{"id":"https://openalex.org/W2943493972","doi":"https://doi.org/10.21437/interspeech.2019-2702","title":"Very Deep Self-Attention Networks for End-to-End Speech Recognition","display_name":"Very Deep Self-Attention Networks for End-to-End Speech Recognition","publication_year":2019,"publication_date":"2019-09-13","ids":{"openalex":"https://openalex.org/W2943493972","doi":"https://doi.org/10.21437/interspeech.2019-2702","mag":"2943493972"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2019-2702","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-2702","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","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/1904.13377","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004365148","display_name":"Ngoc-Quan Pham","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ngoc-Quan Pham","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082064946","display_name":"Thai\u2010Son Nguyen","orcid":"https://orcid.org/0000-0001-7008-0462"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thai-Son Nguyen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046084081","display_name":"Jan Niehues","orcid":"https://orcid.org/0000-0002-4231-6543"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jan Niehues","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106134095","display_name":"Markus M\u00fcller","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Markus M\u00fcller","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Alex Waibel","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alex Waibel","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.8111,"has_fulltext":true,"cited_by_count":48,"citation_normalized_percentile":{"value":0.96325424,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"66","last_page":"70"},"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/T10860","display_name":"Speech 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/T11309","display_name":"Music and Audio Processing","score":0.9991000294685364,"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/end-to-end-principle","display_name":"End-to-end principle","score":0.8316417932510376},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7494571805000305},{"id":"https://openalex.org/keywords/generalizability-theory","display_name":"Generalizability theory","score":0.7419941425323486},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6869228482246399},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5631595253944397},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5544963479042053},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5532424449920654},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5105725526809692},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.496481716632843},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.49342671036720276},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4618450999259949},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1517464816570282}],"concepts":[{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.8316417932510376},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7494571805000305},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.7419941425323486},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6869228482246399},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5631595253944397},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5544963479042053},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5532424449920654},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5105725526809692},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.496481716632843},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.49342671036720276},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4618450999259949},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1517464816570282},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"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":4,"locations":[{"id":"doi:10.21437/interspeech.2019-2702","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-2702","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1904.13377","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1904.13377","pdf_url":"https://arxiv.org/pdf/1904.13377","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"","raw_type":null},{"id":"mag:2943493972","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1904.13377.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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.1904.13377","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1904.13377","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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:1904.13377","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1904.13377","pdf_url":"https://arxiv.org/pdf/1904.13377","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"","raw_type":null},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2943493972.pdf","grobid_xml":"https://content.openalex.org/works/W2943493972.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W1902237438","https://openalex.org/W2064675550","https://openalex.org/W2095705004","https://openalex.org/W2117671523","https://openalex.org/W2183341477","https://openalex.org/W2293858598","https://openalex.org/W2407080277","https://openalex.org/W2514741789","https://openalex.org/W2530876040","https://openalex.org/W2613904329","https://openalex.org/W2626778328","https://openalex.org/W2766453196","https://openalex.org/W2795138957","https://openalex.org/W2799800213","https://openalex.org/W2888520903","https://openalex.org/W2888884590","https://openalex.org/W2889163603","https://openalex.org/W2892009249","https://openalex.org/W2902292292","https://openalex.org/W2911291251","https://openalex.org/W2962826786","https://openalex.org/W2963341956","https://openalex.org/W2964121744","https://openalex.org/W2964308564","https://openalex.org/W3101648800"],"related_works":["https://openalex.org/W2963403868","https://openalex.org/W2936774411","https://openalex.org/W2892009249","https://openalex.org/W2327501763","https://openalex.org/W2964308564","https://openalex.org/W2127141656","https://openalex.org/W2963341956","https://openalex.org/W2962784628","https://openalex.org/W1494198834","https://openalex.org/W854541894","https://openalex.org/W2194775991","https://openalex.org/W1828163288","https://openalex.org/W2972818416","https://openalex.org/W2962826786","https://openalex.org/W2102113734","https://openalex.org/W1522301498","https://openalex.org/W2963242190","https://openalex.org/W2962780374","https://openalex.org/W2064675550","https://openalex.org/W2526425061"],"abstract_inverted_index":{"Recently,":[0],"end-to-end":[1,63,107,135],"sequence-to-sequence":[2],"models":[3,77,103,118,136],"for":[4,84],"speech":[5],"recognition":[6],"have":[7],"gained":[8],"significant":[9],"interest":[10],"in":[11,159],"the":[12,39,68,111,148],"research":[13],"community.":[14],"While":[15],"previous":[16,62,106,141],"architecture":[17,41],"choices":[18],"revolve":[19],"around":[20],"time-delay":[21],"neural":[22,31],"networks":[23,51],"(TDNN)":[24],"and":[25,65,87,98,121,126,164],"long":[26],"short-term":[27],"memory":[28],"(LSTM)":[29],"recurrent":[30],"networks,":[32],"we":[33,73],"propose":[34],"to":[35,58,80,137],"use":[36],"self-attention":[37],"via":[38],"Transformer":[40,50,82],"as":[42],"an":[43],"alternative.":[44],"Our":[45],"analysis":[46],"shows":[47],"that":[48],"deep":[49,76],"with":[52,78,90,140,145],"high":[53],"learning":[54],"capacity":[55],"are":[56,156],"able":[57],"exceed":[59],"performance":[60],"from":[61],"approaches":[64,109],"even":[66],"match":[67],"conventional":[69],"hybrid":[70,142,153],"systems.":[71,143],"Moreover,":[72],"trained":[74],"very":[75],"up":[79],"48":[81],"layers":[83],"both":[85,162],"encoder":[86],"decoders":[88],"combined":[89],"stochastic":[91],"residual":[92],"connections,":[93],"which":[94,155],"greatly":[95],"improve":[96],"generalizability":[97],"training":[99,165],"efficiency.":[100],"The":[101],"resulting":[102],"outperform":[104,151],"all":[105],"ASR":[108],"on":[110,124],"Switchboard":[112,125],"benchmark.":[113],"An":[114],"ensemble":[115],"of":[116,161],"these":[117],"achieve":[119],"9.9%":[120],"17.7%":[122],"WER":[123],"CallHome":[127],"test":[128],"sets":[129],"respectively.":[130],"This":[131],"finding":[132],"brings":[133],"our":[134],"competitive":[138],"levels":[139],"Further,":[144],"model":[146],"ensembling":[147],"Transformers":[149],"can":[150],"certain":[152],"systems,":[154],"more":[157],"complicated":[158],"terms":[160],"structure":[163],"procedure.":[166]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":23},{"year":2020,"cited_by_count":16},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}