{"id":"https://openalex.org/W2889060826","doi":"https://doi.org/10.21437/interspeech.2018-1685","title":"Robust and Discriminative Speaker Embedding via Intra-Class Distance Variance Regularization","display_name":"Robust and Discriminative Speaker Embedding via Intra-Class Distance Variance Regularization","publication_year":2018,"publication_date":"2018-08-28","ids":{"openalex":"https://openalex.org/W2889060826","doi":"https://doi.org/10.21437/interspeech.2018-1685","mag":"2889060826"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2018-1685","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1685","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://infoscience.epfl.ch/record/256296","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100768608","display_name":"Nam Le","orcid":"https://orcid.org/0000-0002-0616-0158"},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]},{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Nam Le","raw_affiliation_strings":["\u00c9cole Polytechnique F\u00e9d\u00e9ral de Lausanne, Switzerland","Idiap Research Institute, Martigny, Switzerland"],"affiliations":[{"raw_affiliation_string":"\u00c9cole Polytechnique F\u00e9d\u00e9ral de Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]},{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053358969","display_name":"Jean\u2010Marc Odobez","orcid":"https://orcid.org/0000-0002-9537-9898"},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]},{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Jean-Marc Odobez","raw_affiliation_strings":["Idiap Research Institute, Martigny, Switzerland","\u00c9cole Polytechnique F\u00e9d\u00e9ral de Lausanne, Switzerland"],"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]},{"raw_affiliation_string":"\u00c9cole Polytechnique F\u00e9d\u00e9ral de Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5053358969"],"corresponding_institution_ids":["https://openalex.org/I5124864","https://openalex.org/I7495430"],"apc_list":null,"apc_paid":null,"fwci":2.4433,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.91506228,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2257","last_page":"2261"},"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":0.9994999766349792,"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":0.9979000091552734,"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/discriminative-model","display_name":"Discriminative model","score":0.810569703578949},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.8017172813415527},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.732230007648468},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.6805104613304138},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5631982684135437},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5034891963005066},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5006604194641113},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4940100312232971},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.45131799578666687},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4366767108440399},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.42329972982406616},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.4228164851665497}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.810569703578949},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.8017172813415527},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.732230007648468},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.6805104613304138},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5631982684135437},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5034891963005066},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5006604194641113},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4940100312232971},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45131799578666687},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4366767108440399},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.42329972982406616},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.4228164851665497},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2018-1685","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1685","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"},{"id":"pmh:oai:infoscience.epfl.ch:256296","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/256296","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://infoscience.epfl.ch/record/256296","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:infoscience.epfl.ch:256296","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/256296","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://infoscience.epfl.ch/record/256296","raw_type":"Text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.8100000023841858}],"awards":[],"funders":[{"id":"https://openalex.org/F4320332999","display_name":"Horizon 2020 Framework Programme","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1996950552","https://openalex.org/W2039057510","https://openalex.org/W2046056978","https://openalex.org/W2106053110","https://openalex.org/W2121812409","https://openalex.org/W2130556178","https://openalex.org/W2150769028","https://openalex.org/W2194775991","https://openalex.org/W2292259253","https://openalex.org/W2520774990","https://openalex.org/W2587150483","https://openalex.org/W2596677785","https://openalex.org/W2612434969","https://openalex.org/W2638067502","https://openalex.org/W2726515241","https://openalex.org/W2747238065","https://openalex.org/W2748488820","https://openalex.org/W2770454110","https://openalex.org/W2890964092","https://openalex.org/W2963350250","https://openalex.org/W2963702081","https://openalex.org/W3099206234","https://openalex.org/W4234330420"],"related_works":["https://openalex.org/W4238897586","https://openalex.org/W435179959","https://openalex.org/W2619091065","https://openalex.org/W2059640416","https://openalex.org/W3208297503","https://openalex.org/W2889153461","https://openalex.org/W3119773509","https://openalex.org/W2964117661","https://openalex.org/W4388405611","https://openalex.org/W2619127353"],"abstract_inverted_index":{"Learning":[0],"a":[1,22,45,98,112],"good":[2],"speaker":[3,32,126],"embedding":[4,71,94],"is":[5,42,61,80,108],"critical":[6],"for":[7,125],"many":[8],"speech":[9],"processing":[10],"tasks,":[11],"including":[12],"recognition,":[13],"verification,":[14,127],"and":[15,101,104,129,145],"diarization.":[16],"To":[17],"this":[18],"end,":[19],"we":[20,86],"propose":[21],"complementary":[23],"optimizing":[24],"goal":[25,60],"called":[26],"intra-class":[27,76,78,135],"loss":[28,40,79,136],"to":[29,62,73],"improve":[30],"deep":[31,93,142],"embed":[33],"dings":[34],"learned":[35],"with":[36,83,111],"triplet":[37,84],"loss.":[38],"This":[39],"function":[41],"formulated":[43],"as":[44],"soft":[46],"constraint":[47],"on":[48,119],"the":[49,56,64,70,75,92,105,139,148,152],"averaged":[50],"pair-wise":[51],"distance":[52],"between":[53],"samples":[54,68],"from":[55],"same":[57],"class.":[58],"Its":[59],"prevent":[63],"scattering":[65],"of":[66,141,151],"these":[67],"within":[69],"space":[72],"increase":[74],"compactncss.When":[77],"jointly":[81],"optimized":[82],"loss,":[85],"can":[87,96],"observe":[88],"2":[89,120],"major":[90],"improvements:":[91],"network":[95,143],"achieve":[97],"more":[99,109],"robust":[100],"discriminative":[102],"representation":[103],"training":[106,144],"process":[107],"stable":[110],"faster":[113],"convergence":[114,140],"rate.":[115],"We":[116],"conduct":[117],"experiments":[118],"large":[121],"public":[122],"benchmarking":[123],"datasets":[124],"VoxCeleb":[128],"VoxForge.":[130],"The":[131],"results":[132],"show":[133],"that":[134],"helps":[137],"accelerating":[138],"significantly":[146],"improves":[147],"overall":[149],"performance":[150],"resulted":[153],"embeddings.":[154]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}