{"id":"https://openalex.org/W3096802056","doi":"https://doi.org/10.21437/interspeech.2020-1774","title":"Weakly Supervised Training of Hierarchical Attention Networks for Speaker Identification","display_name":"Weakly Supervised Training of Hierarchical Attention Networks for Speaker Identification","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3096802056","doi":"https://doi.org/10.21437/interspeech.2020-1774","mag":"3096802056"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-1774","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1774","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":"conference-paper","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":false,"raw_author_name":"Yanpei Shi","raw_affiliation_strings":["Speech and Hearing Research Group Department of Computer Science, University of Sheffield"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech and Hearing Research Group Department of Computer Science, University of Sheffield","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013817745","display_name":"Qiang Huang","orcid":"https://orcid.org/0000-0003-1120-4685"},"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 Department of Computer Science, University of Sheffield"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech and Hearing Research Group Department of Computer Science, 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 Department of Computer Science, University of Sheffield"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech and Hearing Research Group Department of Computer Science, University of Sheffield","institution_ids":["https://openalex.org/I91136226"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I91136226"],"apc_list":null,"apc_paid":null,"fwci":0.345,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.59640276,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991999864578247,"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":0.9991999864578247,"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":0.9979000091552734,"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":0.9907000064849854,"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":0.8060852289199829},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.6346839666366577},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6028909087181091},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5829476118087769},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5755223035812378},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5073785185813904},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48448583483695984},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4826298654079437},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.47259077429771423},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.46933308243751526},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4654361307621002},{"id":"https://openalex.org/keywords/speaker-identification","display_name":"Speaker identification","score":0.42894598841667175},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.42814210057258606},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.42331624031066895},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.3300689458847046}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8060852289199829},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6346839666366577},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6028909087181091},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5829476118087769},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5755223035812378},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5073785185813904},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48448583483695984},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4826298654079437},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.47259077429771423},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.46933308243751526},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4654361307621002},{"id":"https://openalex.org/C2986627078","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker identification","level":3,"score":0.42894598841667175},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.42814210057258606},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.42331624031066895},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.3300689458847046},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2020-1774","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1774","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":[{"score":0.7300000190734863,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1503398984","https://openalex.org/W1522301498","https://openalex.org/W1836465849","https://openalex.org/W1924770834","https://openalex.org/W1992282307","https://openalex.org/W2046056978","https://openalex.org/W2135533176","https://openalex.org/W2165084404","https://openalex.org/W2402146185","https://openalex.org/W2470673105","https://openalex.org/W2561826558","https://openalex.org/W2726515241","https://openalex.org/W2746791238","https://openalex.org/W2794506738","https://openalex.org/W2889519245","https://openalex.org/W2890964092","https://openalex.org/W2894279617","https://openalex.org/W2921528571","https://openalex.org/W2931277313","https://openalex.org/W2962959915","https://openalex.org/W2963449399","https://openalex.org/W2963723765","https://openalex.org/W2964161387","https://openalex.org/W2972757121","https://openalex.org/W3015412845"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W4318225096","https://openalex.org/W4234190324","https://openalex.org/W2545131480","https://openalex.org/W2087341511","https://openalex.org/W1521049138","https://openalex.org/W4247736853","https://openalex.org/W2997340161","https://openalex.org/W1964028329","https://openalex.org/W2136038945"],"abstract_inverted_index":{"Identifying":[0],"multiple":[1],"speakers":[2,107],"without":[3],"knowing":[4],"where":[5,133],"a":[6,11,14,19,27,35,40,44,76,84,109,170],"speaker's":[7],"voice":[8],"is":[9,13,23,99],"in":[10,130],"recording":[12],"challenging":[15],"task.In":[16],"this":[17],"paper,":[18],"hierarchical":[20,36],"attention":[21,64,86],"network":[22],"proposed":[24,116,150],"to":[25,48,88,94,105,141,160],"solve":[26],"weakly":[28],"labelled":[29],"speaker":[30,50],"identification":[31,176],"problem.The":[32],"use":[33],"of":[34,39,114,164],"structure,":[37],"consisting":[38],"frame-level":[41,61],"encoder":[42,62,81],"and":[43,54,67,74,126,138],"segment-level":[45,80,103],"encoder,":[46],"aims":[47],"learn":[49],"related":[51,71,93],"information":[52,98],"locally":[53],"globally.Speech":[55],"streams":[56],"are":[57,128,136,158],"segmented":[58],"into":[59],"fragments.The":[60],"with":[63,83],"learns":[65],"features":[66],"highlights":[68],"the":[69,90,112,115,144,149,162],"target":[70,95],"frames":[72],"locally,":[73],"output":[75],"fragment":[77],"based":[78,120],"embedding.The":[79],"works":[82],"second":[85],"layer":[87],"emphasize":[89],"fragments":[91],"probably":[92],"speakers.The":[96],"global":[97],"finally":[100],"collected":[101],"from":[102],"module":[104],"predict":[106],"via":[108],"classifier.To":[110],"evaluate":[111,161],"effectiveness":[113],"approach,":[117],"artificial":[118],"datasets":[119],"on":[121],"Switchboard":[122],"Cellular":[123],"part1":[124],"(SWBC)":[125],"Voxceleb1":[127],"constructed":[129],"two":[131,142],"conditions,":[132],"speakers'":[134],"voices":[135],"overlapped":[137],"not":[139],"overlapped.Comparing":[140],"baselines":[143],"obtained":[145],"results":[146,167],"show":[147,168],"that":[148,169],"approach":[151],"can":[152,173],"achieve":[153],"better":[154],"performances.Moreover,":[155],"further":[156],"experiments":[157],"conducted":[159],"impact":[163],"utterance":[165],"segmentation.The":[166],"reasonable":[171],"segmentation":[172],"slightly":[174],"improve":[175],"performances.":[177]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}