{"id":"https://openalex.org/W2926063217","doi":"https://doi.org/10.21437/interspeech.2019-2460","title":"Sequence-to-Sequence Speech Recognition with Time-Depth Separable Convolutions","display_name":"Sequence-to-Sequence Speech Recognition with Time-Depth Separable Convolutions","publication_year":2019,"publication_date":"2019-09-13","ids":{"openalex":"https://openalex.org/W2926063217","doi":"https://doi.org/10.21437/interspeech.2019-2460","mag":"2926063217"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2019-2460","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-2460","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/1904.02619","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5087325198","display_name":"Awni Hannun","orcid":"https://orcid.org/0000-0003-3080-4002"},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Awni Hannun","raw_affiliation_strings":["Facebook"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084509956","display_name":"Ann Lee","orcid":"https://orcid.org/0000-0003-4300-9032"},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Ann Lee","raw_affiliation_strings":["Facebook"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102647000","display_name":"Qiantong Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Qiantong Xu","raw_affiliation_strings":["Facebook"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053915453","display_name":"Ronan Collobert","orcid":null},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Ronan Collobert","raw_affiliation_strings":["Facebook"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook","institution_ids":["https://openalex.org/I2252078561"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2252078561"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3785","last_page":"3789"},"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":0.9998000264167786,"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":0.9984999895095825,"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/sequence","display_name":"Sequence (biology)","score":0.7551395297050476},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.6772491335868835},{"id":"https://openalex.org/keywords/convolutional-code","display_name":"Convolutional code","score":0.6724860668182373},{"id":"https://openalex.org/keywords/separable-space","display_name":"Separable space","score":0.663454532623291},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6083986759185791},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5716253519058228},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5352352857589722},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5221878886222839},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5212560296058655},{"id":"https://openalex.org/keywords/beam-search","display_name":"Beam search","score":0.45081526041030884},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.44405195116996765},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4316480755805969},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.41475069522857666},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.38029158115386963},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.3574354648590088},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.28206735849380493},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2816646993160248},{"id":"https://openalex.org/keywords/search-algorithm","display_name":"Search algorithm","score":0.11692103743553162}],"concepts":[{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.7551395297050476},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.6772491335868835},{"id":"https://openalex.org/C157899210","wikidata":"https://www.wikidata.org/wiki/Q1395022","display_name":"Convolutional code","level":3,"score":0.6724860668182373},{"id":"https://openalex.org/C70710897","wikidata":"https://www.wikidata.org/wiki/Q680081","display_name":"Separable space","level":2,"score":0.663454532623291},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6083986759185791},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5716253519058228},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5352352857589722},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5221878886222839},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5212560296058655},{"id":"https://openalex.org/C19889080","wikidata":"https://www.wikidata.org/wiki/Q2835852","display_name":"Beam search","level":3,"score":0.45081526041030884},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.44405195116996765},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4316480755805969},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.41475069522857666},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.38029158115386963},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.3574354648590088},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28206735849380493},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2816646993160248},{"id":"https://openalex.org/C125583679","wikidata":"https://www.wikidata.org/wiki/Q755673","display_name":"Search algorithm","level":2,"score":0.11692103743553162},{"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/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2019-2460","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-2460","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:1904.02619","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1904.02619","pdf_url":"https://arxiv.org/pdf/1904.02619","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":null,"raw_type":"text"},{"id":"mag:2926063217","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1904.02619","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.1904.02619","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1904.02619","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:1904.02619","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1904.02619","pdf_url":"https://arxiv.org/pdf/1904.02619","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":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7200000286102295,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W2926063217.pdf"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W648786980","https://openalex.org/W854541894","https://openalex.org/W1494198834","https://openalex.org/W1524333225","https://openalex.org/W1667652561","https://openalex.org/W1902237438","https://openalex.org/W1904365287","https://openalex.org/W1922655562","https://openalex.org/W2130942839","https://openalex.org/W2134800885","https://openalex.org/W2157331557","https://openalex.org/W2163605009","https://openalex.org/W2183341477","https://openalex.org/W2194775991","https://openalex.org/W2327501763","https://openalex.org/W2520160253","https://openalex.org/W2530876040","https://openalex.org/W2531409750","https://openalex.org/W2549139847","https://openalex.org/W2612445135","https://openalex.org/W2613904329","https://openalex.org/W2782451907","https://openalex.org/W2799800213","https://openalex.org/W2885185669","https://openalex.org/W2888519496","https://openalex.org/W2904818793","https://openalex.org/W2908336025","https://openalex.org/W2950903920","https://openalex.org/W2952444318","https://openalex.org/W2953190524","https://openalex.org/W2962784628","https://openalex.org/W2963403868","https://openalex.org/W2963703197","https://openalex.org/W2963970792","https://openalex.org/W2963979492","https://openalex.org/W2964308564"],"related_works":["https://openalex.org/W2972630480","https://openalex.org/W1494198834","https://openalex.org/W2936774411","https://openalex.org/W2127141656","https://openalex.org/W2904818793","https://openalex.org/W2327501763","https://openalex.org/W3165858867","https://openalex.org/W2884873108","https://openalex.org/W2513928851","https://openalex.org/W3176696796","https://openalex.org/W3014973596","https://openalex.org/W3097554094","https://openalex.org/W2951550300","https://openalex.org/W2941599692","https://openalex.org/W3157602250","https://openalex.org/W3129726516","https://openalex.org/W2787718318","https://openalex.org/W3100718443","https://openalex.org/W2973212992","https://openalex.org/W2810544457"],"abstract_inverted_index":{"We":[0,59],"propose":[1],"a":[2,9,29,38,62,76,81],"fully":[3],"convolutional":[4,82],"sequence-to-sequence":[5,102],"encoder":[6],"architecture":[7,89],"with":[8,80],"simple":[10],"and":[11,64],"efficient":[12,27,65],"decoder.":[13],"Our":[14],"model":[15,52],"improves":[16,90],"WER":[17,96],"on":[18,104],"LibriSpeech":[19,107],"while":[20,53],"being":[21],"an":[22],"order":[23],"of":[24,48],"magnitude":[25],"more":[26,92],"than":[28,93],"strong":[30],"RNN":[31],"baseline.":[32],"Key":[33],"to":[34,73],"our":[35,85],"approach":[36],"is":[37],"time-depth":[39,86],"separable":[40,87],"convolution":[41,88],"block":[42],"which":[43,70],"dramatically":[44],"reduces":[45],"the":[46,51,55,98,105],"number":[47],"parameters":[49],"in":[50],"keeping":[54],"receptive":[56],"field":[57],"large.":[58],"also":[60],"give":[61],"stable":[63],"beam":[66],"search":[67],"inference":[68],"procedure":[69],"allows":[71],"us":[72],"effectively":[74],"integrate":[75],"language":[77,83],"model.":[78],"Coupled":[79],"model,":[84],"by":[91],"22%":[94],"relative":[95],"over":[97],"best":[99],"previously":[100],"reported":[101],"results":[103],"noisy":[106],"test":[108],"set.":[109]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2022-07-24T00:00:00"}