{"id":"https://openalex.org/W4297437764","doi":"https://doi.org/10.21437/interspeech.2022-11412","title":"Spatial-aware Speaker Diarizaiton for Multi-channel Multi-party Meeting","display_name":"Spatial-aware Speaker Diarizaiton for Multi-channel Multi-party Meeting","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4297437764","doi":"https://doi.org/10.21437/interspeech.2022-11412"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-11412","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-11412","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2209.12002","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100440161","display_name":"Jie Wang","orcid":"https://orcid.org/0000-0003-0820-5046"},"institutions":[{"id":"https://openalex.org/I75867142","display_name":"Xiamen University of Technology","ror":"https://ror.org/01285e189","country_code":"CN","type":"education","lineage":["https://openalex.org/I75867142"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Wang","raw_affiliation_strings":["School of Electronic Science and Engineering, Xiamen University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic Science and Engineering, Xiamen University, China","institution_ids":["https://openalex.org/I75867142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028886752","display_name":"Yuji Liu","orcid":"https://orcid.org/0000-0003-2558-5896"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuji Liu","raw_affiliation_strings":["Key Laboratory of Underwater Acoustic Communication and Marine Information Technology (Xiamen University), Minister of Education","College of Ocean and Earth Sciences, Xiamen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Underwater Acoustic Communication and Marine Information Technology (Xiamen University), Minister of Education","institution_ids":["https://openalex.org/I191208505"]},{"raw_affiliation_string":"College of Ocean and Earth Sciences, Xiamen University","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047311847","display_name":"Binling Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Binling Wang","raw_affiliation_strings":["School of Informatics, Xiamen University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics, Xiamen University, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032683415","display_name":"Yiming Zhi","orcid":null},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiming Zhi","raw_affiliation_strings":["School of Informatics, Xiamen University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics, Xiamen University, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000969367","display_name":"Song Li","orcid":null},"institutions":[{"id":"https://openalex.org/I75867142","display_name":"Xiamen University of Technology","ror":"https://ror.org/01285e189","country_code":"CN","type":"education","lineage":["https://openalex.org/I75867142"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Song Li","raw_affiliation_strings":["School of Electronic Science and Engineering, Xiamen University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic Science and Engineering, Xiamen University, China","institution_ids":["https://openalex.org/I75867142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054936283","display_name":"Shipeng Xia","orcid":null},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shipeng Xia","raw_affiliation_strings":["School of Informatics, Xiamen University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics, Xiamen University, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101803788","display_name":"Jiayang Zhang","orcid":"https://orcid.org/0000-0003-3865-9735"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiayang Zhang","raw_affiliation_strings":["College of Ocean and Earth Sciences, Xiamen University","Key Laboratory of Underwater Acoustic Communication and Marine Information Technology (Xiamen University), Minister of Education"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Ocean and Earth Sciences, Xiamen University","institution_ids":["https://openalex.org/I191208505"]},{"raw_affiliation_string":"Key Laboratory of Underwater Acoustic Communication and Marine Information Technology (Xiamen University), Minister of Education","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Feng Tong","orcid":null},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Tong","raw_affiliation_strings":["College of Ocean and Earth Sciences, Xiamen University","Key Laboratory of Underwater Acoustic Communication and Marine Information Technology (Xiamen University), Minister of Education"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Ocean and Earth Sciences, Xiamen University","institution_ids":["https://openalex.org/I191208505"]},{"raw_affiliation_string":"Key Laboratory of Underwater Acoustic Communication and Marine Information Technology (Xiamen University), Minister of Education","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041012768","display_name":"Lin Li","orcid":null},"institutions":[{"id":"https://openalex.org/I75867142","display_name":"Xiamen University of Technology","ror":"https://ror.org/01285e189","country_code":"CN","type":"education","lineage":["https://openalex.org/I75867142"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Li","raw_affiliation_strings":["School of Electronic Science and Engineering, Xiamen University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic Science and Engineering, Xiamen University, China","institution_ids":["https://openalex.org/I75867142"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011997254","display_name":"Qingyang Hong","orcid":"https://orcid.org/0000-0001-7380-8690"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qingyang Hong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1491","last_page":"1495"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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/T11309","display_name":"Music and Audio Processing","score":0.9991999864578247,"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":0.8265607953071594},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7892007231712341},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6138260364532471},{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.6111551523208618},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5966938734054565},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.5385748744010925},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.5062486529350281},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4744590222835541},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4598056375980377},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4043762683868408},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3885151743888855},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.3490883708000183},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.330892950296402},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.18362650275230408}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.8265607953071594},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7892007231712341},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6138260364532471},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.6111551523208618},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5966938734054565},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.5385748744010925},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.5062486529350281},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4744590222835541},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4598056375980377},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4043762683868408},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3885151743888855},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.3490883708000183},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.330892950296402},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.18362650275230408},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2022-11412","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-11412","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2209.12002","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2209.12002","pdf_url":"https://arxiv.org/pdf/2209.12002","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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2209.12002","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2209.12002","pdf_url":"https://arxiv.org/pdf/2209.12002","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":[{"display_name":"Reduced inequalities","score":0.7300000190734863,"id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G2299475589","display_name":null,"funder_award_id":"62001405","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3698338998","display_name":null,"funder_award_id":"61876160","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2097583714","https://openalex.org/W2148613904","https://openalex.org/W2402428045","https://openalex.org/W2750259098","https://openalex.org/W2900212944","https://openalex.org/W2962696180","https://openalex.org/W2964052309","https://openalex.org/W2972552635","https://openalex.org/W3015598461","https://openalex.org/W3015621653","https://openalex.org/W3015783745","https://openalex.org/W3094831814","https://openalex.org/W3097777922","https://openalex.org/W3103152812","https://openalex.org/W3105031100","https://openalex.org/W3197087498","https://openalex.org/W3197801171","https://openalex.org/W4285618512","https://openalex.org/W4292329485","https://openalex.org/W4309845474"],"related_works":["https://openalex.org/W2896203542","https://openalex.org/W876328409","https://openalex.org/W4319068615","https://openalex.org/W4214946933","https://openalex.org/W2206035908","https://openalex.org/W1879255185","https://openalex.org/W2148473678","https://openalex.org/W1977167953","https://openalex.org/W4247736853","https://openalex.org/W3004719695"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"a":[3,47,75],"spatial-aware":[4],"speaker":[5,20],"diarization":[6,14,121,127],"system":[7,15,128],"for":[8],"the":[9,40,81,120],"multi-channel":[10,49,102],"multi-party":[11],"meeting.":[12],"The":[13,71],"obtains":[16],"direction":[17],"information":[18],"of":[19,62,85,125],"by":[21,29,88],"microphone":[22],"array.":[23],"Speaker":[24],"spatial":[25,83],"embedding":[26,41],"is":[27,74],"generated":[28],"xvector":[30],"and":[31,68,104],"s-vector":[32],"derived":[33],"from":[34,131],"superdirective":[35,64],"beamforming":[36,65],"(SDB)":[37],"which":[38,60],"makes":[39],"more":[42],"robust.":[43],"Specifically,":[44],"we":[45],"propose":[46],"novel":[48],"sequence-to-sequence":[50],"neural":[51,57],"network":[52,58],"architecture":[53],"named":[54],"discriminative":[55],"multi-stream":[56],"(DMSNet)":[59],"consists":[61],"attention":[63],"(ASDB)":[66],"block":[67,78],"Conformer":[69],"encoder.":[70],"proposed":[72],"ASDB":[73],"self-adapted":[76],"channel-wise":[77],"that":[79],"extracts":[80],"latent":[82],"features":[84],"array":[86],"audios":[87],"modeling":[89],"interdependencies":[90],"between":[91],"channels.":[92],"We":[93],"explore":[94],"DMSNet":[95,113],"to":[96,133],"address":[97],"overlapped":[98,115],"speech":[99,116],"problem":[100],"on":[101,108],"audio":[103],"achieve":[105],"93.53%":[106],"accuracy":[107],"evaluation":[109],"set.":[110],"By":[111],"performing":[112],"based":[114],"detection":[117],"(OSD)":[118],"module,":[119],"error":[122],"rate":[123],"(DER)":[124],"cluster-based":[126],"decrease":[129],"significantly":[130],"13.45%":[132],"7.64%.":[134]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2022-09-28T00:00:00"}
