{"id":"https://openalex.org/W3162224131","doi":"https://doi.org/10.1109/icassp39728.2021.9414094","title":"Short-Time Spectral Aggregation for Speaker Embedding","display_name":"Short-Time Spectral Aggregation for Speaker Embedding","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3162224131","doi":"https://doi.org/10.1109/icassp39728.2021.9414094","mag":"3162224131"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414094","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414094","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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/A5019467579","display_name":"Youzhi Tu","orcid":"https://orcid.org/0000-0002-9580-2414"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Youzhi Tu","raw_affiliation_strings":["The Hong Kong Polytechnic University, Hong Kong SAR"],"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University, Hong Kong SAR","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068768998","display_name":"Man\u2010Wai Mak","orcid":"https://orcid.org/0000-0001-8854-3760"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Man-Wai Mak","raw_affiliation_strings":["The Hong Kong Polytechnic University, Hong Kong SAR"],"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University, Hong Kong SAR","institution_ids":["https://openalex.org/I14243506"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5019467579"],"corresponding_institution_ids":["https://openalex.org/I14243506"],"apc_list":null,"apc_paid":null,"fwci":1.0877,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.81420421,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"25","issue":null,"first_page":"6708","last_page":"6712"},"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":0.9976000189781189,"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":0.9958999752998352,"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":0.8185350298881531},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.8144201040267944},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7124742865562439},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.7048331499099731},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6579905152320862},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6538196802139282},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6176322102546692},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5593814849853516},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5326191186904907},{"id":"https://openalex.org/keywords/aggregate","display_name":"Aggregate (composite)","score":0.5070273876190186},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.49736669659614563},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4592999219894409}],"concepts":[{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.8185350298881531},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8144201040267944},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7124742865562439},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.7048331499099731},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6579905152320862},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6538196802139282},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6176322102546692},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5593814849853516},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5326191186904907},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.5070273876190186},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.49736669659614563},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4592999219894409},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414094","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414094","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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":0.7400000095367432,"display_name":"Reduced inequalities"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W123426918","https://openalex.org/W1557133539","https://openalex.org/W1839118408","https://openalex.org/W2020997493","https://openalex.org/W2150769028","https://openalex.org/W2194775991","https://openalex.org/W2478884216","https://openalex.org/W2612434969","https://openalex.org/W2747165665","https://openalex.org/W2794506738","https://openalex.org/W2796898542","https://openalex.org/W2888867175","https://openalex.org/W2889519245","https://openalex.org/W2890964092","https://openalex.org/W2916024349","https://openalex.org/W2916104401","https://openalex.org/W2963371159","https://openalex.org/W2972392008","https://openalex.org/W2973147881","https://openalex.org/W2981087920","https://openalex.org/W3015261361","https://openalex.org/W3015964387","https://openalex.org/W3024200162","https://openalex.org/W3038083940","https://openalex.org/W4288558760","https://openalex.org/W6638946568","https://openalex.org/W6737575990","https://openalex.org/W6760112457","https://openalex.org/W6769246335"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W2088854863","https://openalex.org/W4402568167","https://openalex.org/W3179495260","https://openalex.org/W1976719989","https://openalex.org/W3127543252","https://openalex.org/W2065606036","https://openalex.org/W2953234277"],"abstract_inverted_index":{"State-of-the-art":[0],"speaker":[1,52,88,151],"verification":[2],"systems":[3],"take":[4],"frame-level":[5,23,42],"acoustics":[6],"features":[7,24],"as":[8,14],"input":[9],"and":[10,59,122,131],"produce":[11,148],"fixed-dimensional":[12],"embeddings":[13],"utterance-level":[15],"representations.":[16],"Thus,":[17],"how":[18],"to":[19,83],"aggregate":[20],"information":[21,89,141],"from":[22,72],"is":[25,81,105],"vital":[26],"for":[27,38,69],"achieving":[28],"high":[29],"performance.":[30],"This":[31],"paper":[32],"introduces":[33],"short-time":[34],"spectral":[35,57,63,97,115,140],"pooling":[36,104,130],"(STSP)":[37],"better":[39],"aggregation":[40],"of":[41,50,65,76,86,109],"information.":[43],"STSP":[44,80,110,127],"transforms":[45],"the":[46,56,61,66,73,77,87,91,113,143],"temporal":[47],"feature":[48,92,145],"maps":[49,93,146],"a":[51,95,106],"embedding":[53],"network":[54],"into":[55],"domain":[58],"extracts":[60],"lowest":[62],"components":[64,98,116],"averaged":[67,78],"spectrograms":[68],"aggregation.":[70],"Benefiting":[71],"low-pass":[74],"characteristic":[75],"spectrograms,":[79],"able":[82],"preserve":[84],"most":[85],"in":[90,142],"using":[94],"few":[96],"only.":[99],"We":[100],"show":[101,125],"that":[102,126,137],"statistics":[103,129],"special":[107],"case":[108],"where":[111],"only":[112],"DC":[114],"are":[117],"used.":[118],"Experiments":[119],"on":[120],"VoxCeleb1":[121],"VOiCES":[123],"2019":[124],"outperforms":[128],"multi-head":[132],"attentive":[133],"pooling,":[134],"which":[135],"suggests":[136],"leveraging":[138],"more":[139],"CNN":[144],"can":[147],"highly":[149],"discriminative":[150],"embeddings.":[152]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}