{"id":"https://openalex.org/W4294691186","doi":"https://doi.org/10.1109/aicas54282.2022.9870007","title":"An Attention-based Neural Network on Multiple Speaker Diarization","display_name":"An Attention-based Neural Network on Multiple Speaker Diarization","publication_year":2022,"publication_date":"2022-06-13","ids":{"openalex":"https://openalex.org/W4294691186","doi":"https://doi.org/10.1109/aicas54282.2022.9870007"},"language":"en","primary_location":{"id":"doi:10.1109/aicas54282.2022.9870007","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aicas54282.2022.9870007","pdf_url":null,"source":{"id":"https://openalex.org/S4363608281","display_name":"2022 IEEE 4th International Conference on Artificial Intelligence Circuits and Systems (AICAS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE 4th International Conference on Artificial Intelligence Circuits and Systems (AICAS)","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/A5110934406","display_name":"Shao Wen Cheng","orcid":null},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Shao Wen Cheng","raw_affiliation_strings":["National Yang Ming Chiao, Tung University,Hsinchu,Taiwan","National Yang Ming Chiao, Tung University, Hsinchu, Taiwan"],"affiliations":[{"raw_affiliation_string":"National Yang Ming Chiao, Tung University,Hsinchu,Taiwan","institution_ids":["https://openalex.org/I148366613"]},{"raw_affiliation_string":"National Yang Ming Chiao, Tung University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009773692","display_name":"Kai Jyun Hung","orcid":null},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Kai Jyun Hung","raw_affiliation_strings":["National Yang Ming Chiao, Tung University,Hsinchu,Taiwan","National Yang Ming Chiao, Tung University, Hsinchu, Taiwan"],"affiliations":[{"raw_affiliation_string":"National Yang Ming Chiao, Tung University,Hsinchu,Taiwan","institution_ids":["https://openalex.org/I148366613"]},{"raw_affiliation_string":"National Yang Ming Chiao, Tung University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034141299","display_name":"Hsie Chia Chang","orcid":null},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hsie Chia Chang","raw_affiliation_strings":["National Yang Ming Chiao, Tung University,Hsinchu,Taiwan","National Yang Ming Chiao, Tung University, Hsinchu, Taiwan"],"affiliations":[{"raw_affiliation_string":"National Yang Ming Chiao, Tung University,Hsinchu,Taiwan","institution_ids":["https://openalex.org/I148366613"]},{"raw_affiliation_string":"National Yang Ming Chiao, Tung University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068253119","display_name":"Yen Chin Liao","orcid":null},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yen Chin Liao","raw_affiliation_strings":["National Yang Ming Chiao, Tung University,Hsinchu,Taiwan","National Yang Ming Chiao, Tung University, Hsinchu, Taiwan"],"affiliations":[{"raw_affiliation_string":"National Yang Ming Chiao, Tung University,Hsinchu,Taiwan","institution_ids":["https://openalex.org/I148366613"]},{"raw_affiliation_string":"National Yang Ming Chiao, Tung University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I148366613"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5110934406"],"corresponding_institution_ids":["https://openalex.org/I148366613"],"apc_list":null,"apc_paid":null,"fwci":0.1041,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.28384421,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"431","last_page":"434"},"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":0.9998000264167786,"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":0.9997000098228455,"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/speaker-diarisation","display_name":"Speaker diarisation","score":0.9516476988792419},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8106093406677246},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7371825575828552},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.5579262375831604},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5467175841331482},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.5203251838684082},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.47048166394233704},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.42702871561050415},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4213300049304962},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4179949462413788},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41158750653266907}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.9516476988792419},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8106093406677246},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7371825575828552},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.5579262375831604},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5467175841331482},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.5203251838684082},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.47048166394233704},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.42702871561050415},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4213300049304962},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4179949462413788},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41158750653266907},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/aicas54282.2022.9870007","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aicas54282.2022.9870007","pdf_url":null,"source":{"id":"https://openalex.org/S4363608281","display_name":"2022 IEEE 4th International Conference on Artificial Intelligence Circuits and Systems (AICAS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE 4th International Conference on Artificial Intelligence Circuits and Systems (AICAS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6299999952316284}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2221409856","https://openalex.org/W2460742184","https://openalex.org/W2896457183","https://openalex.org/W2936774411","https://openalex.org/W2972949456","https://openalex.org/W3008357631","https://openalex.org/W3010196324","https://openalex.org/W3095212884","https://openalex.org/W4385245566","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6761305474","https://openalex.org/W6774558098"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2149220986","https://openalex.org/W1493012537","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1999004162","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2023466863","https://openalex.org/W2696990509"],"abstract_inverted_index":{"Speaker":[0],"diarization":[1,40,57,85,92,113],"is":[2],"a":[3,28,34,83],"task":[4],"to":[5,15,44,116,120,134],"label":[6],"audio":[7],"or":[8,36],"video":[9],"recordings":[10],"with":[11,64,154,160],"classes":[12],"that":[13,145],"correspond":[14],"speaker":[16,39,91,112],"identity":[17],"for":[18],"each":[19,128],"point":[20],"in":[21,27,151],"time,":[22],"which":[23],"can":[24,41],"be":[25,42],"used":[26,43],"multi-speaker":[29],"conversation":[30],"environment,":[31],"such":[32],"as":[33,114],"meeting":[35],"interview.":[37],"Moreover,":[38],"improve":[45],"the":[46,73,77,90,101,125,136,140,152],"performance":[47],"of":[48,79,127],"auto":[49,95],"speech":[50,96],"recognition.":[51],"This":[52],"paper":[53],"presents":[54],"an":[55,61,106],"end-to-end":[56],"model":[58,98,133,147],"based":[59],"on":[60,105,139,157],"attention":[62],"mechanism":[63],"data":[65,68,75],"augmentation,":[66],"several":[67],"pre-processing,":[69],"and":[70,94,99,163],"post-processing.":[71],"In":[72],"CALLHOME":[74],"set,":[76],"case":[78],"two":[80,155],"speakers":[81],"reached":[82],"9.12%":[84],"error":[86],"rate.":[87],"We":[88],"combine":[89],"model,":[93],"recognition":[97],"implement":[100],"transcript":[102,126,137],"conversion":[103,138],"system":[104],"edge":[107,141,158],"device.":[108,142],"By":[109],"using":[110],"proposed":[111],"preprocessing":[115],"segment":[117],"recording":[118],"according":[119],"different":[121],"speakers,":[122],"then":[123],"get":[124],"segmented":[129],"utterance":[130],"by":[131],"ASR":[132],"fulfill":[135],"Experiment":[143],"shows":[144],"our":[146],"also":[148],"performs":[149],"well":[150],"scenario":[153],"people":[156],"devices":[159],"both":[161],"accuracy":[162],"inference":[164],"time.":[165]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
