{"id":"https://openalex.org/W2726225402","doi":"https://doi.org/10.21437/interspeech.2017-1544","title":"Comparing Human and Machine Errors in Conversational Speech Transcription","display_name":"Comparing Human and Machine Errors in Conversational Speech Transcription","publication_year":2017,"publication_date":"2017-08-16","ids":{"openalex":"https://openalex.org/W2726225402","doi":"https://doi.org/10.21437/interspeech.2017-1544","mag":"2726225402"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2017-1544","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-1544","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/1708.08615","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5060979948","display_name":"Andreas Stolcke","orcid":"https://orcid.org/0000-0002-9925-905X"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Andreas Stolcke","raw_affiliation_strings":["Microsoft (United States), Redmond, United States"],"affiliations":[{"raw_affiliation_string":"Microsoft (United States), Redmond, United States","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012153296","display_name":"Jasha Droppo","orcid":"https://orcid.org/0000-0001-6097-0090"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jasha Droppo","raw_affiliation_strings":["Microsoft (United States), Redmond, United States"],"affiliations":[{"raw_affiliation_string":"Microsoft (United States), Redmond, United States","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5060979948"],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":null,"apc_paid":null,"fwci":1.4539,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.86625567,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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":0.9987999796867371,"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/T12031","display_name":"Speech and dialogue systems","score":0.9972000122070312,"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":0.7478525042533875},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7006840109825134},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.6200178861618042},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.580646276473999},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.5684438943862915},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5373453497886658},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4757799208164215},{"id":"https://openalex.org/keywords/turing-test","display_name":"Turing test","score":0.4684097170829773},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4257197082042694},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36473116278648376},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09411868453025818},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0650673508644104}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7478525042533875},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7006840109825134},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.6200178861618042},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.580646276473999},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.5684438943862915},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5373453497886658},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4757799208164215},{"id":"https://openalex.org/C577917","wikidata":"https://www.wikidata.org/wiki/Q189223","display_name":"Turing test","level":2,"score":0.4684097170829773},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4257197082042694},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36473116278648376},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09411868453025818},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0650673508644104},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2017-1544","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-1544","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:1708.08615","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1708.08615","pdf_url":"https://arxiv.org/pdf/1708.08615","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:2726225402","is_oa":true,"landing_page_url":"http://arxiv.org/pdf/1708.08615.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.1708.08615","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1708.08615","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-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1708.08615","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1708.08615","pdf_url":"https://arxiv.org/pdf/1708.08615","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":0.6200000047683716,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W196692374","https://openalex.org/W1741269295","https://openalex.org/W1872348600","https://openalex.org/W1999965501","https://openalex.org/W2097560587","https://openalex.org/W2098318492","https://openalex.org/W2099424804","https://openalex.org/W2115407392","https://openalex.org/W2163680580","https://openalex.org/W2198724430","https://openalex.org/W2293634267","https://openalex.org/W2394932179","https://openalex.org/W2397947827","https://openalex.org/W2507436421","https://openalex.org/W2515753980","https://openalex.org/W2533523411","https://openalex.org/W2604132379","https://openalex.org/W2916986993","https://openalex.org/W2963920996"],"related_works":["https://openalex.org/W2963980299","https://openalex.org/W2737982026","https://openalex.org/W2599727673","https://openalex.org/W3199323122","https://openalex.org/W86526702","https://openalex.org/W2024633751","https://openalex.org/W2796069293","https://openalex.org/W1843577977","https://openalex.org/W2250243221","https://openalex.org/W1493946344","https://openalex.org/W2186793356","https://openalex.org/W1751699554","https://openalex.org/W2904673831","https://openalex.org/W1556750318","https://openalex.org/W2336426217","https://openalex.org/W2067208615","https://openalex.org/W2741920812","https://openalex.org/W3195128650","https://openalex.org/W2048105631","https://openalex.org/W114943906"],"abstract_inverted_index":{"Recent":[0],"work":[1],"in":[2],"automatic":[3,112,183],"recognition":[4,73],"of":[5,68,77,96,103,162],"conversational":[6],"telephone":[7],"speech":[8,80],"(CTS)":[9],"has":[10],"achieved":[11],"accuracy":[12],"levels":[13],"comparable":[14],"to":[15,24,75,115,127,133,141,180],"human":[16,27,52,150,185],"transcribers,":[17],"although":[18],"there":[19],"is":[20,109],"some":[21],"debate":[22],"how":[23],"precisely":[25],"quantify":[26,146],"performance":[28],"on":[29,173],"this":[30,58,62,129],"task,":[31],"using":[32],"the":[33,41,66,87,111,134,147,155,160],"NIST":[34],"2000":[35],"CTS":[36,72],"evaluation":[37],"set.":[38],"This":[39],"raises":[40],"question":[42,63],"what":[43],"systematic":[44],"differences,":[45],"if":[46],"any,":[47],"may":[48],"be":[49],"found":[50],"differentiating":[51],"from":[53],"machine":[54,152],"transcription":[55,81,186],"errors.":[56],"In":[57],"paper":[59],"we":[60,145,171],"approach":[61],"by":[64],"comparing":[65],"output":[67],"our":[69],"most":[70,88],"accurate":[71],"system":[74],"that":[76,86,110],"a":[78,100],"standard":[79],"vendor":[82],"pipeline.":[83],"We":[84],"find":[85],"frequent":[89],"substitution,":[90],"deletion":[91],"and":[92,120,136,151,158,167,184],"insertion":[93],"error":[94,187],"types":[95],"both":[97],"outputs":[98],"show":[99],"high":[101],"degree":[102],"overlap.":[104],"The":[105],"only":[106],"notable":[107],"exception":[108],"recognizer":[113],"tends":[114],"confuse":[116],"filled":[117],"pauses":[118],"(\"uh\")":[119],"backchannel":[121],"acknowledgments":[122],"(\"uhhuh\").":[123],"Humans":[124],"tend":[125],"not":[126],"make":[128],"error,":[130],"presumably":[131],"due":[132],"distinctive":[135],"opposing":[137],"pragmatic":[138],"functions":[139],"attached":[140],"these":[142],"words.":[143],"Furthermore,":[144],"correlation":[148],"between":[149,165,182],"errors":[153],"at":[154],"speaker":[156,163],"level,":[157],"investigate":[159],"effect":[161],"overlap":[164],"training":[166],"test":[168],"data.":[169],"Finally,":[170],"report":[172],"an":[174],"informal":[175],"\"Turing":[176],"test\"":[177],"asking":[178],"humans":[179],"discriminate":[181],"cases.":[188]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}