{"id":"https://openalex.org/W2888416031","doi":"https://doi.org/10.1109/iscslp.2018.8706589","title":"Exploring a Unified Attention-Based Pooling Framework for Speaker Verification","display_name":"Exploring a Unified Attention-Based Pooling Framework for Speaker Verification","publication_year":2018,"publication_date":"2018-11-01","ids":{"openalex":"https://openalex.org/W2888416031","doi":"https://doi.org/10.1109/iscslp.2018.8706589","mag":"2888416031"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp.2018.8706589","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2018.8706589","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 11th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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/A5100330618","display_name":"Yi Liu","orcid":"https://orcid.org/0000-0003-1399-7420"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yi Liu","raw_affiliation_strings":["Tsinghua National Laboratory for Information Science and Technology, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua National Laboratory for Information Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049944728","display_name":"Liang He","orcid":"https://orcid.org/0000-0003-4076-7479"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang He","raw_affiliation_strings":["Tsinghua National Laboratory for Information Science and Technology, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua National Laboratory for Information Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100359533","display_name":"Weiwei Liu","orcid":"https://orcid.org/0000-0003-2188-3597"},"institutions":[{"id":"https://openalex.org/I4210162172","display_name":"Chinese People\u2019s Liberation Army 263 hospital","ror":"https://ror.org/05b51ak88","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210162172"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiwei Liu","raw_affiliation_strings":["62315 Unit, Chinese People\u2019s Liberation Army, Beijing, China","62315 Unit, Chinese People's Liberation Army, Beijing, China"],"affiliations":[{"raw_affiliation_string":"62315 Unit, Chinese People\u2019s Liberation Army, Beijing, China","institution_ids":["https://openalex.org/I4210162172"]},{"raw_affiliation_string":"62315 Unit, Chinese People's Liberation Army, Beijing, China","institution_ids":["https://openalex.org/I4210162172"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100409741","display_name":"Jia Liu","orcid":"https://orcid.org/0000-0003-0383-0934"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jia Liu","raw_affiliation_strings":["Tsinghua National Laboratory for Information Science and Technology, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua National Laboratory for Information Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100330618"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.6515,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.76710595,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"200","last_page":"204"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9950000047683716,"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":0.9934999942779541,"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/pooling","display_name":"Pooling","score":0.9578482508659363},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.757481575012207},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.73963862657547},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.6324716806411743},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5923490524291992},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.5553431510925293},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5412589311599731},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.470726877450943},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.43885987997055054},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.43309125304222107},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.42427781224250793},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4193316698074341},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.339338481426239}],"concepts":[{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.9578482508659363},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.757481575012207},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.73963862657547},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.6324716806411743},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5923490524291992},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.5553431510925293},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5412589311599731},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.470726877450943},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.43885987997055054},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.43309125304222107},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.42427781224250793},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4193316698074341},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.339338481426239},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp.2018.8706589","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2018.8706589","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 11th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.6499999761581421,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W97072897","https://openalex.org/W119864726","https://openalex.org/W123007118","https://openalex.org/W204053250","https://openalex.org/W1514535095","https://openalex.org/W1524333225","https://openalex.org/W1902237438","https://openalex.org/W2039057510","https://openalex.org/W2046056978","https://openalex.org/W2114925438","https://openalex.org/W2395750323","https://openalex.org/W2402146185","https://openalex.org/W2584329820","https://openalex.org/W2612434969","https://openalex.org/W2640729626","https://openalex.org/W2748488820","https://openalex.org/W2786149683","https://openalex.org/W2787051072","https://openalex.org/W2794506738","https://openalex.org/W2953384591","https://openalex.org/W2962826786","https://openalex.org/W2962832278","https://openalex.org/W2962959915","https://openalex.org/W2963403868","https://openalex.org/W4234330420","https://openalex.org/W4385245566","https://openalex.org/W6603931906","https://openalex.org/W6604892825","https://openalex.org/W6605010638","https://openalex.org/W6608353291","https://openalex.org/W6630875275","https://openalex.org/W6631362777","https://openalex.org/W6712930963","https://openalex.org/W6713134421","https://openalex.org/W6732884072","https://openalex.org/W6737575990","https://openalex.org/W6739901393","https://openalex.org/W6745983287","https://openalex.org/W6748701266"],"related_works":["https://openalex.org/W2118039276","https://openalex.org/W2051274299","https://openalex.org/W1521299571","https://openalex.org/W2767892728","https://openalex.org/W468945283","https://openalex.org/W4235705411","https://openalex.org/W3141593045","https://openalex.org/W1998549096","https://openalex.org/W2134501921","https://openalex.org/W204267554"],"abstract_inverted_index":{"The":[0,101],"pooling":[1,24,32,59,92],"layer":[2],"is":[3,40,46],"an":[4],"essential":[5],"component":[6],"in":[7,19],"the":[8,16,27,43,65,70,86,106],"neural":[9],"network":[10],"based":[11],"speaker":[12,20,29],"verification.":[13],"Most":[14],"of":[15],"current":[17],"networks":[18],"verification":[21],"use":[22],"average":[23,91],"to":[25,84],"derive":[26],"utterance-level":[28],"representations.":[30],"Average":[31],"takes":[33],"every":[34],"frame":[35],"as":[36],"equally":[37],"important,":[38],"which":[39],"suboptimal":[41],"since":[42],"speaker-discriminant":[44],"power":[45],"different":[47],"between":[48],"speech":[49],"segments.":[50],"In":[51],"this":[52],"paper,":[53],"we":[54],"present":[55],"a":[56],"unified":[57],"attention-based":[58],"framework":[60],"and":[61,72,93],"combine":[62],"it":[63],"with":[64],"multi-head":[66,102],"attention.":[67],"Experiments":[68],"on":[69],"Fisher":[71],"NIST":[73],"SRE":[74],"2010":[75],"dataset":[76],"show":[77],"that":[78],"involving":[79],"outputs":[80],"from":[81],"lower":[82],"layers":[83],"compute":[85],"attention":[87,99,103],"weights":[88],"can":[89],"outperform":[90],"achieve":[94],"better":[95],"results":[96],"than":[97],"vanilla":[98],"method.":[100],"further":[104],"improves":[105],"performance.":[107]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}