{"id":"https://openalex.org/W2913507073","doi":"https://doi.org/10.1109/slt.2018.8639611","title":"Role Annotated Speech Recognition for Conversational Interactions","display_name":"Role Annotated Speech Recognition for Conversational Interactions","publication_year":2018,"publication_date":"2018-12-01","ids":{"openalex":"https://openalex.org/W2913507073","doi":"https://doi.org/10.1109/slt.2018.8639611","mag":"2913507073"},"language":"en","primary_location":{"id":"doi:10.1109/slt.2018.8639611","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2018.8639611","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Spoken Language Technology Workshop (SLT)","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/A5082528065","display_name":"Nikolaos Flemotomos","orcid":"https://orcid.org/0000-0001-5227-0246"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nikolaos Flemotomos","raw_affiliation_strings":["Department of Electrical Engineering, University of Southern California, Los Angeles, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053133208","display_name":"Zhuohao Chen","orcid":"https://orcid.org/0000-0002-0105-2852"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhuohao Chen","raw_affiliation_strings":["Department of Electrical Engineering, University of Southern California, Los Angeles, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021605006","display_name":"David C. Atkins","orcid":"https://orcid.org/0000-0002-5781-9880"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David C. Atkins","raw_affiliation_strings":["Department of Psychiatry and Behavioral Sciences, University of Washington, Seattle, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Psychiatry and Behavioral Sciences, University of Washington, Seattle, WA, USA","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010028928","display_name":"Shrikanth Narayanan","orcid":"https://orcid.org/0000-0002-1052-6204"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shrikanth Narayanan","raw_affiliation_strings":["Department of Electrical Engineering, University of Southern California, Los Angeles, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.169,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.63348266,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"4","issue":null,"first_page":"1036","last_page":"1043"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","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"}},"topics":[{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9994999766349792,"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":0.8060852289199829},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7663397789001465},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.6454458236694336},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6328065991401672},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.6277009844779968},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.6254523992538452},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5556374788284302},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.4733799993991852},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.46277058124542236},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4409506916999817},{"id":"https://openalex.org/keywords/homogeneous","display_name":"Homogeneous","score":0.4257768392562866},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3806103467941284},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.11973780393600464}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8060852289199829},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7663397789001465},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.6454458236694336},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6328065991401672},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.6277009844779968},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.6254523992538452},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5556374788284302},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.4733799993991852},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.46277058124542236},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4409506916999817},{"id":"https://openalex.org/C66882249","wikidata":"https://www.wikidata.org/wiki/Q169336","display_name":"Homogeneous","level":2,"score":0.4257768392562866},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3806103467941284},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11973780393600464},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"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":1,"locations":[{"id":"doi:10.1109/slt.2018.8639611","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2018.8639611","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Spoken Language Technology Workshop (SLT)","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":40,"referenced_works":["https://openalex.org/W97072897","https://openalex.org/W1524333225","https://openalex.org/W1589339348","https://openalex.org/W1608667326","https://openalex.org/W1631260214","https://openalex.org/W1975884129","https://openalex.org/W1989464534","https://openalex.org/W2002342963","https://openalex.org/W2026369565","https://openalex.org/W2046932483","https://openalex.org/W2062783322","https://openalex.org/W2079623482","https://openalex.org/W2091802891","https://openalex.org/W2094386595","https://openalex.org/W2144599546","https://openalex.org/W2154608152","https://openalex.org/W2158069733","https://openalex.org/W2164031777","https://openalex.org/W2172202672","https://openalex.org/W2341536223","https://openalex.org/W2395087347","https://openalex.org/W2402146185","https://openalex.org/W2403310668","https://openalex.org/W2405441567","https://openalex.org/W2408623794","https://openalex.org/W2746710273","https://openalex.org/W2791373548","https://openalex.org/W2888909528","https://openalex.org/W2895288567","https://openalex.org/W2963227667","https://openalex.org/W4245490569","https://openalex.org/W4300357431","https://openalex.org/W6603931906","https://openalex.org/W6631362777","https://openalex.org/W6635144179","https://openalex.org/W6636488977","https://openalex.org/W6681284347","https://openalex.org/W6712930963","https://openalex.org/W6713002670","https://openalex.org/W6713330251"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2149220986","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2023466863","https://openalex.org/W2099333848"],"abstract_inverted_index":{"Speaker":[0],"Role":[1,72],"Recognition":[2,50,75],"(SRR)":[3],"assigns":[4],"a":[5,15,26,71,80,84,105],"specific":[6],"speaker":[7,92,127],"role":[8],"to":[9,21,44,61,64,110,129,140],"each":[10],"speaker-homogeneous":[11],"speech":[12,63,81],"segment":[13],"in":[14,59,104],"conversation.":[16],"Typically,":[17],"those":[18],"segments":[19],"have":[20],"be":[22,45],"identified":[23],"first":[24],"through":[25],"diarization":[27],"step.":[28],"Additionally,":[29],"since":[30],"SRR":[31],"is":[32,53,113],"usually":[33],"based":[34],"on":[35],"the":[36,42,57,90,95,123],"different":[37,98],"linguistic":[38],"patterns":[39],"observed":[40],"between":[41],"roles":[43,128],"recognized,":[46],"an":[47,131],"Automatic":[48],"Speech":[49,74],"(ASR)":[51],"system":[52,77,121],"also":[54],"indispensable":[55],"for":[56,122,134],"task":[58],"hand":[60],"convert":[62],"text.":[65],"In":[66],"this":[67],"work":[68],"we":[69],"introduce":[70],"Annotated":[73],"(RASR)":[76],"which,":[78],"given":[79],"signal,":[82],"outputs":[83],"sequence":[85],"of":[86,97,125],"words":[87],"annotated":[88],"with":[89,138],"corresponding":[91],"roles.":[93],"Thus,":[94],"need":[96],"component":[99],"modules":[100],"which":[101],"are":[102],"connected":[103],"way":[106],"that":[107],"may":[108],"lead":[109],"error":[111],"propagation":[112],"eliminated.":[114],"We":[115],"present,":[116],"analyze,":[117],"and":[118],"test":[119],"our":[120],"case":[124],"two":[126],"show-case":[130],"end-to-end":[132],"approach":[133],"automatic":[135],"rich":[136],"transcription":[137],"application":[139],"clinical":[141],"dyadic":[142],"interactions.":[143]},"counts_by_year":[{"year":2019,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
