{"id":"https://openalex.org/W2801608439","doi":"https://doi.org/10.1109/icassp.2018.8461296","title":"Generalised Discriminative Transform via Curriculum Learning for Speaker Recognition","display_name":"Generalised Discriminative Transform via Curriculum Learning for Speaker Recognition","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2801608439","doi":"https://doi.org/10.1109/icassp.2018.8461296","mag":"2801608439"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461296","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-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/A5009327522","display_name":"Erik Marchi","orcid":"https://orcid.org/0000-0002-5335-6356"},"institutions":[{"id":"https://openalex.org/I4210153776","display_name":"Apple (United States)","ror":"https://ror.org/059hsda18","country_code":"US","type":"company","lineage":["https://openalex.org/I4210153776"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Erik Marchi","raw_affiliation_strings":["Siri Speech Apple Inc."],"affiliations":[{"raw_affiliation_string":"Siri Speech Apple Inc.","institution_ids":["https://openalex.org/I4210153776"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051278718","display_name":"Stephen Shum","orcid":null},"institutions":[{"id":"https://openalex.org/I4210153776","display_name":"Apple (United States)","ror":"https://ror.org/059hsda18","country_code":"US","type":"company","lineage":["https://openalex.org/I4210153776"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stephen Shum","raw_affiliation_strings":["Siri Speech Apple Inc."],"affiliations":[{"raw_affiliation_string":"Siri Speech Apple Inc.","institution_ids":["https://openalex.org/I4210153776"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057914051","display_name":"Kyuyeon Hwang","orcid":"https://orcid.org/0000-0001-6700-1583"},"institutions":[{"id":"https://openalex.org/I4210153776","display_name":"Apple (United States)","ror":"https://ror.org/059hsda18","country_code":"US","type":"company","lineage":["https://openalex.org/I4210153776"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kyuyeon Hwang","raw_affiliation_strings":["Siri Speech Apple Inc."],"affiliations":[{"raw_affiliation_string":"Siri Speech Apple Inc.","institution_ids":["https://openalex.org/I4210153776"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065814281","display_name":"Sachin Kajarekar","orcid":null},"institutions":[{"id":"https://openalex.org/I4210153776","display_name":"Apple (United States)","ror":"https://ror.org/059hsda18","country_code":"US","type":"company","lineage":["https://openalex.org/I4210153776"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sachin Kajarekar","raw_affiliation_strings":["Siri Speech Apple Inc."],"affiliations":[{"raw_affiliation_string":"Siri Speech Apple Inc.","institution_ids":["https://openalex.org/I4210153776"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113798270","display_name":"Siddharth Sigtia","orcid":null},"institutions":[{"id":"https://openalex.org/I4210153776","display_name":"Apple (United States)","ror":"https://ror.org/059hsda18","country_code":"US","type":"company","lineage":["https://openalex.org/I4210153776"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Siddharth Sigtia","raw_affiliation_strings":["Siri Speech Apple Inc."],"affiliations":[{"raw_affiliation_string":"Siri Speech Apple Inc.","institution_ids":["https://openalex.org/I4210153776"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005078804","display_name":"Hywel Richards","orcid":null},"institutions":[{"id":"https://openalex.org/I4210153776","display_name":"Apple (United States)","ror":"https://ror.org/059hsda18","country_code":"US","type":"company","lineage":["https://openalex.org/I4210153776"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hywel Richards","raw_affiliation_strings":["Siri Speech Apple Inc."],"affiliations":[{"raw_affiliation_string":"Siri Speech Apple Inc.","institution_ids":["https://openalex.org/I4210153776"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000034447","display_name":"Rob Haynes","orcid":null},"institutions":[{"id":"https://openalex.org/I4210153776","display_name":"Apple (United States)","ror":"https://ror.org/059hsda18","country_code":"US","type":"company","lineage":["https://openalex.org/I4210153776"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rob Haynes","raw_affiliation_strings":["Siri Speech Apple Inc."],"affiliations":[{"raw_affiliation_string":"Siri Speech Apple Inc.","institution_ids":["https://openalex.org/I4210153776"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100693795","display_name":"Yoon Kim","orcid":"https://orcid.org/0000-0001-7257-1679"},"institutions":[{"id":"https://openalex.org/I4210153776","display_name":"Apple (United States)","ror":"https://ror.org/059hsda18","country_code":"US","type":"company","lineage":["https://openalex.org/I4210153776"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yoon Kim","raw_affiliation_strings":["Siri Speech Apple Inc."],"affiliations":[{"raw_affiliation_string":"Siri Speech Apple Inc.","institution_ids":["https://openalex.org/I4210153776"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103410518","display_name":"John S. Bridle","orcid":null},"institutions":[{"id":"https://openalex.org/I4210153776","display_name":"Apple (United States)","ror":"https://ror.org/059hsda18","country_code":"US","type":"company","lineage":["https://openalex.org/I4210153776"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John Bridle","raw_affiliation_strings":["Siri Speech Apple Inc."],"affiliations":[{"raw_affiliation_string":"Siri Speech Apple Inc.","institution_ids":["https://openalex.org/I4210153776"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.102,"has_fulltext":true,"fulltext_origin":"ngrams","cited_by_count":22,"citation_normalized_percentile":{"value":0.79171,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":92},"biblio":{"volume":null,"issue":null,"first_page":"5324","last_page":"5328"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9999,"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":0.9999,"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":0.9994,"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/T10860","display_name":"Speech and Audio Processing","score":0.9977,"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":0.7699309},{"id":"https://openalex.org/keywords/cosine-similarity","display_name":"Cosine similarity","score":0.6837031},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.6065328},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5319011},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.49230134},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.42280623}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7939532},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7699309},{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.6837031},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6465609},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6065328},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5593676},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5319011},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4926322},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.49230134},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4763458},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.42280623},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39248577},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461296","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":18,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W183625566","https://openalex.org/W2040105822","https://openalex.org/W2041823554","https://openalex.org/W2078953162","https://openalex.org/W2114925438","https://openalex.org/W2116261113","https://openalex.org/W2129379984","https://openalex.org/W2150769028","https://openalex.org/W2163840654","https://openalex.org/W2296073425","https://openalex.org/W2345837149","https://openalex.org/W2584329820","https://openalex.org/W2587150483","https://openalex.org/W2612434969","https://openalex.org/W2963390466","https://openalex.org/W4297580293","https://openalex.org/W4298018319"],"related_works":["https://openalex.org/W4255044973","https://openalex.org/W3148366653","https://openalex.org/W2890936991","https://openalex.org/W2727729836","https://openalex.org/W2619127353","https://openalex.org/W2548037963","https://openalex.org/W2499802997","https://openalex.org/W2162582511","https://openalex.org/W2112059504","https://openalex.org/W1960256358"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3],"introduce":[4,48],"a":[5,19,24,33,63,96,109],"speaker":[6,34,41],"verification":[7],"system":[8,27,56,93],"deployed":[9],"on":[10,80,102],"mobile":[11],"devices":[12],"that":[13,28,85],"can":[14],"be":[15],"used":[16,38],"to":[17,32,39,67],"personalise":[18],"keyword":[20],"spotter.":[21],"We":[22,46],"describe":[23],"baseline":[25,92],"DNN":[26,91],"maps":[29],"an":[30,49,54],"utterance":[31],"embedding,":[35],"which":[36,52],"is":[37],"measure":[40],"differences":[42],"via":[43,62],"cosine":[44],"similarity.":[45],"then":[47],"architectural":[50],"modification":[51],"uses":[53],"LSTM":[55],"where":[57],"the":[58,69,86,90],"parameters":[59],"are":[60],"optimised":[61],"curriculum":[64],"learning":[65],"procedure":[66],"reduce":[68],"detection":[70],"error":[71],"and":[72,94,105],"improve":[73],"its":[74],"generalisability":[75],"across":[76],"various":[77],"conditions.":[78,113],"Experiments":[79],"our":[81],"internal":[82],"datasets":[83],"show":[84],"proposed":[87],"approach":[88],"outperforms":[89],"yields":[95],"relative":[97],"EER":[98],"reduction":[99],"of":[100,111],"30-70%":[101],"both":[103],"text-dependent":[104],"text-independent":[106],"tasks":[107],"under":[108],"variety":[110],"acoustic":[112]},"abstract_inverted_index_v3":null,"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2801608439","counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":4}],"updated_date":"2025-03-19T23:49:27.042519","created_date":"2018-05-17"}