{"id":"https://openalex.org/W2604132379","doi":"https://doi.org/10.21437/interspeech.2017-405","title":"English Conversational Telephone Speech Recognition by Humans and Machines","display_name":"English Conversational Telephone Speech Recognition by Humans and Machines","publication_year":2017,"publication_date":"2017-08-16","ids":{"openalex":"https://openalex.org/W2604132379","doi":"https://doi.org/10.21437/interspeech.2017-405","mag":"2604132379"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2017-405","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-405","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1703.02136","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079994647","display_name":"George Saon","orcid":"https://orcid.org/0009-0004-6837-5009"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"George Saon","raw_affiliation_strings":["IBM (United States), Armonk, United States"],"affiliations":[{"raw_affiliation_string":"IBM (United States), Armonk, United States","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021294422","display_name":"Gakuto Kurata","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gakuto Kurata","raw_affiliation_strings":["IBM (United States), Armonk, United States"],"affiliations":[{"raw_affiliation_string":"IBM (United States), Armonk, United States","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006044037","display_name":"Tom Sercu","orcid":"https://orcid.org/0000-0003-2947-6064"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tom Sercu","raw_affiliation_strings":["IBM (United States), Armonk, United States"],"affiliations":[{"raw_affiliation_string":"IBM (United States), Armonk, United States","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015927589","display_name":"Kartik Audhkhasi","orcid":"https://orcid.org/0000-0002-2340-1144"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kartik Audhkhasi","raw_affiliation_strings":["IBM (United States), Armonk, United States"],"affiliations":[{"raw_affiliation_string":"IBM (United States), Armonk, United States","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101787514","display_name":"Samuel Thomas","orcid":"https://orcid.org/0000-0001-7573-0620"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Samuel Thomas","raw_affiliation_strings":["IBM (United States), Armonk, United States"],"affiliations":[{"raw_affiliation_string":"IBM (United States), Armonk, United States","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115044944","display_name":"Dimitrios Dimitriadis","orcid":"https://orcid.org/0000-0001-8483-0105"},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"company","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dimitrios Dimitriadis","raw_affiliation_strings":["AT&T (United States), Bedminster, United States"],"affiliations":[{"raw_affiliation_string":"AT&T (United States), Bedminster, United States","institution_ids":["https://openalex.org/I1283103587"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102014291","display_name":"Xiaodong Cui","orcid":"https://orcid.org/0000-0003-4865-1307"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaodong Cui","raw_affiliation_strings":["IBM (United States), Armonk, United States"],"affiliations":[{"raw_affiliation_string":"IBM (United States), Armonk, United States","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071715737","display_name":"Bhuvana Ramabhadran","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bhuvana Ramabhadran","raw_affiliation_strings":["IBM (United States), Armonk, United States"],"affiliations":[{"raw_affiliation_string":"IBM (United States), Armonk, United States","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034529775","display_name":"Michael Picheny","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Picheny","raw_affiliation_strings":["IBM (United States), Armonk, United States"],"affiliations":[{"raw_affiliation_string":"IBM (United States), Armonk, United States","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006994122","display_name":"Lynn-Li Lim","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lynn-Li Lim","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041682898","display_name":"Bergul Roomi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bergul Roomi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5103361564","display_name":"Phil Hall","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Phil Hall","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":12,"corresponding_author_ids":["https://openalex.org/A5079994647"],"corresponding_institution_ids":["https://openalex.org/I1341412227"],"apc_list":null,"apc_paid":null,"fwci":12.462,"has_fulltext":true,"cited_by_count":79,"citation_normalized_percentile":{"value":0.98822555,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"132","last_page":"136"},"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/T10028","display_name":"Topic Modeling","score":0.9980999827384949,"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":0.9976999759674072,"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/computer-science","display_name":"Computer science","score":0.8178716897964478},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7066304683685303},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6009097099304199},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5599091053009033},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5569201707839966},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5237902402877808},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.45742547512054443},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4501957893371582},{"id":"https://openalex.org/keywords/statement","display_name":"Statement (logic)","score":0.4437797963619232},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.41677534580230713},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09912633895874023}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8178716897964478},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7066304683685303},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6009097099304199},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5599091053009033},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5569201707839966},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5237902402877808},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.45742547512054443},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4501957893371582},{"id":"https://openalex.org/C2777026412","wikidata":"https://www.wikidata.org/wiki/Q2684591","display_name":"Statement (logic)","level":2,"score":0.4437797963619232},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.41677534580230713},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09912633895874023},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2017-405","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-405","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1703.02136","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1703.02136","pdf_url":"https://arxiv.org/pdf/1703.02136","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:2604132379","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1703.02136","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.1703.02136","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1703.02136","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":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1703.02136","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1703.02136","pdf_url":"https://arxiv.org/pdf/1703.02136","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":[{"score":0.5899999737739563,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2604132379.pdf","grobid_xml":"https://content.openalex.org/works/W2604132379.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W753012316","https://openalex.org/W1522301498","https://openalex.org/W1533416326","https://openalex.org/W1591801644","https://openalex.org/W1686810756","https://openalex.org/W1731081199","https://openalex.org/W1736701665","https://openalex.org/W1899794420","https://openalex.org/W1987238397","https://openalex.org/W2028706510","https://openalex.org/W2121227244","https://openalex.org/W2125234026","https://openalex.org/W2194775991","https://openalex.org/W2198724430","https://openalex.org/W2394922404","https://openalex.org/W2401231614","https://openalex.org/W2510867321","https://openalex.org/W2530876040","https://openalex.org/W2533523411","https://openalex.org/W2594856242","https://openalex.org/W2949382160","https://openalex.org/W2949427019","https://openalex.org/W2949563612","https://openalex.org/W2951327905"],"related_works":["https://openalex.org/W2533523411","https://openalex.org/W2127141656","https://openalex.org/W1524333225","https://openalex.org/W2963266252","https://openalex.org/W2327501763","https://openalex.org/W2194775991","https://openalex.org/W2160815625","https://openalex.org/W1494198834","https://openalex.org/W2514741789","https://openalex.org/W2102113734","https://openalex.org/W2064675550","https://openalex.org/W2147768505","https://openalex.org/W1522301498","https://openalex.org/W854541894","https://openalex.org/W2964308564","https://openalex.org/W2936774411","https://openalex.org/W2193413348","https://openalex.org/W2916979304","https://openalex.org/W1922655562","https://openalex.org/W1821462560"],"abstract_inverted_index":{"One":[0],"of":[1,11,67,116,160,172,183,189,201,229],"the":[2,21,32,139,168,181,186,190,199,221,260],"most":[3,55],"difficult":[4],"speech":[5,28,88],"recognition":[6,10,29,89],"tasks":[7,123],"is":[8,205],"accurate":[9],"human":[12,14,68,78,103,117,127,218],"to":[13,50,62,107,145,180,216],"communication.":[15],"Advances":[16],"in":[17,154],"deep":[18],"learning":[19,245],"over":[20],"last":[22],"few":[23,43],"years":[24,44],"have":[25,48,100],"produced":[26],"major":[27],"improvements":[30],"on":[31,120,150,185],"representative":[33],"Switchboard":[34],"conversational":[35,122,176],"corpus.":[36],"Word":[37],"error":[38,90,170],"rates":[39],"that":[40,98,126,166],"just":[41],"a":[42,141,158,206,226,238,247],"ago":[45],"were":[46],"14%":[47],"dropped":[49],"8.0%,":[51],"then":[52,71],"6.6%":[53],"and":[54,58,80,124,162,246,256,267,270],"recently":[56],"5.8%,":[57],"are":[59],"now":[60],"believed":[61],"be":[63,130,217],"within":[64],"striking":[65],"range":[66],"performance.":[69,104],"This":[70],"raises":[72],"two":[73,121],"issues":[74],"-":[75,195,204],"what":[76,134,213],"IS":[77],"performance,":[79],"how":[81],"far":[82],"down":[83],"can":[84],"we":[85,99,111,214,224,264],"still":[86],"drive":[87],"rates?":[91],"A":[92],"recent":[93],"paper":[94,203],"by":[95],"Microsoft":[96],"suggests":[97],"already":[101],"achieved":[102],"In":[105],"trying":[106],"verify":[108],"this":[109,155,202],"statement,":[110],"performed":[112],"an":[113],"independent":[114],"set":[115,159],"performance":[118,128,208],"measurements":[119],"found":[125],"may":[129],"considerably":[131],"better":[132],"than":[133],"was":[135],"earlier":[136],"reported,":[137],"giving":[138],"community":[140],"significantly":[142],"harder":[143],"goal":[144],"achieve.":[146],"We":[147],"also":[148],"report":[149],"our":[151,173],"own":[152,174],"efforts":[153],"area,":[156],"presenting":[157],"acoustic":[161,222],"language":[163,261,273],"modeling":[164,262],"techniques":[165],"lowered":[167],"word":[169,266],"rate":[171],"English":[175],"telephone":[177],"LVCSR":[178],"system":[179],"level":[182],"5.5%/10.3%":[184],"Switchboard/CallHome":[187],"subsets":[188],"Hub5":[191],"2000":[192],"evaluation,":[193],"which":[194],"at":[196,198,212],"least":[197],"writing":[200],"new":[207],"milestone":[209],"(albeit":[210],"not":[211],"measure":[215],"performance!).":[219],"On":[220,259],"side,":[223,263],"use":[225,265],"score":[227],"fusion":[228],"three":[230],"models:":[231],"one":[232],"LSTM":[233,240],"with":[234,242,252],"multiple":[235],"feature":[236],"inputs,":[237],"second":[239],"trained":[241],"speaker-adversarial":[243],"multi-task":[244],"third":[248],"residual":[249],"net":[250],"(ResNet)":[251],"25":[253],"convolutional":[254,271],"layers":[255],"time-dilated":[257],"convolutions.":[258],"character":[268],"LSTMs":[269],"WaveNet-style":[272],"models.":[274]},"counts_by_year":[{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":15},{"year":2020,"cited_by_count":22},{"year":2019,"cited_by_count":14},{"year":2018,"cited_by_count":14},{"year":2017,"cited_by_count":10}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}