{"id":"https://openalex.org/W3015412845","doi":"https://doi.org/10.1109/icassp40776.2020.9054448","title":"H-Vectors: Utterance-Level Speaker Embedding Using a Hierarchical Attention Model","display_name":"H-Vectors: Utterance-Level Speaker Embedding Using a Hierarchical Attention Model","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015412845","doi":"https://doi.org/10.1109/icassp40776.2020.9054448","mag":"3015412845"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054448","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054448","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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/A5088459219","display_name":"Yanpei Shi","orcid":"https://orcid.org/0000-0001-8157-2630"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Yanpei Shi","raw_affiliation_strings":["Speech and Hearing Research Group, University of Sheffield"],"affiliations":[{"raw_affiliation_string":"Speech and Hearing Research Group, University of Sheffield","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100617917","display_name":"Qiang Huang","orcid":"https://orcid.org/0000-0003-0046-0923"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Qiang Huang","raw_affiliation_strings":["Speech and Hearing Research Group, University of Sheffield"],"affiliations":[{"raw_affiliation_string":"Speech and Hearing Research Group, University of Sheffield","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030528300","display_name":"Thomas Hain","orcid":"https://orcid.org/0000-0003-0939-3464"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Thomas Hain","raw_affiliation_strings":["Speech and Hearing Research Group, University of Sheffield"],"affiliations":[{"raw_affiliation_string":"Speech and Hearing Research Group, University of Sheffield","institution_ids":["https://openalex.org/I91136226"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5088459219"],"corresponding_institution_ids":["https://openalex.org/I91136226"],"apc_list":null,"apc_paid":null,"fwci":2.121,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.8961615,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"7579","last_page":"7583"},"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":0.9962000250816345,"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":0.993399977684021,"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/utterance","display_name":"Utterance","score":0.8890097141265869},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7540483474731445},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.688407838344574},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6040858030319214},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.5942035913467407},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5934429168701172},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5768380761146545},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.47332534193992615},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4670112729072571},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4653632938861847},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4343832731246948},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4323105216026306},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.4278607666492462},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.41408276557922363}],"concepts":[{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.8890097141265869},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7540483474731445},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.688407838344574},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6040858030319214},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.5942035913467407},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5934429168701172},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5768380761146545},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.47332534193992615},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4670112729072571},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4653632938861847},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4343832731246948},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4323105216026306},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.4278607666492462},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.41408276557922363},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054448","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054448","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.7200000286102295,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1576113739","https://openalex.org/W1836465849","https://openalex.org/W1924770834","https://openalex.org/W2046056978","https://openalex.org/W2095705004","https://openalex.org/W2150769028","https://openalex.org/W2187089797","https://openalex.org/W2470673105","https://openalex.org/W2481304079","https://openalex.org/W2593163713","https://openalex.org/W2638067502","https://openalex.org/W2748488820","https://openalex.org/W2807305309","https://openalex.org/W2889050579","https://openalex.org/W2889060826","https://openalex.org/W2889519245","https://openalex.org/W2890964092","https://openalex.org/W2894279617","https://openalex.org/W2963470929","https://openalex.org/W2963576203","https://openalex.org/W2964121744","https://openalex.org/W2972757121","https://openalex.org/W2973016613","https://openalex.org/W6631190155","https://openalex.org/W6638667902","https://openalex.org/W6640212811","https://openalex.org/W6674330103","https://openalex.org/W6682600690"],"related_works":["https://openalex.org/W4384929466","https://openalex.org/W2206035908","https://openalex.org/W3148366653","https://openalex.org/W2149220986","https://openalex.org/W1493012537","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1999004162","https://openalex.org/W2125642021","https://openalex.org/W1521049138"],"abstract_inverted_index":{"In":[0,46,130],"this":[1],"paper,":[2],"a":[3,149,168],"hierarchical":[4,35],"attention":[5,53,70],"network":[6],"is":[7,71,97],"proposed":[8,48,88],"to":[9,29,38,77,116],"generate":[10,63],"utterance-level":[11,156],"embeddings":[12,123,157],"(H-vectors)":[13],"for":[14,99],"speaker":[15,30,40,125],"identification":[16,126],"and":[17,44,52,62,101,108,127,136],"verification.":[18],"Since":[19],"different":[20,27],"parts":[21],"of":[22,34,58,86,92,120,145],"an":[23,59,79],"utterance":[24,61,80,122],"may":[25],"have":[26],"contributions":[28],"identities,":[31],"the":[32,47,74,84,87,90,93,104,109,118,138,143,154,162],"use":[33,144],"structure":[36],"aims":[37],"learn":[39],"related":[41],"information":[42],"locally":[43],"globally.":[45],"approach,":[49,89],"frame-level":[50],"encoder":[51],"are":[54,114,158],"applied":[55,72],"on":[56,73,124],"segments":[57],"input":[60],"individual":[64],"segment":[65,68,75],"vectors.":[66],"Then,":[67],"level":[69],"vectors":[76],"construct":[78],"representation.":[81],"To":[82],"evaluate":[83,117],"effectiveness":[85],"data":[91],"NIST":[94],"SRE2008":[95],"Part1":[96],"used":[98,115],"training,":[100],"two":[102,133,163],"datasets,":[103],"Switchboard":[105],"Cellular":[106],"(Part1)":[107],"CallHome":[110],"American":[111],"English":[112],"Speech,":[113],"quality":[119],"extracted":[121],"verification":[128],"tasks.":[129],"comparison":[131],"with":[132],"baselines,":[134],"X-vectors":[135],"X-vectors+Attention,":[137],"obtained":[139],"results":[140],"show":[141],"that":[142],"H-vectors":[146],"can":[147],"achieve":[148],"significantly":[150],"better":[151],"performance.":[152],"Furthermore,":[153],"learned":[155],"more":[159],"discriminative":[160],"than":[161],"baselines":[164],"when":[165],"mapped":[166],"into":[167],"2D":[169],"space":[170],"using":[171],"t-SNE.":[172]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":8}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}