{"id":"https://openalex.org/W2963447639","doi":"https://doi.org/10.21437/interspeech.2017-71","title":"Multitask Learning with CTC and Segmental CRF for Speech Recognition","display_name":"Multitask Learning with CTC and Segmental CRF for Speech Recognition","publication_year":2017,"publication_date":"2017-08-16","ids":{"openalex":"https://openalex.org/W2963447639","doi":"https://doi.org/10.21437/interspeech.2017-71","mag":"2963447639"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2017-71","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-71","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":"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/A5101607148","display_name":"Liang Lu","orcid":"https://orcid.org/0000-0003-4005-679X"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Liang Lu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101497114","display_name":"Lingpeng Kong","orcid":"https://orcid.org/0000-0002-9407-7193"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lingpeng Kong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111222692","display_name":"Chris Dyer","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chris Dyer","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5088517824","display_name":"Noah A. Smith","orcid":"https://orcid.org/0000-0002-2310-6380"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Noah A. Smith","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101607148"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.3403,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.91497231,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"954","last_page":"958"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9987999796867371,"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":0.9957000017166138,"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":0.7915418744087219},{"id":"https://openalex.org/keywords/sequence-labeling","display_name":"Sequence labeling","score":0.6499338746070862},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6416745781898499},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6030641794204712},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5376888513565063},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5135476589202881},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.49939417839050293},{"id":"https://openalex.org/keywords/conditional-random-field","display_name":"Conditional random field","score":0.47972574830055237},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.45672091841697693},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"Multi-task learning","score":0.4473438262939453},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4399992525577545},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.4366884231567383},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.43632131814956665},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.4162844121456146},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3765718638896942},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1355183720588684},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.11024323105812073}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7915418744087219},{"id":"https://openalex.org/C35639132","wikidata":"https://www.wikidata.org/wiki/Q7452468","display_name":"Sequence labeling","level":3,"score":0.6499338746070862},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6416745781898499},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6030641794204712},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5376888513565063},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5135476589202881},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.49939417839050293},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.47972574830055237},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.45672091841697693},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.4473438262939453},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4399992525577545},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.4366884231567383},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.43632131814956665},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.4162844121456146},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3765718638896942},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1355183720588684},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.11024323105812073},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2017-71","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-71","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"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2962906565","https://openalex.org/W2798423868","https://openalex.org/W3027026357","https://openalex.org/W3015678144","https://openalex.org/W3126392069","https://openalex.org/W2076440176","https://openalex.org/W3136048405","https://openalex.org/W2109665237","https://openalex.org/W2061027419","https://openalex.org/W2944198262"],"abstract_inverted_index":{"Segmental":[0],"conditional":[1],"random":[2],"fields":[3],"(SCRFs)":[4],"and":[5,52,54,87],"connectionist":[6],"temporal":[7],"classification":[8],"(CTC)":[9],"are":[10],"two":[11],"sequence":[12,39],"labeling":[13],"methods":[14],"used":[15,99,132],"for":[16,100,103],"end-to-end":[17],"training":[18],"of":[19,49,68],"speech":[20],"recognition":[21,78,113],"models.":[22,123],"Both":[23],"models":[24],"define":[25],"a":[26,38,44,66,77],"transcription":[27],"probability":[28],"by":[29,80],"marginalizing":[30],"decisions":[31],"about":[32],"latent":[33],"segmentation":[34],"alternatives":[35],"to":[36,133],"derive":[37],"probability:":[40],"the":[41,55,69,85,91,119,135,140,145],"former":[42],"uses":[43],"globally":[45],"normalized":[46],"joint":[47,146],"model":[48,79],"segment":[50],"labels":[51],"durations,":[53],"latter":[56],"classifies":[57],"each":[58],"frame":[59],"as":[60],"either":[61,118],"an":[62,82],"output":[63],"symbol":[64],"or":[65,121],"\"continuation\"":[67],"previous":[70],"label.":[71],"In":[72],"this":[73,109],"paper,":[74],"we":[75,125],"train":[76],"optimizing":[81],"interpolation":[83],"between":[84],"SCRF":[86,120],"CTC":[88,122,128],"losses,":[89],"where":[90],"same":[92],"recurrent":[93],"neural":[94],"network":[95],"(RNN)":[96],"encoder":[97],"is":[98],"feature":[101],"extraction":[102],"both":[104],"outputs.":[105],"We":[106],"find":[107],"that":[108,127],"multitask":[110],"objective":[111],"improves":[112,139],"accuracy":[114],"when":[115,143],"decoding":[116],"with":[117],"Additionally,":[124],"show":[126],"can":[129],"also":[130],"be":[131],"pretrain":[134],"RNN":[136],"encoder,":[137],"which":[138],"convergence":[141],"rate":[142],"learning":[144],"model.":[147]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}