{"id":"https://openalex.org/W3205878676","doi":"https://doi.org/10.1109/icassp43922.2022.9746806","title":"TitaNet: Neural Model for Speaker Representation with 1D Depth-Wise Separable Convolutions and Global Context","display_name":"TitaNet: Neural Model for Speaker Representation with 1D Depth-Wise Separable Convolutions and Global Context","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W3205878676","doi":"https://doi.org/10.1109/icassp43922.2022.9746806","mag":"3205878676"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746806","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746806","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5040007143","display_name":"Nithin Rao Koluguri","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Nithin Rao Koluguri","raw_affiliation_strings":["NVIDIA,USA","NVIDIA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA,USA","institution_ids":["https://openalex.org/I4210127875"]},{"raw_affiliation_string":"NVIDIA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101511624","display_name":"Taejin Park","orcid":"https://orcid.org/0000-0003-2040-5884"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Taejin Park","raw_affiliation_strings":["NVIDIA,USA","NVIDIA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA,USA","institution_ids":["https://openalex.org/I4210127875"]},{"raw_affiliation_string":"NVIDIA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032957280","display_name":"Boris Ginsburg","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Boris Ginsburg","raw_affiliation_strings":["NVIDIA,USA","NVIDIA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA,USA","institution_ids":["https://openalex.org/I4210127875"]},{"raw_affiliation_string":"NVIDIA, USA","institution_ids":["https://openalex.org/I4210127875"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5040007143"],"corresponding_institution_ids":["https://openalex.org/I4210127875"],"apc_list":null,"apc_paid":null,"fwci":10.8136,"has_fulltext":false,"cited_by_count":113,"citation_normalized_percentile":{"value":0.98971913,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"8102","last_page":"8106"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9990000128746033,"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":0.9984999895095825,"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":0.7398830056190491},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.7034217715263367},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.632720410823822},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6218051314353943},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.605475127696991},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6040180325508118},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5619316697120667},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.5594282746315002},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.461546927690506},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.45577242970466614},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4454607367515564},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.41509494185447693},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.378583163022995},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3652351498603821},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.3391384184360504},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2838686406612396},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10424572229385376}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7398830056190491},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.7034217715263367},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.632720410823822},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6218051314353943},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.605475127696991},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6040180325508118},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5619316697120667},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.5594282746315002},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.461546927690506},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.45577242970466614},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4454607367515564},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.41509494185447693},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.378583163022995},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3652351498603821},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.3391384184360504},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2838686406612396},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10424572229385376},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746806","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746806","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6499999761581421,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2046056978","https://openalex.org/W2125336414","https://openalex.org/W2396765756","https://openalex.org/W2406312423","https://openalex.org/W2696967604","https://openalex.org/W2802488037","https://openalex.org/W2808631503","https://openalex.org/W2889016587","https://openalex.org/W2889418727","https://openalex.org/W2890964092","https://openalex.org/W2936774411","https://openalex.org/W2940070181","https://openalex.org/W2969985801","https://openalex.org/W2972961496","https://openalex.org/W2974231335","https://openalex.org/W2981461916","https://openalex.org/W3015537910","https://openalex.org/W3015783745","https://openalex.org/W3015985683","https://openalex.org/W3021469861","https://openalex.org/W3024869864","https://openalex.org/W3095173472","https://openalex.org/W3096918678","https://openalex.org/W3097777922","https://openalex.org/W3105031100","https://openalex.org/W3134299941","https://openalex.org/W3143367551","https://openalex.org/W3178462146","https://openalex.org/W4288091954","https://openalex.org/W6678809451","https://openalex.org/W6711908931","https://openalex.org/W6713727690","https://openalex.org/W6767671539","https://openalex.org/W6769178842","https://openalex.org/W6785552926"],"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":{"In":[0],"this":[1],"paper,":[2],"we":[3,94],"propose":[4],"TitaNet,":[5],"a":[6,41,47,102],"novel":[7],"neural":[8],"network":[9],"architecture":[10,49],"for":[11],"extracting":[12],"speaker":[13,55,74],"representations.":[14],"We":[15],"employ":[16],"1D":[17],"depth-wise":[18],"separable":[19],"convolutions":[20],"with":[21,25,58,77,106],"Squeeze-and-Excitation":[22],"(SE)":[23],"layers":[24],"global":[26],"context":[27],"followed":[28],"by":[29],"channel":[30],"attention":[31],"based":[32],"statistics":[33],"pooling":[34],"layer":[35],"to":[36,40],"map":[37],"variable-length":[38],"utterances":[39],"fixed-length":[42],"embedding":[43],"(t-vector).":[44],"TitaNet":[45,99],"is":[46],"scalable":[48],"and":[50,71,89,100],"achieves":[51],"state-of-the-art":[52,113],"performance":[53],"on":[54,66,73,84,87,91],"verification":[56],"task":[57],"an":[59],"equal":[60],"error":[61,79],"rate":[62,80],"(EER)":[63],"of":[64,82,98],"0.68%":[65],"the":[67],"VoxCeleb1":[68],"trial":[69],"file":[70],"also":[72],"diarization":[75,78,116],"tasks":[76],"(DER)":[81],"1.73%":[83],"AMI-MixHeadset,":[85],"1.99%":[86],"AMI-Lapel":[88],"1.11%":[90],"CH109.":[92],"Furthermore,":[93],"investigate":[95],"various":[96],"sizes":[97],"present":[101],"light":[103],"TitaNet-S":[104],"model":[105],"only":[107],"6M":[108],"parameters":[109],"that":[110],"achieve":[111],"near":[112],"results":[114],"in":[115],"tasks.":[117]},"counts_by_year":[{"year":2026,"cited_by_count":9},{"year":2025,"cited_by_count":45},{"year":2024,"cited_by_count":26},{"year":2023,"cited_by_count":31},{"year":2022,"cited_by_count":2}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}