{"id":"https://openalex.org/W4296068430","doi":"https://doi.org/10.21437/interspeech.2022-219","title":"Multi-Channel Far-Field Speaker Verification with Large-Scale Ad-hoc Microphone Arrays","display_name":"Multi-Channel Far-Field Speaker Verification with Large-Scale Ad-hoc Microphone Arrays","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4296068430","doi":"https://doi.org/10.21437/interspeech.2022-219"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-219","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-219","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":"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/A5027514862","display_name":"Chengdong Liang","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chengdong Liang","raw_affiliation_strings":["School of Marine Science and Technology, Northwestern Polytechnical University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"School of Marine Science and Technology, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101436485","display_name":"Yijiang Chen","orcid":"https://orcid.org/0000-0001-5816-5535"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yijiang Chen","raw_affiliation_strings":["School of Marine Science and Technology, Northwestern Polytechnical University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"School of Marine Science and Technology, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087696297","display_name":"Jiadi Yao","orcid":"https://orcid.org/0000-0002-5490-2179"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiadi Yao","raw_affiliation_strings":["School of Marine Science and Technology, Northwestern Polytechnical University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"School of Marine Science and Technology, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100450091","display_name":"Xiao-Lei Zhang","orcid":"https://orcid.org/0000-0001-7694-193X"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao-Lei Zhang","raw_affiliation_strings":["School of Marine Science and Technology, Northwestern Polytechnical University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"School of Marine Science and Technology, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5027514862"],"corresponding_institution_ids":["https://openalex.org/I17145004"],"apc_list":null,"apc_paid":null,"fwci":0.6137,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.65466035,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3679","last_page":"3683"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9980000257492065,"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":0.9914000034332275,"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/computer-science","display_name":"Computer science","score":0.6646143198013306},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.5193834900856018},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5100113153457642},{"id":"https://openalex.org/keywords/near-and-far-field","display_name":"Near and far field","score":0.48026251792907715},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.4693976938724518},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.44076356291770935},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3222786784172058},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.2481922209262848},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.16078919172286987},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.15553313493728638},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.06520283222198486}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6646143198013306},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.5193834900856018},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5100113153457642},{"id":"https://openalex.org/C25227671","wikidata":"https://www.wikidata.org/wiki/Q13405516","display_name":"Near and far field","level":2,"score":0.48026251792907715},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.4693976938724518},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.44076356291770935},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3222786784172058},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.2481922209262848},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.16078919172286987},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.15553313493728638},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.06520283222198486},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-219","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-219","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1973787919","https://openalex.org/W1974387177","https://openalex.org/W1992879732","https://openalex.org/W2062470372","https://openalex.org/W2148613904","https://openalex.org/W2194775991","https://openalex.org/W2289394825","https://openalex.org/W2799831802","https://openalex.org/W2889411318","https://openalex.org/W2889519245","https://openalex.org/W2972992051","https://openalex.org/W3013020904","https://openalex.org/W3016912202","https://openalex.org/W3036598372","https://openalex.org/W3094893851","https://openalex.org/W3132229649","https://openalex.org/W3133848124","https://openalex.org/W3140371908","https://openalex.org/W3146087165","https://openalex.org/W3160071434","https://openalex.org/W3160207687","https://openalex.org/W3169722760","https://openalex.org/W3177479551","https://openalex.org/W3196393301","https://openalex.org/W4286795917","https://openalex.org/W4297733535","https://openalex.org/W4298857741","https://openalex.org/W4394666973"],"related_works":["https://openalex.org/W2357191878","https://openalex.org/W1997078944","https://openalex.org/W1968065688","https://openalex.org/W1552846815","https://openalex.org/W2142945567","https://openalex.org/W2030332364","https://openalex.org/W2005459225","https://openalex.org/W4289829835","https://openalex.org/W4220830676","https://openalex.org/W2140022733"],"abstract_inverted_index":{"Speaker":[0],"verification":[1],"based":[2],"on":[3],"ad-hoc":[4,30,55],"microphone":[5,31,56],"arrays":[6],"has":[7],"the":[8,12,38,42,50,54,59,63,92,98,111,115,118,124],"potential":[9],"of":[10,28,53,78],"reducing":[11],"error":[13],"significantly":[14],"in":[15,127],"adverse":[16],"acoustic":[17],"environments.However,":[18],"existing":[19],"approaches":[20],"extract":[21],"utterancelevel":[22],"speaker":[23],"embeddings":[24],"from":[25],"each":[26],"channel":[27],"an":[29],"array,":[32],"which":[33],"does":[34],"not":[35],"consider":[36],"fully":[37],"spatialtemporal":[39],"information":[40,65,102],"across":[41],"devices.In":[43],"this":[44],"paper,":[45],"we":[46],"propose":[47],"to":[48],"aggregate":[49],"multichannel":[51],"signals":[52],"array":[57],"at":[58,91],"frame-level":[60],"by":[61],"exploring":[62],"cross-channel":[64,85,101],"deeply":[66],"with":[67],"two":[68,104],"attention":[69,106],"mechanisms.The":[70],"first":[71],"one":[72,96],"is":[73,121],"a":[74,79,84],"self-attention":[75,86,125],"method.It":[76],"consists":[77],"cross-frame":[80,99],"selfattention":[81],"layer":[82,87],"and":[83,100],"successively,":[88],"both":[89],"working":[90],"frame":[93],"level.The":[94],"second":[95],"learns":[97],"via":[103],"graph":[105],"layers.Experimental":[107],"results":[108],"demonstrate":[109],"that":[110],"proposed":[112],"methods":[113],"reach":[114],"state-of-the-art":[116],"performance.Moreover,":[117],"graph-attention":[119],"method":[120,126],"better":[122],"than":[123],"most":[128],"cases.":[129]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
