{"id":"https://openalex.org/W2767085854","doi":"https://doi.org/10.1109/icassp.2018.8462210","title":"A Study of All-Convolutional Encoders for Connectionist Temporal Classification","display_name":"A Study of All-Convolutional Encoders for Connectionist Temporal Classification","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2767085854","doi":"https://doi.org/10.1109/icassp.2018.8462210","mag":"2767085854"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8462210","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462210","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1710.10398","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078893115","display_name":"Kalpesh Krishna","orcid":"https://orcid.org/0000-0001-6574-0817"},"institutions":[{"id":"https://openalex.org/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Kalpesh Krishna","raw_affiliation_strings":["Indian Institute of Technology Bombay, India","Indian Institute of Technology \u2014 Bombay, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Bombay, India","institution_ids":["https://openalex.org/I162827531"]},{"raw_affiliation_string":"Indian Institute of Technology \u2014 Bombay, India","institution_ids":["https://openalex.org/I162827531"]}]},{"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/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liang Lu","raw_affiliation_strings":["Microsoft AI and Research, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft AI and Research, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081022650","display_name":"Kevin Gimpel","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":false,"raw_author_name":"Kevin Gimpel","raw_affiliation_strings":["Toyota Technological Institute at Chicago, USA","[Toyota Technological Institute at Chicago, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toyota Technological Institute at Chicago, USA","institution_ids":["https://openalex.org/I160992636"]},{"raw_affiliation_string":"[Toyota Technological Institute at Chicago, USA]","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, USA","[Toyota Technological Institute at Chicago, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toyota Technological Institute at Chicago, USA","institution_ids":["https://openalex.org/I160992636"]},{"raw_affiliation_string":"[Toyota Technological Institute at Chicago, USA]","institution_ids":["https://openalex.org/I160992636"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"abs 1702 7793","issue":null,"first_page":"5814","last_page":"5818"},"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":0.9991999864578247,"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":0.9990000128746033,"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/connectionism","display_name":"Connectionism","score":0.8664404153823853},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8473930954933167},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6790755987167358},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6356220841407776},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6156603097915649},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.6080698370933533},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5760709047317505},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5576201677322388},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.4729941785335541},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4580913484096527},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.44911277294158936},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4446914792060852},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.4283216595649719},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4146782457828522},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41027140617370605},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2972830533981323},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.11511179804801941}],"concepts":[{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.8664404153823853},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8473930954933167},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6790755987167358},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6356220841407776},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6156603097915649},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.6080698370933533},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5760709047317505},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5576201677322388},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.4729941785335541},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4580913484096527},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.44911277294158936},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4446914792060852},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.4283216595649719},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4146782457828522},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41027140617370605},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2972830533981323},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.11511179804801941},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp.2018.8462210","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462210","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1710.10398","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1710.10398","pdf_url":"https://arxiv.org/pdf/1710.10398","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:2767085854","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1710.10398","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.1710.10398","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1710.10398","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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1710.10398","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1710.10398","pdf_url":"https://arxiv.org/pdf/1710.10398","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":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.47999998927116394}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2767085854.pdf","grobid_xml":"https://content.openalex.org/works/W2767085854.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W1631260214","https://openalex.org/W1836465849","https://openalex.org/W2117671523","https://openalex.org/W2127141656","https://openalex.org/W2166637769","https://openalex.org/W2173629880","https://openalex.org/W2193413348","https://openalex.org/W2194775991","https://openalex.org/W2293858598","https://openalex.org/W2402146185","https://openalex.org/W2520160253","https://openalex.org/W2545177271","https://openalex.org/W2597757402","https://openalex.org/W2949117887","https://openalex.org/W2949888546","https://openalex.org/W2963211739","https://openalex.org/W2963403664","https://openalex.org/W2963537349","https://openalex.org/W2964121744","https://openalex.org/W6631190155","https://openalex.org/W6631362777","https://openalex.org/W6636811518","https://openalex.org/W6637242042","https://openalex.org/W6637794970","https://openalex.org/W6679436768","https://openalex.org/W6684440257","https://openalex.org/W6687483927","https://openalex.org/W6687566353","https://openalex.org/W6696750753","https://openalex.org/W6702097088","https://openalex.org/W6712930963","https://openalex.org/W6727193155","https://openalex.org/W6727336983","https://openalex.org/W6734241735","https://openalex.org/W6743440867"],"related_works":["https://openalex.org/W2964330921","https://openalex.org/W2516608830","https://openalex.org/W2907719996","https://openalex.org/W3119439212","https://openalex.org/W2775473040","https://openalex.org/W2173601261","https://openalex.org/W2963927463","https://openalex.org/W2033310064","https://openalex.org/W2799034895","https://openalex.org/W3049708400","https://openalex.org/W2198724430","https://openalex.org/W1555696814","https://openalex.org/W2912831041","https://openalex.org/W2971900328","https://openalex.org/W3134727464","https://openalex.org/W2754613063","https://openalex.org/W2530876040","https://openalex.org/W3010074710","https://openalex.org/W2753094133","https://openalex.org/W2401062389"],"abstract_inverted_index":{"Connectionist":[0],"temporal":[1],"classification":[2],"(CTC)":[3],"is":[4,15],"a":[5,91],"popular":[6],"sequence":[7],"prediction":[8],"approach":[9],"for":[10,75],"automatic":[11,84],"speech":[12,85],"recognition":[13],"that":[14,59,133],"typically":[16],"used":[17,36],"with":[18],"models":[19,107,111,136],"based":[20],"on":[21,126],"recurrent":[22],"neural":[23,31],"networks":[24,32],"(RNNs).":[25],"We":[26,66,100,131],"explore":[27,90],"whether":[28],"deep":[29],"convolutional":[30],"(CNNs)":[33],"can":[34],"be":[35],"effectively":[37],"instead":[38],"of":[39,51,70,81,93,104,114],"RNNs":[40],"as":[41,73],"the":[42,52,57,79,102,127],"\u201cencoder\u201d":[43],"in":[44,78,112,139],"CTC.":[45],"CNNs":[46],"lack":[47],"an":[48,68],"explicit":[49],"representation":[50],"entire":[53],"sequence,":[54],"but":[55],"have":[56],"advantage":[58],"they":[60],"are":[61,97,137,148],"much":[62,149],"faster":[63,150],"to":[64,141,151],"train.":[65],"present":[67],"exploration":[69],"CNN":[71],"s":[72],"encoders":[74],"CTC":[76],"models,":[77],"context":[80],"character-based":[82],"(lexicon-free)":[83],"recognition.":[86],"In":[87],"particular,":[88],"we":[89],"range":[92],"one-dimensional":[94],"convolutionallayers,":[95],"which":[96],"particularly":[98],"efficient.":[99],"compare":[101],"performance":[103,140],"our":[105,134],"CNN-based":[106,135],"against":[108],"typical":[109],"RNN-based":[110],"terms":[113],"training":[115],"time,":[116,118],"decoding":[117],"model":[119],"size":[120],"and":[121,147,153],"word":[122],"error":[123],"rate":[124],"(WER)":[125],"Switchboard":[128],"Eva12000":[129],"corpus.":[130],"find":[132],"close":[138],"LSTMs,":[142],"while":[143],"not":[144],"matching":[145],"them,":[146],"train":[152],"decode.":[154]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}