{"id":"https://openalex.org/W2937657912","doi":"https://doi.org/10.1109/icassp.2019.8683211","title":"English Broadcast News Speech Recognition by Humans and Machines","display_name":"English Broadcast News Speech Recognition by Humans and Machines","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2937657912","doi":"https://doi.org/10.1109/icassp.2019.8683211","mag":"2937657912"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8683211","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683211","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":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1904.13258","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101787514","display_name":"Samuel Thomas","orcid":"https://orcid.org/0000-0001-7573-0620"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Samuel Thomas","raw_affiliation_strings":["IBM Research AI, USA"],"affiliations":[{"raw_affiliation_string":"IBM Research AI, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028421346","display_name":"Masayuki Suzuki","orcid":"https://orcid.org/0000-0002-0436-1490"},"institutions":[{"id":"https://openalex.org/I4210145865","display_name":"IBM Research - Tokyo","ror":"https://ror.org/04915qk43","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210145865"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masayuki Suzuki","raw_affiliation_strings":["IBM Research AI, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"IBM Research AI, Tokyo, Japan","institution_ids":["https://openalex.org/I4210145865"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101673889","display_name":"Yinghui Huang","orcid":"https://orcid.org/0000-0003-0607-1507"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yinghui Huang","raw_affiliation_strings":["IBM Research AI, USA"],"affiliations":[{"raw_affiliation_string":"IBM Research AI, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021294422","display_name":"Gakuto Kurata","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145865","display_name":"IBM Research - Tokyo","ror":"https://ror.org/04915qk43","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210145865"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Gakuto Kurata","raw_affiliation_strings":["IBM Research AI, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"IBM Research AI, Tokyo, Japan","institution_ids":["https://openalex.org/I4210145865"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047353872","display_name":"Zolt\u00e1n T\u00fcske","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zoltan Tuske","raw_affiliation_strings":["IBM Research AI, USA"],"affiliations":[{"raw_affiliation_string":"IBM Research AI, USA","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":["IBM Research AI, USA"],"affiliations":[{"raw_affiliation_string":"IBM Research AI, USA","institution_ids":[]}]},{"author_position":"middle","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":["IBM Research AI, USA"],"affiliations":[{"raw_affiliation_string":"IBM Research AI, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034529775","display_name":"Michael Picheny","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michael Picheny","raw_affiliation_strings":["IBM Research AI, USA"],"affiliations":[{"raw_affiliation_string":"IBM Research AI, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080404107","display_name":"Tom Dibert","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tom Dibert","raw_affiliation_strings":["Appen, Sydney, Australia"],"affiliations":[{"raw_affiliation_string":"Appen, Sydney, Australia","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060117476","display_name":"Alice Kaiser-Schatzlein","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alice Kaiser-Schatzlein","raw_affiliation_strings":["Appen, Sydney, Australia"],"affiliations":[{"raw_affiliation_string":"Appen, Sydney, Australia","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062417061","display_name":"Bern Samko","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bern Samko","raw_affiliation_strings":["Appen, Sydney, Australia"],"affiliations":[{"raw_affiliation_string":"Appen, Sydney, Australia","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":11,"corresponding_author_ids":["https://openalex.org/A5101787514"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.302,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.853072,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"6455","last_page":"6459"},"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":0.9983999729156494,"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":0.9980000257492065,"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/computer-science","display_name":"Computer science","score":0.8413885831832886},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7285418510437012},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.633764922618866},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.598153829574585},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5660747289657593},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5342556238174438},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4976673424243927},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49109959602355957},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.46857404708862305},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4317416548728943},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4185379147529602},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4176270067691803},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3404603600502014},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07082408666610718}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8413885831832886},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7285418510437012},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.633764922618866},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.598153829574585},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5660747289657593},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5342556238174438},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4976673424243927},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49109959602355957},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.46857404708862305},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4317416548728943},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4185379147529602},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4176270067691803},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3404603600502014},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07082408666610718},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2019.8683211","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683211","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:1904.13258","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1904.13258","pdf_url":"https://arxiv.org/pdf/1904.13258","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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1904.13258","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1904.13258","pdf_url":"https://arxiv.org/pdf/1904.13258","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W103244930","https://openalex.org/W245306944","https://openalex.org/W1522301498","https://openalex.org/W1594833364","https://openalex.org/W1773599773","https://openalex.org/W2097560587","https://openalex.org/W2098318492","https://openalex.org/W2099424804","https://openalex.org/W2117590177","https://openalex.org/W2128014038","https://openalex.org/W2161513525","https://openalex.org/W2163426739","https://openalex.org/W2194775991","https://openalex.org/W2288371874","https://openalex.org/W2493346775","https://openalex.org/W2746475861","https://openalex.org/W2782451907","https://openalex.org/W2916979304","https://openalex.org/W2962719052","https://openalex.org/W2962832505","https://openalex.org/W2963266252","https://openalex.org/W2963499843","https://openalex.org/W2964121744","https://openalex.org/W2964286182","https://openalex.org/W4285719527","https://openalex.org/W4299838440","https://openalex.org/W6631190155","https://openalex.org/W6677717300","https://openalex.org/W6735593169","https://openalex.org/W6742632731","https://openalex.org/W6747836893"],"related_works":["https://openalex.org/W2145230572","https://openalex.org/W2401827384","https://openalex.org/W2355290951","https://openalex.org/W2166312020","https://openalex.org/W2052688117","https://openalex.org/W2150750161","https://openalex.org/W151018310","https://openalex.org/W642007152","https://openalex.org/W2341426843","https://openalex.org/W2131711534"],"abstract_inverted_index":{"With":[0],"recent":[1],"advances":[2],"in":[3,172],"deep":[4],"learning,":[5],"considerable":[6],"attention":[7],"has":[8],"been":[9],"given":[10],"to":[11,18,56,67,137,175],"achieving":[12,114],"automatic":[13,62],"speech":[14,26,63,84],"recognition":[15,54,64,85,147],"performance":[16,20,69,116,148,178],"close":[17,59],"human":[19,68,146,177],"on":[21,40,70,118,128,149],"tasks":[22],"like":[23,132],"conversational":[24],"telephone":[25],"(CTS)":[27],"recognition.":[28],"In":[29,141],"this":[30,71,173],"paper":[31],"we":[32],"evaluate":[33],"the":[34,60,143],"usefulness":[35],"of":[36,53,98],"these":[37,119,150],"proposed":[38],"techniques":[39,126,169],"broadcast":[41],"news":[42],"(BN),":[43],"a":[44,51,96],"similar":[45,139],"challenging":[46],"task.":[47,72],"We":[48],"also":[49],"perform":[50],"set":[52],"measurements":[55],"understand":[57],"how":[58],"achieved":[61],"results":[65],"are":[66],"On":[73],"two":[74],"publicly":[75],"available":[76],"BN":[77],"test":[78,120,151],"sets,":[79,121],"DEV04F":[80],"and":[81,89,100,108,158,170],"RT04,":[82],"our":[83,122],"system":[86],"using":[87],"LSTM":[88],"residual":[90],"network":[91,102],"based":[92],"acoustic":[93],"models":[94,104],"with":[95],"combination":[97],"n-gram":[99],"neural":[101],"language":[103],"performs":[105],"at":[106,156],"6.5%":[107],"5.9%":[109],"word":[110],"error":[111],"rate.":[112],"By":[113],"new":[115,168],"milestones":[117],"experiments":[123],"show":[124],"that":[125,162],"developed":[127],"other":[129],"related":[130],"tasks,":[131],"CTS,":[133],"can":[134],"be":[135],"transferred":[136],"achieve":[138],"performance.":[140],"contrast,":[142],"best":[144],"measured":[145],"sets":[152],"is":[153,164],"much":[154],"lower,":[155],"3.6%":[157],"2.8%":[159],"respectively,":[160],"indicating":[161],"there":[163],"still":[165],"room":[166],"for":[167],"improvements":[171],"space,":[174],"reach":[176],"levels.":[179]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":4}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}