{"id":"https://openalex.org/W3002595344","doi":"https://doi.org/10.21437/interspeech.2020-1488","title":"Single Headed Attention Based Sequence-to-Sequence Model for State-of-the-Art Results on Switchboard","display_name":"Single Headed Attention Based Sequence-to-Sequence Model for State-of-the-Art Results on Switchboard","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3002595344","doi":"https://doi.org/10.21437/interspeech.2020-1488","mag":"3002595344"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-1488","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1488","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","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/2001.07263","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047353872","display_name":"Zolt\u00e1n T\u00fcske","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zolt\u00e1n T\u00fcske","raw_affiliation_strings":["IBM"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079994647","display_name":"George Saon","orcid":"https://orcid.org/0009-0004-6837-5009"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"George Saon","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015927589","display_name":"Kartik Audhkhasi","orcid":"https://orcid.org/0000-0002-2340-1144"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kartik Audhkhasi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5003725957","display_name":"Brian Kingsbury","orcid":"https://orcid.org/0000-0002-1343-6837"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Brian Kingsbury","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":null,"has_fulltext":true,"cited_by_count":42,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"551","last_page":"555"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.998199999332428,"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":0.9980000257492065,"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/pronunciation","display_name":"Pronunciation","score":0.8652485609054565},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6841129660606384},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.6480962634086609},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.6360266208648682},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6317214369773865},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5434257984161377},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5320544838905334},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.5088610649108887},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.4763472378253937},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4480401575565338},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4202617108821869},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4105875790119171},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3756767213344574},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35929059982299805},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.20938414335250854},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.14056020975112915}],"concepts":[{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.8652485609054565},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6841129660606384},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6480962634086609},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6360266208648682},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6317214369773865},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5434257984161377},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5320544838905334},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.5088610649108887},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.4763472378253937},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4480401575565338},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4202617108821869},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4105875790119171},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3756767213344574},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35929059982299805},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.20938414335250854},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.14056020975112915},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2020-1488","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1488","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2001.07263","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2001.07263","pdf_url":"https://arxiv.org/pdf/2001.07263","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:3002595344","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2001.07263.pdf","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.2001.07263","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2001.07263","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:2001.07263","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2001.07263","pdf_url":"https://arxiv.org/pdf/2001.07263","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","score":0.7900000214576721,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3002595344.pdf","grobid_xml":"https://content.openalex.org/works/W3002595344.grobid-xml"},"referenced_works_count":55,"referenced_works":["https://openalex.org/W4919037","https://openalex.org/W648786980","https://openalex.org/W854541894","https://openalex.org/W1524333225","https://openalex.org/W1553004968","https://openalex.org/W1828163288","https://openalex.org/W1836465849","https://openalex.org/W1904365287","https://openalex.org/W1915251500","https://openalex.org/W1977434607","https://openalex.org/W1989674786","https://openalex.org/W2064675550","https://openalex.org/W2072349636","https://openalex.org/W2094225911","https://openalex.org/W2095705004","https://openalex.org/W2108677974","https://openalex.org/W2111406701","https://openalex.org/W2131774270","https://openalex.org/W2144513243","https://openalex.org/W2145249131","https://openalex.org/W2183341477","https://openalex.org/W2193413348","https://openalex.org/W2194775991","https://openalex.org/W2288502450","https://openalex.org/W2296073425","https://openalex.org/W2327501763","https://openalex.org/W2400505028","https://openalex.org/W2402268235","https://openalex.org/W2407080277","https://openalex.org/W2622263826","https://openalex.org/W2747685395","https://openalex.org/W2782451907","https://openalex.org/W2798405286","https://openalex.org/W2888781539","https://openalex.org/W2889282842","https://openalex.org/W2899771611","https://openalex.org/W2916979304","https://openalex.org/W2936774411","https://openalex.org/W2937780860","https://openalex.org/W2962826786","https://openalex.org/W2962970071","https://openalex.org/W2963260202","https://openalex.org/W2963266252","https://openalex.org/W2963266340","https://openalex.org/W2963403868","https://openalex.org/W2963827914","https://openalex.org/W2964286182","https://openalex.org/W2964308564","https://openalex.org/W2972818416","https://openalex.org/W2973229104","https://openalex.org/W2981857663","https://openalex.org/W2991324852","https://openalex.org/W3007776460","https://openalex.org/W3015889230","https://openalex.org/W3103005696"],"related_works":["https://openalex.org/W2936774411","https://openalex.org/W2327501763","https://openalex.org/W1828163288","https://openalex.org/W2127141656","https://openalex.org/W2064675550","https://openalex.org/W1494198834","https://openalex.org/W2962826786","https://openalex.org/W2407080277","https://openalex.org/W3016234571","https://openalex.org/W2964308564","https://openalex.org/W2166637769","https://openalex.org/W3008191852","https://openalex.org/W3008174054","https://openalex.org/W2972818416","https://openalex.org/W2937780860","https://openalex.org/W2799800213","https://openalex.org/W1553004968","https://openalex.org/W854541894","https://openalex.org/W1915251500","https://openalex.org/W1524333225"],"abstract_inverted_index":{"It":[0],"is":[1,28,106],"generally":[2],"believed":[3],"that":[4,37,104],"direct":[5],"sequence-to-sequence":[6],"(seq2seq)":[7],"speech":[8],"recognition":[9,39],"models":[10,15],"are":[11,92],"competitive":[12],"with":[13],"hybrid":[14],"only":[16],"when":[17],"a":[18,25,49,57,83,119,127],"large":[19,123],"amount":[20],"of":[21,80,98,115,130],"data,":[22],"at":[23],"least":[24],"thousand":[26],"hours,":[27],"available":[29],"for":[30],"training.":[31],"In":[32],"this":[33,96],"paper,":[34],"we":[35],"show":[36,103],"state-of-the-art":[38],"performance":[40],"can":[41],"be":[42],"achieved":[43],"on":[44,74,101,137],"the":[45,75,113,131,138],"Switchboard-300":[46],"database":[47],"using":[48,143],"single":[50],"headed":[51],"attention,":[52],"LSTM":[53],"based":[54],"model.":[55],"Using":[56],"cross-utterance":[58],"language":[59],"model,":[60],"our":[61],"single-pass":[62],"speaker":[63],"independent":[64],"system":[65],"reaches":[66],"6.4%":[67],"and":[68,77,89,118,134,140],"12.5%":[69],"word":[70],"error":[71],"rate":[72],"(WER)":[73],"Switchboard":[76,139],"CallHome":[78,141],"subsets":[79],"Hub5'00,":[81],"without":[82,145],"pronunciation":[84],"lexicon.":[85],"While":[86],"careful":[87],"regularization":[88],"data":[90,148],"augmentation":[91],"crucial":[93],"in":[94,126],"achieving":[95],"level":[97],"performance,":[99],"experiments":[100],"Switchboard-2000":[102],"nothing":[105],"more":[107,110],"useful":[108],"than":[109],"data.":[111],"Overall,":[112],"combination":[114],"various":[116],"regularizations":[117],"simple":[120],"but":[121],"fairly":[122],"model":[124],"results":[125],"new":[128],"state":[129],"art,":[132],"4.7%":[133],"7.8%":[135],"WER":[136],"sets,":[142],"SWB-2000":[144],"any":[146],"external":[147],"resources.":[149]},"counts_by_year":[{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":24},{"year":2020,"cited_by_count":7}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2022-07-26T00:00:00"}