{"id":"https://openalex.org/W2607361225","doi":"https://doi.org/10.21437/interspeech.2017-1118","title":"Multitask Learning with Low-Level Auxiliary Tasks for Encoder-Decoder Based Speech Recognition","display_name":"Multitask Learning with Low-Level Auxiliary Tasks for Encoder-Decoder Based Speech Recognition","publication_year":2017,"publication_date":"2017-08-16","ids":{"openalex":"https://openalex.org/W2607361225","doi":"https://doi.org/10.21437/interspeech.2017-1118","mag":"2607361225"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2017-1118","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-1118","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1704.01631","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5073890145","display_name":"Shubham Toshniwal","orcid":null},"institutions":[{"id":"https://openalex.org/I160992636","display_name":"Toyota Technological Institute at Chicago","ror":"https://ror.org/02sn5gb64","country_code":"US","type":"education","lineage":["https://openalex.org/I160992636"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Shubham Toshniwal","raw_affiliation_strings":["Toyota Technological Institute at Chicago, Chicago, United States"],"affiliations":[{"raw_affiliation_string":"Toyota Technological Institute at Chicago, Chicago, United States","institution_ids":["https://openalex.org/I160992636"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100662187","display_name":"Hao Tang","orcid":"https://orcid.org/0000-0002-2445-2605"},"institutions":[{"id":"https://openalex.org/I37802460","display_name":"Northwest University","ror":"https://ror.org/00z3td547","country_code":"CN","type":"education","lineage":["https://openalex.org/I37802460"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Tang","raw_affiliation_strings":["Northwest University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"Northwest University, Xi'an, China","institution_ids":["https://openalex.org/I37802460"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101607148","display_name":"Liang Lu","orcid":"https://orcid.org/0000-0003-4005-679X"},"institutions":[{"id":"https://openalex.org/I160992636","display_name":"Toyota Technological Institute at Chicago","ror":"https://ror.org/02sn5gb64","country_code":"US","type":"education","lineage":["https://openalex.org/I160992636"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liang Lu","raw_affiliation_strings":["Toyota Technological Institute at Chicago, Chicago, United States"],"affiliations":[{"raw_affiliation_string":"Toyota Technological Institute at Chicago, Chicago, United States","institution_ids":["https://openalex.org/I160992636"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015602781","display_name":"Karen Livescu","orcid":"https://orcid.org/0000-0003-4962-946X"},"institutions":[{"id":"https://openalex.org/I160992636","display_name":"Toyota Technological Institute at Chicago","ror":"https://ror.org/02sn5gb64","country_code":"US","type":"education","lineage":["https://openalex.org/I160992636"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Karen Livescu","raw_affiliation_strings":["Toyota Technological Institute at Chicago, Chicago, United States"],"affiliations":[{"raw_affiliation_string":"Toyota Technological Institute at Chicago, Chicago, United States","institution_ids":["https://openalex.org/I160992636"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5073890145"],"corresponding_institution_ids":["https://openalex.org/I160992636"],"apc_list":null,"apc_paid":null,"fwci":1.6616,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":{"value":0.87824868,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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":0.9997000098228455,"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":0.9994999766349792,"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":0.8271611928939819},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6997503638267517},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.644313633441925},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6297630071640015},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5681359767913818},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.49445056915283203},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.48849666118621826},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.4820857644081116},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4605604112148285},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"Multi-task learning","score":0.45893996953964233},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.41239702701568604},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.08048072457313538}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8271611928939819},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6997503638267517},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.644313633441925},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6297630071640015},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5681359767913818},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.49445056915283203},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.48849666118621826},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.4820857644081116},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4605604112148285},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.45893996953964233},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.41239702701568604},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.08048072457313538},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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":4,"locations":[{"id":"doi:10.21437/interspeech.2017-1118","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-1118","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1704.01631","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1704.01631","pdf_url":"https://arxiv.org/pdf/1704.01631","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":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:2607361225","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1704.01631.pdf","pdf_url":null,"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":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1704.01631","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1704.01631","pdf_url":null,"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":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1704.01631","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1704.01631","pdf_url":"https://arxiv.org/pdf/1704.01631","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":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.6000000238418579,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2607361225.pdf","grobid_xml":"https://content.openalex.org/works/W2607361225.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W1499332833","https://openalex.org/W1591801644","https://openalex.org/W1736701665","https://openalex.org/W1849277567","https://openalex.org/W2064675550","https://openalex.org/W2100664567","https://openalex.org/W2102605133","https://openalex.org/W2127141656","https://openalex.org/W2131342762","https://openalex.org/W2154887136","https://openalex.org/W2166637769","https://openalex.org/W2172097686","https://openalex.org/W2293858598","https://openalex.org/W2327501763","https://openalex.org/W2514969556","https://openalex.org/W2516255829","https://openalex.org/W2550821151","https://openalex.org/W2603679025","https://openalex.org/W2608712415","https://openalex.org/W2949888546","https://openalex.org/W2949892913","https://openalex.org/W2950304420","https://openalex.org/W2951883919","https://openalex.org/W2952230511","https://openalex.org/W2952470929","https://openalex.org/W2953022181","https://openalex.org/W2962826786","https://openalex.org/W2963069010","https://openalex.org/W2964308564","https://openalex.org/W2964325005"],"related_works":["https://openalex.org/W2963303028","https://openalex.org/W3008370744","https://openalex.org/W2526425061","https://openalex.org/W2920831951","https://openalex.org/W2992632249","https://openalex.org/W2964182350","https://openalex.org/W3095773170","https://openalex.org/W2890197052","https://openalex.org/W3021188327","https://openalex.org/W3041561163","https://openalex.org/W2946555236","https://openalex.org/W2775304348","https://openalex.org/W1495019370","https://openalex.org/W2929315483","https://openalex.org/W2942807473","https://openalex.org/W3014973941","https://openalex.org/W3143377973","https://openalex.org/W1600431506","https://openalex.org/W3008284571","https://openalex.org/W2765507192"],"abstract_inverted_index":{"End-to-end":[0],"training":[1,59,84],"of":[2,10,45,53,57,98,105],"deep":[3,46],"learning-based":[4],"models":[5],"allows":[6],"for":[7,90],"implicit":[8],"learning":[9],"intermediate":[11,37],"representations":[12,38],"based":[13],"on":[14,68,111,127],"the":[15,20,24,55,103,106,112,128],"final":[16],"task":[17],"loss.":[18],"However,":[19],"end-to-end":[21,58],"approach":[22,85,118],"ignores":[23],"useful":[25],"domain":[26],"knowledge":[27],"encoded":[28],"in":[29,81],"explicit":[30],"intermediate-level":[31],"supervision.":[32],"We":[33,65,94],"hypothesize":[34],"that":[35,116],"using":[36],"as":[39,78],"auxiliary":[40,107],"supervision":[41],"at":[42],"lower":[43],"levels":[44],"networks":[47],"may":[48],"be":[49],"a":[50,82,123],"good":[51],"way":[52],"combining":[54],"advantages":[56],"and":[60,101],"more":[61],"traditional":[62],"pipeline":[63],"approaches.":[64],"present":[66],"experiments":[67],"conversational":[69],"speech":[70],"recognition":[71,120],"where":[72],"we":[73],"use":[74],"lower-level":[75,99],"tasks,":[76],"such":[77],"phoneme":[79],"recognition,":[80],"multitask":[83],"with":[86],"an":[87],"encoder-decoder":[88,125],"model":[89,126],"direct":[91],"character":[92],"transcription.":[93],"compare":[95],"multiple":[96],"types":[97],"tasks":[100],"analyze":[102],"effects":[104],"tasks.":[108],"Our":[109],"results":[110],"Switchboard":[113],"corpus":[114],"show":[115],"this":[117],"improves":[119],"accuracy":[121],"over":[122],"standard":[124],"Eval2000":[129],"test":[130],"set.":[131]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}