex.org/W2962824709","https://openalex.org/W2962826786","https://openalex.org/W2963070863","https://openalex.org/W2963211739","https://openalex.org/W2963226322","https://openalex.org/W2963292011","https://openalex.org/W2963303028","https://openalex.org/W2963537349","https://openalex.org/W2963953073","https://openalex.org/W6601894380","https://openalex.org/W6631362777","https://openalex.org/W6734588641","https://openalex.org/W6746892368","https://openalex.org/W6747492260","https://openalex.org/W6748477376","https://openalex.org/W6752958021"],"related_works":["https://openalex.org/W2594897229","https://openalex.org/W2151348424","https://openalex.org/W4221142855","https://openalex.org/W2050138804","https://openalex.org/W4290708361","https://openalex.org/W2129812225","https://openalex.org/W26527944","https://openalex.org/W2523799048","https://openalex.org/W2155620340","https://openalex.org/W2944691285"],"abstract_inverted_index":{"In":[0,47],"Automatic":[1],"Speech":[2],"Recognition,":[3],"it":[4],"is":[5],"still":[6],"challenging":[7],"to":[8,43],"learn":[9],"useful":[10,61],"intermediate":[11,62],"representations":[12],"when":[13,26],"using":[14],"high-level":[15],"(or":[16],"abstract)":[17],"target":[18],"units":[19],"such":[20],"as":[21],"words.":[22],"For":[23],"that":[24],"reason,":[25],"only":[27],"a":[28],"few":[29],"hundreds":[30],"of":[31,33,60,75,80,115,128],"hours":[32],"training":[34,100],"data":[35],"are":[36],"available,":[37],"character":[38],"or":[39,136],"phoneme-based":[40],"systems":[41],"tend":[42],"outperform":[44],"word-based":[45],"systems.":[46],"this":[48,66],"paper,":[49],"we":[50],"show":[51],"how":[52],"Hierarchical":[53],"Multitask":[54],"Learning":[55],"can":[56],"encourage":[57],"the":[58,76,92,96,112,125,129,140],"formation":[59],"representations.":[63],"We":[64],"achieve":[65],"by":[67],"performing":[68],"Connectionist":[69],"Temporal":[70],"Classification":[71],"at":[72],"different":[73,81],"levels":[74],"network":[77],"with":[78,111],"targets":[79],"granularity.":[82],"Our":[83,117],"model":[84,118],"thus":[85],"performs":[86],"predictions":[87],"in":[88],"multiple":[89],"scales":[90],"for":[91],"same":[93,113],"input.":[94],"On":[95],"standard":[97],"300h":[98],"Switchboard":[99,126],"setup,":[101],"our":[102],"hierarchical":[103],"multitask":[104],"architecture":[105],"demonstrates":[106],"improvements":[107],"over":[108],"singletask":[109],"architectures":[110],"number":[114],"parameters.":[116],"obtains":[119],"14.0%":[120],"Word":[121],"Error":[122],"Rate":[123],"on":[124,143],"subset":[127],"Eval2000":[130],"test":[131],"set":[132],"without":[133],"any":[134],"decoder":[135],"language":[137],"model,":[138],"outperforming":[139],"current":[141],"state-of-the-art":[142],"non-autoregressive":[144],"Acoustic-to-Word":[145],"models.":[146]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":17},{"year":2018,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}