{"id":"https://openalex.org/W3196435865","doi":"https://doi.org/10.21437/interspeech.2021-691","title":"Understanding Medical Conversations: Rich Transcription, Confidence Scores & Information Extraction","display_name":"Understanding Medical Conversations: Rich Transcription, Confidence Scores & Information Extraction","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3196435865","doi":"https://doi.org/10.21437/interspeech.2021-691","mag":"3196435865"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-691","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-691","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},"type":"article","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/A5010878109","display_name":"Hagen Soltau","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Hagen Soltau","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036732709","display_name":"Mingqiu Wang","orcid":"https://orcid.org/0000-0001-7164-0054"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mingqiu Wang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025419994","display_name":"Izhak Shafran","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Izhak Shafran","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5072051996","display_name":"Laurent El Shafey","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Laurent El Shafey","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5010878109"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6987,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.76310462,"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":"4418","last_page":"4422"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.979200005531311,"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/T10028","display_name":"Topic Modeling","score":0.979200005531311,"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/T13629","display_name":"Text Readability and Simplification","score":0.9620000123977661,"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":0.9490000009536743,"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":0.8238874077796936},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6984127759933472},{"id":"https://openalex.org/keywords/punctuation","display_name":"Punctuation","score":0.6094297170639038},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.6065995097160339},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5887143611907959},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5469563007354736},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5293216109275818},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4844379723072052},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.4774104356765747},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.46509850025177},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.45559927821159363},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4546748101711273},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.45046183466911316},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3765888810157776},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34382525086402893}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8238874077796936},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6984127759933472},{"id":"https://openalex.org/C540372491","wikidata":"https://www.wikidata.org/wiki/Q82622","display_name":"Punctuation","level":2,"score":0.6094297170639038},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.6065995097160339},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5887143611907959},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5469563007354736},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5293216109275818},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4844379723072052},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.4774104356765747},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.46509850025177},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.45559927821159363},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4546748101711273},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.45046183466911316},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3765888810157776},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34382525086402893},{"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},{"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},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2021-691","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-691","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2936002343","https://openalex.org/W2188883480","https://openalex.org/W1592364192","https://openalex.org/W656840002","https://openalex.org/W1605117403","https://openalex.org/W2381416480","https://openalex.org/W2380599343","https://openalex.org/W2160451571","https://openalex.org/W2495256954","https://openalex.org/W2259317772"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,55,131],"describe":[4,23,132],"novel":[5],"components":[6],"for":[7,33,151,154,157,160,164,171,182],"extracting":[8],"clinically":[9],"relevant":[10],"information":[11],"from":[12,120],"medical":[13],"conversations":[14],"which":[15,36],"will":[16],"be":[17],"available":[18],"as":[19],"Google":[20],"APIs.":[21],"We":[22],"a":[24,51,110,133],"transformer-based":[25,69],"Recurrent":[26],"Neural":[27],"Network":[28],"Transducer":[29],"(RNN-T)":[30],"model":[31,71,112,124,142],"tailored":[32],"long-form":[34],"audio,":[35],"can":[37],"produce":[38],"rich":[39],"transcriptions":[40],"including":[41],"speaker":[42,44],"segmentation,":[43],"role":[45],"labeling,":[46],"punctuation":[47],"and":[48,65,100,117,162],"capitalization.":[49,104],"On":[50],"representative":[52],"test":[53],"set,":[54],"compare":[56],"performance":[57,139],"of":[58,140,149],"RNN-T":[59,134],"models":[60,178],"with":[61,109,147],"different":[62],"encoders,":[63],"units":[64],"streaming":[66,70],"constraints.":[67],"Our":[68,105],"performs":[72,125],"at":[73,126],"about":[74,127],"20%":[75],"WER":[76],"on":[77,83,89,93,97,103,144],"the":[78,84,121,141,145],"ASR":[79],"task,":[80,86],"6%":[81],"WDER":[82],"diarization":[85],"43%":[87,95],"SER":[88,92,96,102],"periods,":[90],"52%":[91],"commas,":[94],"question":[98],"marks":[99],"30%":[101],"recognizer":[106],"is":[107,168],"paired":[108],"confidence":[111],"that":[113,176],"utilizes":[114],"both":[115],"acoustic":[116],"lexical":[118],"features":[119],"recognizer.":[122],"The":[123,138],"0.37":[128],"NCE.":[129],"Finally,":[130],"based":[135],"tagging":[136],"model.":[137],"depends":[143],"ontologies,":[146],"F-scores":[148],"0.90":[150],"medications,":[152],"0.76":[153,159],"symptoms,":[155],"0.75":[156],"conditions,":[158],"diagnosis,":[161],"0.61":[163],"treatments.":[165],"While":[166],"there":[167],"still":[169],"room":[170],"improvement,":[172],"our":[173],"results":[174],"suggest":[175],"these":[177],"are":[179],"sufficiently":[180],"accurate":[181],"practical":[183],"applications.":[184]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3}],"updated_date":"2026-03-04T09:10:02.777135","created_date":"2025-10-10T00:00:00"}