{"id":"https://openalex.org/W2973135063","doi":"https://doi.org/10.21437/interspeech.2019-1343","title":"Exploring Methods for the Automatic Detection of Errors in Manual Transcription","display_name":"Exploring Methods for the Automatic Detection of Errors in Manual Transcription","publication_year":2019,"publication_date":"2019-09-13","ids":{"openalex":"https://openalex.org/W2973135063","doi":"https://doi.org/10.21437/interspeech.2019-1343","mag":"2973135063"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2019-1343","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-1343","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":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100363489","display_name":"Xiaofei Wang","orcid":"https://orcid.org/0009-0004-6683-3969"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xiaofei Wang","raw_affiliation_strings":["Center for Language and Speech Processing, The Johns Hopkins University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, The Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025903049","display_name":"Jinyi Yang","orcid":"https://orcid.org/0000-0001-5287-4242"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jinyi Yang","raw_affiliation_strings":["Center for Language and Speech Processing, The Johns Hopkins University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, The Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100760516","display_name":"Ruizhi Li","orcid":"https://orcid.org/0000-0002-2496-5224"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ruizhi Li","raw_affiliation_strings":["Center for Language and Speech Processing, The Johns Hopkins University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, The Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021725828","display_name":"Samik Sadhu","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Samik Sadhu","raw_affiliation_strings":["Center for Language and Speech Processing, The Johns Hopkins University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, The Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042260050","display_name":"Hynek He\u0159mansk\u00fd","orcid":"https://orcid.org/0000-0001-8032-4811"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hynek Hermansky","raw_affiliation_strings":["Center for Language and Speech Processing, The Johns Hopkins University, USA","Human Language Technology Center of Excellence, The Johns Hopkins University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, The Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Human Language Technology Center of Excellence, The Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5100363489"],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":0.1093,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.40290381,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":93},"biblio":{"volume":null,"issue":null,"first_page":"3003","last_page":"3007"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9998000264167786,"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":0.9983999729156494,"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":0.8379451632499695},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.7876161336898804},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6697431206703186},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6484271883964539},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4905552268028259},{"id":"https://openalex.org/keywords/phonetic-transcription","display_name":"Phonetic transcription","score":0.4713156819343567},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.47064799070358276},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.45234692096710205},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.41978731751441956},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.32364708185195923},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07175350189208984}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8379451632499695},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.7876161336898804},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6697431206703186},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6484271883964539},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4905552268028259},{"id":"https://openalex.org/C2777853878","wikidata":"https://www.wikidata.org/wiki/Q743569","display_name":"Phonetic transcription","level":2,"score":0.4713156819343567},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.47064799070358276},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.45234692096710205},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.41978731751441956},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.32364708185195923},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07175350189208984},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2019-1343","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-1343","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"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5099999904632568,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G5206847443","display_name":"RI: Medium: Collaborative Research: Variance and Invariance in Voice Quality: Implications for Machine and Human Speaker Identification","funder_award_id":"1704170","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W85707815","https://openalex.org/W1486694252","https://openalex.org/W1524333225","https://openalex.org/W1984541135","https://openalex.org/W2126315862","https://openalex.org/W2143562645","https://openalex.org/W2510616059","https://openalex.org/W2767017426","https://openalex.org/W2889508099","https://openalex.org/W2900092534","https://openalex.org/W4233200656"],"related_works":["https://openalex.org/W2121652828","https://openalex.org/W2126322296","https://openalex.org/W2163537793","https://openalex.org/W4386794561","https://openalex.org/W2916997151","https://openalex.org/W2781555308","https://openalex.org/W2785584785","https://openalex.org/W3021690593","https://openalex.org/W2020079054","https://openalex.org/W2992378684"],"abstract_inverted_index":{"Quality":[0],"of":[1,16,43,53,67,112],"data":[2],"plays":[3],"an":[4],"important":[5],"role":[6],"in":[7,30,71,77],"most":[8],"deep":[9],"learning":[10],"tasks.In":[11],"the":[12,21,41,47,51,72,109],"speech":[13,17,56],"community,":[14],"transcription":[15,22],"recording":[18],"is":[19,23],"indispensable.Since":[20],"usually":[24],"generated":[25],"artificially,":[26],"automatically":[27],"finding":[28],"errors":[29,128],"manual":[31],"transcriptions":[32,73],"not":[33],"only":[34],"saves":[35],"time":[36],"and":[37,62,129],"labors":[38],"but":[39],"benefits":[40],"performance":[42],"tasks":[44],"that":[45],"need":[46],"training":[48],"process.Inspired":[49],"by":[50],"success":[52],"hybrid":[54],"automatic":[55,68],"recognition":[57],"using":[58,81],"both":[59],"language":[60,84,92],"model":[61,85,104],"acoustic":[63,103],"model,":[64,93],"two":[65],"approaches":[66],"error":[69],"detection":[70],"have":[74,115],"been":[75,95,116],"explored":[76],"this":[78,97],"work.Previous":[79],"study":[80],"a":[82,89,101,119],"biased":[83],"approach,":[86,106],"relying":[87],"on":[88,108,118],"strong":[90],"transcription-dependent":[91],"has":[94],"reviewed.In":[96],"work,":[98],"we":[99],"propose":[100],"novel":[102],"based":[105],"focusing":[107],"phonetic":[110],"sequence":[111],"speech.Both":[113],"methods":[114],"evaluated":[117],"completely":[120],"real":[121],"dataset,":[122],"which":[123],"was":[124],"originally":[125],"transcribed":[126],"with":[127],"strictly":[130],"corrected":[131],"manually":[132],"afterwards.":[133]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}