{"id":"https://openalex.org/W2937033898","doi":"https://doi.org/10.1109/icassp.2019.8682676","title":"Seq2Seq Attentional Siamese Neural Networks for Text-dependent Speaker Verification","display_name":"Seq2Seq Attentional Siamese Neural Networks for Text-dependent Speaker Verification","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2937033898","doi":"https://doi.org/10.1109/icassp.2019.8682676","mag":"2937033898"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8682676","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682676","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 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/A5100444198","display_name":"Yichi Zhang","orcid":"https://orcid.org/0000-0003-0465-6341"},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yichi Zhang","raw_affiliation_strings":["Dept. of Electrical and Computer Engineering, University of Rochester, Rochester, NY, USA"],"affiliations":[{"raw_affiliation_string":"Dept. of Electrical and Computer Engineering, University of Rochester, Rochester, NY, USA","institution_ids":["https://openalex.org/I5388228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100770786","display_name":"Meng Yu","orcid":"https://orcid.org/0000-0003-2554-2888"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meng Yu","raw_affiliation_strings":["Tencent AI Lab, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100368048","display_name":"Na Li","orcid":"https://orcid.org/0000-0001-9545-3050"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Na Li","raw_affiliation_strings":["Tencent AI Lab, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040951732","display_name":"Chengzhu Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210108985","display_name":"Bellevue Hospital Center","ror":"https://ror.org/01ky34z31","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1283621791","https://openalex.org/I4210086933","https://openalex.org/I4210108985"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chengzhu Yu","raw_affiliation_strings":["Tencent AI Lab, Bellevue, WA, USA"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Bellevue, WA, USA","institution_ids":["https://openalex.org/I4210108985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101625242","display_name":"Jia Cui","orcid":"https://orcid.org/0000-0002-1631-0535"},"institutions":[{"id":"https://openalex.org/I4210108985","display_name":"Bellevue Hospital Center","ror":"https://ror.org/01ky34z31","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1283621791","https://openalex.org/I4210086933","https://openalex.org/I4210108985"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jia Cui","raw_affiliation_strings":["Tencent AI Lab, Bellevue, WA, USA"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Bellevue, WA, USA","institution_ids":["https://openalex.org/I4210108985"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034476404","display_name":"Dong Yu","orcid":"https://orcid.org/0000-0003-0520-6844"},"institutions":[{"id":"https://openalex.org/I4210108985","display_name":"Bellevue Hospital Center","ror":"https://ror.org/01ky34z31","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1283621791","https://openalex.org/I4210086933","https://openalex.org/I4210108985"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dong Yu","raw_affiliation_strings":["Tencent AI Lab, Bellevue, WA, USA"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Bellevue, WA, USA","institution_ids":["https://openalex.org/I4210108985"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100444198"],"corresponding_institution_ids":["https://openalex.org/I5388228"],"apc_list":null,"apc_paid":null,"fwci":4.4806,"has_fulltext":false,"cited_by_count":47,"citation_normalized_percentile":{"value":0.95609479,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"6131","last_page":"6135"},"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":0.9987000226974487,"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":0.998199999332428,"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":0.8007974624633789},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.7602856755256653},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6644382476806641},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5910150408744812},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5848026871681213},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5661031007766724},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5564278364181519},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5507168769836426},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5198134183883667},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5149058103561401},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.49545180797576904},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4845656454563141},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.4299767017364502},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42714235186576843},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.3296896815299988}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8007974624633789},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.7602856755256653},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6644382476806641},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5910150408744812},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5848026871681213},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5661031007766724},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5564278364181519},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5507168769836426},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5198134183883667},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5149058103561401},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.49545180797576904},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4845656454563141},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.4299767017364502},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42714235186576843},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.3296896815299988},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"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/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8682676","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682676","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7200000286102295,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1895577753","https://openalex.org/W1902237438","https://openalex.org/W2041823554","https://openalex.org/W2046056978","https://openalex.org/W2064364374","https://openalex.org/W2114925438","https://openalex.org/W2129244720","https://openalex.org/W2147147599","https://openalex.org/W2150769028","https://openalex.org/W2157364932","https://openalex.org/W2160815625","https://openalex.org/W2184045248","https://openalex.org/W2407374891","https://openalex.org/W2470394683","https://openalex.org/W2584329820","https://openalex.org/W2612434969","https://openalex.org/W2775430159","https://openalex.org/W2885918317","https://openalex.org/W2889726676","https://openalex.org/W2962898354","https://openalex.org/W2962959915","https://openalex.org/W6714259624","https://openalex.org/W6732884072","https://openalex.org/W6737575990","https://openalex.org/W6745983287"],"related_works":["https://openalex.org/W2970216048","https://openalex.org/W2747262669","https://openalex.org/W2103897043","https://openalex.org/W58284675","https://openalex.org/W1901037250","https://openalex.org/W1946464671","https://openalex.org/W3148366653","https://openalex.org/W2066941761","https://openalex.org/W1889843584","https://openalex.org/W2018305822"],"abstract_inverted_index":{"In":[0,21],"this":[1],"paper,":[2],"we":[3],"present":[4],"a":[5,40,105,114],"Sequence-to-Sequence":[6],"Attentional":[7],"Siamese":[8],"Neural":[9],"Network":[10],"(Seq2Seq-ASNN)":[11],"that":[12,84],"leverages":[13],"temporal":[14],"alignment":[15],"information":[16],"for":[17,62,109],"end-to-end":[18,78,98],"speaker":[19,25,31,99,111],"verification.":[20],"prior":[22],"works":[23],"of":[24],"discriminative":[26],"neural":[27],"networks,":[28],"utterance-level":[29,58],"evaluation/enrollment":[30],"representations":[32],"are":[33,73],"usually":[34],"calculated.":[35],"Our":[36],"proposed":[37,86],"model,":[38,108],"utilizing":[39],"sequence-to-sequence":[41],"(Seq2Seq)":[42],"attention":[43,68,107],"mechanism,":[44,69],"maps":[45],"the":[46,93],"frame-level":[47],"evaluation":[48],"representation":[49],"into":[50],"enrollment":[51],"feature":[52],"domain":[53],"and":[54,70,104],"further":[55],"generates":[56],"an":[57,77],"evaluation-enrollment":[59],"joint":[60],"vector":[61],"final":[63],"similarity":[64],"measure.":[65],"Feature":[66],"learning,":[67],"metric":[71],"learning":[72],"jointly":[74],"optimized":[75],"using":[76],"loss":[79],"function.":[80],"Experimental":[81],"results":[82],"show":[83],"our":[85],"model":[87],"outperforms":[88],"various":[89],"baseline":[90],"methods,":[91],"including":[92],"traditional":[94],"i-Vector/PLDA":[95],"method,":[96],"multi-enrollment":[97],"verification":[100,112],"models,":[101],"d-vector":[102],"approaches,":[103],"self":[106],"text-dependent":[110],"on":[113],"Tencent":[115],"internal":[116],"voice":[117],"wake-up":[118],"dataset.":[119]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":11},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}