{"id":"https://openalex.org/W2911291251","doi":"https://doi.org/10.1109/icassp.2019.8682539","title":"Self-attention Networks for Connectionist Temporal Classification in Speech Recognition","display_name":"Self-attention Networks for Connectionist Temporal Classification in Speech Recognition","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2911291251","doi":"https://doi.org/10.1109/icassp.2019.8682539","mag":"2911291251"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8682539","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682539","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1901.10055","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037283647","display_name":"Juli\u00e1n Salazar","orcid":"https://orcid.org/0000-0003-0943-7594"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Julian Salazar","raw_affiliation_strings":["Amazon AI"],"affiliations":[{"raw_affiliation_string":"Amazon AI","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050325468","display_name":"Katrin Kirchhoff","orcid":"https://orcid.org/0000-0002-6645-6030"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Katrin Kirchhoff","raw_affiliation_strings":["University of Washington"],"affiliations":[{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011349177","display_name":"Zhiheng Huang","orcid":"https://orcid.org/0000-0001-5982-9778"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhiheng Huang","raw_affiliation_strings":["Amazon AI"],"affiliations":[{"raw_affiliation_string":"Amazon AI","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5037283647"],"corresponding_institution_ids":["https://openalex.org/I1311688040"],"apc_list":null,"apc_paid":null,"fwci":14.5753,"has_fulltext":false,"cited_by_count":133,"citation_normalized_percentile":{"value":0.99113315,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"2019","issue":null,"first_page":"7115","last_page":"7119"},"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/T11309","display_name":"Music and Audio Processing","score":0.9993000030517578,"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":0.996999979019165,"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/connectionism","display_name":"Connectionism","score":0.8362631797790527},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7870264053344727},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7381313443183899},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5866181254386902},{"id":"https://openalex.org/keywords/upsampling","display_name":"Upsampling","score":0.5567947626113892},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.4882676601409912},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4730866551399231},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4445186257362366},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.41551387310028076},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3089092969894409},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.09391742944717407}],"concepts":[{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.8362631797790527},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7870264053344727},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7381313443183899},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5866181254386902},{"id":"https://openalex.org/C110384440","wikidata":"https://www.wikidata.org/wiki/Q1143270","display_name":"Upsampling","level":3,"score":0.5567947626113892},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.4882676601409912},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4730866551399231},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4445186257362366},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.41551387310028076},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3089092969894409},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.09391742944717407},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp.2019.8682539","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682539","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1901.10055","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1901.10055","pdf_url":"https://arxiv.org/pdf/1901.10055","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:3088610837","is_oa":false,"landing_page_url":"https://jglobal.jst.go.jp/en/detail?JGLOBAL_ID=201902284823469853","pdf_url":null,"source":{"id":"https://openalex.org/S4306512817","display_name":"IEEE Conference Proceedings","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":null,"raw_source_name":"IEEE Conference Proceedings","raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1901.10055","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1901.10055","pdf_url":"https://arxiv.org/pdf/1901.10055","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":[{"id":"https://metadata.un.org/sdg/4","score":0.5699999928474426,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":66,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1524333225","https://openalex.org/W1600744878","https://openalex.org/W1710082047","https://openalex.org/W1922655562","https://openalex.org/W2102113734","https://openalex.org/W2110871230","https://openalex.org/W2127141656","https://openalex.org/W2130942839","https://openalex.org/W2133564696","https://openalex.org/W2170942820","https://openalex.org/W2186615578","https://openalex.org/W2193413348","https://openalex.org/W2267186426","https://openalex.org/W2293858598","https://openalex.org/W2327501763","https://openalex.org/W2477205648","https://openalex.org/W2520160253","https://openalex.org/W2526425061","https://openalex.org/W2530876040","https://openalex.org/W2593910181","https://openalex.org/W2627092829","https://openalex.org/W2750499125","https://openalex.org/W2781384251","https://openalex.org/W2799800213","https://openalex.org/W2802023636","https://openalex.org/W2808640845","https://openalex.org/W2808998745","https://openalex.org/W2885724687","https://openalex.org/W2888779557","https://openalex.org/W2892009249","https://openalex.org/W2962712200","https://openalex.org/W2962778134","https://openalex.org/W2962824709","https://openalex.org/W2962826786","https://openalex.org/W2962962542","https://openalex.org/W2963071736","https://openalex.org/W2963211739","https://openalex.org/W2963226322","https://openalex.org/W2963403664","https://openalex.org/W2963403868","https://openalex.org/W2963727906","https://openalex.org/W2963742216","https://openalex.org/W2964089206","https://openalex.org/W2964189376","https://openalex.org/W2964308564","https://openalex.org/W4289440825","https://openalex.org/W4297818305","https://openalex.org/W4385245566","https://openalex.org/W6631362777","https://openalex.org/W6640090968","https://openalex.org/W6675365184","https://openalex.org/W6679434410","https://openalex.org/W6679436768","https://openalex.org/W6686509673","https://openalex.org/W6687566353","https://openalex.org/W6703944212","https://openalex.org/W6727336983","https://openalex.org/W6734241735","https://openalex.org/W6739366949","https://openalex.org/W6739901393","https://openalex.org/W6743440867","https://openalex.org/W6744649695","https://openalex.org/W6747270024","https://openalex.org/W6752630080","https://openalex.org/W6754576867"],"related_works":["https://openalex.org/W2062399876","https://openalex.org/W2607795551","https://openalex.org/W4205841273","https://openalex.org/W4205525690","https://openalex.org/W1732468982","https://openalex.org/W1761388607","https://openalex.org/W3155117723","https://openalex.org/W1991429770","https://openalex.org/W1983892167","https://openalex.org/W1997922073"],"abstract_inverted_index":{"The":[0],"success":[1],"of":[2,81],"self-attention":[3],"in":[4,11,37,83,91],"NLP":[5],"has":[6,23],"led":[7],"to":[8,30],"recent":[9],"applications":[10],"end-to-end":[12,61],"encoder-decoder":[13,74],"architectures":[14],"for":[15,51,60,107,116],"speech":[16,62],"recognition.":[17,63],"Separately,":[18],"connectionist":[19],"temporal":[20],"classification":[21],"(CTC)":[22],"matured":[24],"as":[25],"an":[26],"alignment-free,":[27],"non-autoregressive":[28],"approach":[29],"sequence":[31],"transduction,":[32],"either":[33],"by":[34],"itself":[35],"or":[36],"various":[38],"multitask":[39],"and":[40,53,58,67,72,89,101,120,123,134],"decoding":[41],"frameworks.":[42],"We":[43,112],"propose":[44],"SAN-CTC,":[45],"a":[46,98],"deep,":[47],"fully":[48],"self-attentional":[49],"network":[50],"CTC,":[52],"show":[54],"it":[55],"is":[56],"tractable":[57],"competitive":[59],"SAN-CTC":[64],"trains":[65],"quickly":[66],"outperforms":[68],"existing":[69],"CTC":[70],"models":[71],"most":[73],"models,":[75],"with":[76,97],"character":[77],"error":[78],"rates":[79],"(CERs)":[80],"4.7%":[82],"1":[84,92],"day":[85],"on":[86,94],"WSJ":[87],"eval92":[88],"2.8%":[90],"week":[93],"LibriSpeech":[95],"test-clean,":[96],"fixed":[99],"architecture":[100,115],"one":[102],"GPU.":[103],"Similar":[104],"improvements":[105],"hold":[106],"WERs":[108],"after":[109],"LM":[110],"decoding.":[111],"motivate":[113],"the":[114],"speech,":[117],"evaluate":[118],"position":[119],"down-sampling":[121],"approaches,":[122],"explore":[124],"how":[125],"label":[126],"alphabets":[127],"(character,":[128],"phoneme,":[129],"subword)":[130],"affect":[131],"attention":[132],"heads":[133],"performance.":[135]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":18},{"year":2022,"cited_by_count":18},{"year":2021,"cited_by_count":28},{"year":2020,"cited_by_count":35},{"year":2019,"cited_by_count":20}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}