{"id":"https://openalex.org/W4226230385","doi":"https://doi.org/10.1109/taslp.2022.3153267","title":"Aggregating Frame-Level Information in the Spectral Domain With Self-Attention for Speaker Embedding","display_name":"Aggregating Frame-Level Information in the Spectral Domain With Self-Attention for Speaker Embedding","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4226230385","doi":"https://doi.org/10.1109/taslp.2022.3153267"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2022.3153267","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3153267","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://ira.lib.polyu.edu.hk/bitstream/10397/95740/1/att_stsp_j.pdf","any_repository_has_fulltext":true},"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, China"],"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University, Hong Kong, China","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, China"],"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University, Hong Kong, China","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":1.3797,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.83819271,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"30","issue":null,"first_page":"944","last_page":"957"},"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":0.9991999864578247,"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":0.9987000226974487,"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":0.7029203176498413},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6933474540710449},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6739926338195801},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.6394089460372925},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6356273889541626},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6294174194335938},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6077032089233398},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5403227806091309},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.47600802779197693},{"id":"https://openalex.org/keywords/frequency-domain","display_name":"Frequency domain","score":0.445169597864151},{"id":"https://openalex.org/keywords/aggregate","display_name":"Aggregate (composite)","score":0.42424753308296204},{"id":"https://openalex.org/keywords/fourier-transform","display_name":"Fourier transform","score":0.4212011694908142},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4199274182319641},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3909553289413452},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2617177367210388},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.08095544576644897}],"concepts":[{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.7029203176498413},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6933474540710449},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6739926338195801},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.6394089460372925},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6356273889541626},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6294174194335938},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6077032089233398},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5403227806091309},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.47600802779197693},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.445169597864151},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.42424753308296204},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.4212011694908142},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4199274182319641},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3909553289413452},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2617177367210388},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.08095544576644897},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","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/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/taslp.2022.3153267","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3153267","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:ira.lib.polyu.edu.hk:10397/95740","is_oa":true,"landing_page_url":"http://hdl.handle.net/10397/95740","pdf_url":"http://ira.lib.polyu.edu.hk/bitstream/10397/95740/1/att_stsp_j.pdf","source":{"id":"https://openalex.org/S4306400205","display_name":"PolyU Institutional Research Archive (Hong Kong Polytechnic University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I14243506","host_organization_name":"Hong Kong Polytechnic University","host_organization_lineage":["https://openalex.org/I14243506"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Journal/Magazine Article"}],"best_oa_location":{"id":"pmh:oai:ira.lib.polyu.edu.hk:10397/95740","is_oa":true,"landing_page_url":"http://hdl.handle.net/10397/95740","pdf_url":"http://ira.lib.polyu.edu.hk/bitstream/10397/95740/1/att_stsp_j.pdf","source":{"id":"https://openalex.org/S4306400205","display_name":"PolyU Institutional Research Archive (Hong Kong Polytechnic University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I14243506","host_organization_name":"Hong Kong Polytechnic University","host_organization_lineage":["https://openalex.org/I14243506"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Journal/Magazine Article"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7200000286102295}],"awards":[{"id":"https://openalex.org/G2168692635","display_name":null,"funder_award_id":"61971371","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4226230385.pdf","grobid_xml":"https://content.openalex.org/works/W4226230385.grobid-xml"},"referenced_works_count":49,"referenced_works":["https://openalex.org/W1557133539","https://openalex.org/W1589137271","https://openalex.org/W2020997493","https://openalex.org/W2111460811","https://openalex.org/W2114925438","https://openalex.org/W2137075158","https://openalex.org/W2150769028","https://openalex.org/W2194775991","https://openalex.org/W2281740710","https://openalex.org/W2478884216","https://openalex.org/W2566079294","https://openalex.org/W2612434969","https://openalex.org/W2747165665","https://openalex.org/W2784163702","https://openalex.org/W2794506738","https://openalex.org/W2889519245","https://openalex.org/W2890964092","https://openalex.org/W2916104401","https://openalex.org/W2916301830","https://openalex.org/W2928165649","https://openalex.org/W2944398172","https://openalex.org/W2951019013","https://openalex.org/W2963371159","https://openalex.org/W2971105107","https://openalex.org/W2972369255","https://openalex.org/W2972387750","https://openalex.org/W2972392008","https://openalex.org/W2973147881","https://openalex.org/W2978904488","https://openalex.org/W2979593053","https://openalex.org/W2981087920","https://openalex.org/W3015197287","https://openalex.org/W3015261361","https://openalex.org/W3015964387","https://openalex.org/W3024200162","https://openalex.org/W3024855809","https://openalex.org/W3024869864","https://openalex.org/W3038083940","https://openalex.org/W3103152812","https://openalex.org/W3162224131","https://openalex.org/W3162267844","https://openalex.org/W4244003036","https://openalex.org/W6638667902","https://openalex.org/W6638946568","https://openalex.org/W6737575990","https://openalex.org/W6739901393","https://openalex.org/W6740005241","https://openalex.org/W6755308174","https://openalex.org/W6781533629"],"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/W2064323827"],"abstract_inverted_index":{"Most":[0],"pooling":[1,75,165],"methods":[2],"in":[3,10,20,63,136],"state-of-the-art":[4],"speaker":[5,125,187],"embedding":[6],"networks":[7],"are":[8],"implemented":[9],"the":[11,17,21,26,36,45,64,84,88,99,107,124,130,137,141,147,152],"temporal":[12,46],"domain.":[13,66],"However,":[14],"due":[15],"to":[16,34,55,82,122,161],"high":[18],"non-stationarity":[19],"feature":[22,47,89,131],"maps":[23,48],"produced":[24],"from":[25,78],"last":[27],"frame-level":[28],"layer,":[29],"it":[30],"is":[31,134,159],"not":[32],"advantageous":[33],"use":[35],"global":[37],"statistics":[38],"(e.g.,":[39],"means":[40],"and":[41,60,116,170,179],"standard":[42],"deviations)":[43],"of":[44,87,106,129,140],"as":[49],"aggregated":[50],"embeddings.":[51,188],"This":[52,172],"motivates":[53],"us":[54],"explore":[56],"stationary":[57],"spectral":[58,65,74,100,120,142,154,182],"representations":[59,101],"perform":[61],"aggregation":[62,149],"In":[67,91],"this":[68],"paper,":[69],"we":[70,97],"propose":[71],"attentive":[72,92,144,164],"short-time":[73],"(attentive":[76],"STSP)":[77],"a":[79,103],"Fourier":[80],"perspective":[81],"exploit":[83],"local":[85],"stationarity":[86],"maps.":[90],"STSP,":[93],"for":[94],"each":[95,111],"utterance,":[96],"compute":[98],"through":[102],"weighted":[104],"average":[105],"windowed":[108],"segments":[109],"within":[110],"spectrogram":[112],"by":[113,150],"attention":[114,178],"weights":[115],"aggregate":[117],"their":[118],"lowest":[119],"components":[121,155,183],"form":[123],"embedding.":[126],"Because":[127],"most":[128],"map":[132],"energy":[133],"concentrated":[135],"low-frequency":[138],"region":[139],"domain,":[143],"STSP":[145,158],"facilitates":[146],"information":[148],"retaining":[151],"low":[153,181],"only.":[156],"Attentive":[157],"shown":[160],"consistently":[162],"outperform":[163],"on":[166],"VoxCeleb1,":[167],"VOiCES19-eval,":[168],"SRE16-eval,":[169],"SRE18-CMN2-eval.":[171],"observation":[173],"suggests":[174],"that":[175],"applying":[176],"segment-level":[177],"leveraging":[180],"can":[184],"produce":[185],"discriminative":[186]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}