{"id":"https://openalex.org/W3197111314","doi":"https://doi.org/10.21437/interspeech.2021-111","title":"Bidirectional Multiscale Feature Aggregation for Speaker Verification","display_name":"Bidirectional Multiscale Feature Aggregation for Speaker Verification","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3197111314","doi":"https://doi.org/10.21437/interspeech.2021-111","mag":"3197111314"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-111","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-111","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","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/A5006734883","display_name":"Jiajun Qi","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiajun Qi","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038369085","display_name":"Wu Guo","orcid":"https://orcid.org/0000-0002-3779-7944"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wu Guo","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101875578","display_name":"Bin Gu","orcid":"https://orcid.org/0000-0003-1621-7311"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Gu","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5006734883"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.6987,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.76340296,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"71","last_page":"75"},"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":0.9983999729156494,"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":0.9959999918937683,"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/concatenation","display_name":"Concatenation (mathematics)","score":0.8964493274688721},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7952162027359009},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.7747796773910522},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.7731060981750488},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.6675168871879578},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.5994606018066406},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5483513474464417},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4947311580181122},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.4670281410217285},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3233250379562378},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.2659309506416321},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07831910252571106}],"concepts":[{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.8964493274688721},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7952162027359009},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.7747796773910522},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.7731060981750488},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.6675168871879578},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.5994606018066406},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5483513474464417},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4947311580181122},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.4670281410217285},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3233250379562378},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.2659309506416321},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07831910252571106},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2021-111","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-111","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4000000059604645,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3085993365","display_name":null,"funder_award_id":"(Grant No.","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6450856609","display_name":null,"funder_award_id":"U1836219","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7726157001","display_name":null,"funder_award_id":"Grant No.","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":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1836465849","https://openalex.org/W2046056978","https://openalex.org/W2150769028","https://openalex.org/W2194775991","https://openalex.org/W2406312423","https://openalex.org/W2726515241","https://openalex.org/W2747238065","https://openalex.org/W2808631503","https://openalex.org/W2889016587","https://openalex.org/W2890964092","https://openalex.org/W2916104401","https://openalex.org/W2951758756","https://openalex.org/W2953384591","https://openalex.org/W2962788625","https://openalex.org/W2963371159","https://openalex.org/W2963466847","https://openalex.org/W2972441390","https://openalex.org/W2972627751","https://openalex.org/W2972657845","https://openalex.org/W2972885011","https://openalex.org/W3020953549","https://openalex.org/W3024869864","https://openalex.org/W3094735979","https://openalex.org/W3094897602","https://openalex.org/W4283014282"],"related_works":["https://openalex.org/W2158491338","https://openalex.org/W2807901368","https://openalex.org/W2133733652","https://openalex.org/W2072658171","https://openalex.org/W2606392311","https://openalex.org/W2320042380","https://openalex.org/W4385956668","https://openalex.org/W2051274299","https://openalex.org/W468945283","https://openalex.org/W4404183094"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"propose":[4],"a":[5,37],"novel":[6],"bidirectional":[7,82],"multiscale":[8],"feature":[9,21,50],"aggregation":[10,83],"(BMFA)":[11],"network":[12,29],"with":[13],"attentional":[14,56,90],"fusion":[15,57,64,91],"modules":[16],"for":[17],"text-independent":[18],"speaker":[19],"verification.The":[20],"maps":[22,51],"from":[23,52],"different":[24,53],"stages":[25],"of":[26,43,49,80],"the":[27,63,69,78,81,88,96],"backbone":[28],"are":[30,66],"iteratively":[31],"combined":[32],"and":[33,39,72,85],"refined":[34],"in":[35],"both":[36],"bottom-up":[38],"top-down":[40],"manner.Furthermore,":[41],"instead":[42],"simple":[44],"concatenation":[45],"or":[46],"elementwise":[47],"addition":[48],"stages,":[54],"an":[55],"module":[58,92],"is":[59],"designed":[60],"to":[61],"compute":[62],"weights.Experiments":[65],"conducted":[67],"on":[68],"NIST":[70],"SRE16":[71],"VoxCeleb1":[73],"datasets.The":[74],"experimental":[75],"results":[76],"demonstrate":[77],"effectiveness":[79],"strategy":[84],"show":[86],"that":[87],"proposed":[89],"can":[93],"further":[94],"improve":[95],"performance.":[97]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-03-18T14:38:29.013473","created_date":"2025-10-10T00:00:00"}
