{"id":"https://openalex.org/W3025384377","doi":"https://doi.org/10.21437/odyssey.2020-10","title":"Neural i-vectors","display_name":"Neural i-vectors","publication_year":2020,"publication_date":"2020-05-15","ids":{"openalex":"https://openalex.org/W3025384377","doi":"https://doi.org/10.21437/odyssey.2020-10","mag":"3025384377"},"language":"en","primary_location":{"id":"doi:10.21437/odyssey.2020-10","is_oa":false,"landing_page_url":"https://doi.org/10.21437/odyssey.2020-10","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Speaker and Language Recognition Workshop (Odyssey 2020)","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/A5031094144","display_name":"Ville Vestman","orcid":"https://orcid.org/0000-0002-7281-0278"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Ville Vestman","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004287909","display_name":"Kong Aik Lee","orcid":"https://orcid.org/0000-0001-9133-3000"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kong Aik Lee","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5043168931","display_name":"Tomi Kinnunen","orcid":"https://orcid.org/0000-0002-4371-7322"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tomi Kinnunen","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5031094144"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7954,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.77856921,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"67","last_page":"74"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9943000078201294,"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":0.9803000092506409,"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":0.5577185153961182},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37149864435195923}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5577185153961182},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37149864435195923}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/odyssey.2020-10","is_oa":false,"landing_page_url":"https://doi.org/10.21437/odyssey.2020-10","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Speaker and Language Recognition Workshop (Odyssey 2020)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7799999713897705,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2093578348","https://openalex.org/W2376932109","https://openalex.org/W2382290278","https://openalex.org/W2766271392","https://openalex.org/W2350741829","https://openalex.org/W3107474891"],"abstract_inverted_index":{"Deep":[0],"speaker":[1,14],"embeddings":[2,100,131],"have":[3],"been":[4],"demonstrated":[5],"to":[6,61,76,89,101,135],"outperform":[7,155],"their":[8],"generative":[9,25],"counterparts,":[10],"i-vectors,":[11],"in":[12,38,109,161],"recent":[13],"verification":[15],"evaluations.":[16],"To":[17,40],"combine":[18],"the":[19,29,42,56,62,72,86,98,102,107,110,114,124,136,147,152,156,162],"benefits":[20],"of":[21,31,68,82,127],"high":[22],"performance":[23,133,145],"and":[24,35,113,120],"interpretation,":[26],"we":[27,50,92],"investigate":[28],"use":[30],"deep":[32,43,99,130,148],"embedding":[33,44,63],"extractor":[34,37,45,64,88],"i-vector":[36,48,87,158],"succession.":[39],"bundle":[41],"with":[46],"an":[47],"extractor,":[49],"adopt":[51],"aggregation":[52],"layers":[53],"inspired":[54],"by":[55,164],"Gaussian":[57],"mixture":[58],"model":[59],"(GMM)":[60],"networks.":[65],"The":[66,138],"inclusion":[67],"GMM-like":[69],"layer":[70],"allows":[71],"discriminatively":[73],"trained":[74],"network":[75],"be":[77],"used":[78],"as":[79],"a":[80,165],"provider":[81],"sufficient":[83],"statistics":[84],"for":[85],"extract":[90],"what":[91],"call":[93],"neural":[94,104,139],"i-vectors.":[95],"We":[96],"compare":[97],"proposed":[103],"i-vectors":[105,140],"on":[106,151],"Speakers":[108],"Wild":[111],"(SITW)":[112],"Speaker":[115],"Recognition":[116],"Evaluation":[117],"(SRE)":[118],"2018":[119],"2019":[121],"datasets.":[122],"On":[123],"core-core":[125],"condition":[126],"SITW,":[128],"our":[129],"obtain":[132,141],"comparative":[134],"state-of-the-art.":[137],"about":[142],"50%":[143],"worse":[144],"than":[146],"embeddings,":[149],"but":[150],"other":[153],"hand":[154],"previous":[157],"approaches":[159],"reported":[160],"literature":[163],"clear":[166],"margin.":[167]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2020-05-21T00:00:00"}