{"id":"https://openalex.org/W3097073596","doi":"https://doi.org/10.21437/interspeech.2020-1818","title":"Speaker-Utterance Dual Attention for Speaker and Utterance Verification","display_name":"Speaker-Utterance Dual Attention for Speaker and Utterance Verification","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3097073596","doi":"https://doi.org/10.21437/interspeech.2020-1818","mag":"3097073596"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-1818","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1818","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 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/A5013047791","display_name":"Tianchi Liu","orcid":"https://orcid.org/0000-0003-3472-0703"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Tianchi Liu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029637694","display_name":"Rohan Kumar Das","orcid":"https://orcid.org/0000-0002-1332-3357"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rohan Kumar Das","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048910634","display_name":"Maulik C. Madhavi","orcid":"https://orcid.org/0000-0001-8743-6437"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Maulik Madhavi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028803088","display_name":"Shengmei Shen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shengmei Shen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":"https://orcid.org/0000-0001-9158-9401"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5013047791"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9279,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.80808127,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"4293","last_page":"4297"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"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":0.9994000196456909,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9925000071525574,"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/T10028","display_name":"Topic Modeling","score":0.9879000186920166,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.9556543827056885},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7143862247467041},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.7068862915039062},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6636916995048523},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.617434024810791},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5507071614265442},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5339300632476807},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3544016480445862},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3542373776435852},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.16338521242141724}],"concepts":[{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.9556543827056885},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7143862247467041},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.7068862915039062},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6636916995048523},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.617434024810791},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5507071614265442},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5339300632476807},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3544016480445862},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3542373776435852},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.16338521242141724},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2020-1818","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1818","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6600000262260437}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W1901037250","https://openalex.org/W1946464671","https://openalex.org/W58284675","https://openalex.org/W2747262669","https://openalex.org/W2018305822","https://openalex.org/W2687193347","https://openalex.org/W4313033198","https://openalex.org/W2066941761","https://openalex.org/W2167882836","https://openalex.org/W2951423096"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"study":[4],"a":[5,37],"novel":[6],"technique":[7],"that":[8,101],"exploits":[9],"the":[10,50,68,71,83,91,102,106],"interaction":[11,69],"between":[12,70],"speaker":[13,21,54,72,119],"traits":[14],"and":[15,23,55,73,120],"linguistic":[16],"content":[17],"to":[18,45,66,79],"improve":[19],"both":[20,118],"verification":[22,25],"utterance":[24,56,74,121],"performance.":[26],"We":[27],"implement":[28],"an":[29,46,62],"idea":[30],"of":[31,53],"speaker-utterance":[32],"dual":[33,42],"attention":[34,43,47,63,109],"(SUDA)":[35],"in":[36],"unified":[38],"neural":[39],"network.":[40],"The":[41,58,94],"refers":[44],"mechanism":[48,65],"for":[49,86,117],"two":[51],"tasks":[52],"verification.":[57,122],"proposed":[59,103],"SUDA":[60,104],"features":[61],"mask":[64,110],"learn":[67],"information":[75,85],"streams.":[76],"This":[77],"helps":[78],"focus":[80],"only":[81],"on":[82,97],"required":[84],"respective":[87],"task":[88],"by":[89],"masking":[90],"irrelevant":[92],"counterparts.":[93],"studies":[95],"conducted":[96],"RSR2015":[98],"corpus":[99],"confirm":[100],"outperforms":[105],"framework":[107],"without":[108],"as":[111,113],"well":[112],"several":[114],"competitive":[115],"systems":[116]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
