{"id":"https://openalex.org/W4221154746","doi":"https://doi.org/10.1109/icassp43922.2022.9747021","title":"MFA: TDNN with Multi-Scale Frequency-Channel Attention for Text-Independent Speaker Verification with Short Utterances","display_name":"MFA: TDNN with Multi-Scale Frequency-Channel Attention for Text-Independent Speaker Verification with Short Utterances","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4221154746","doi":"https://doi.org/10.1109/icassp43922.2022.9747021"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747021","doi":"https://doi.org/10.1109/icassp43922.2022.9747021","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747021","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"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/A5013047791","display_name":"Tianchi Liu","orcid":"https://orcid.org/0000-0003-3472-0703","observed_orcids":["https://orcid.org/0000-0003-3472-0703"]},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Tianchi Liu","raw_affiliation_strings":["A*STAR,Institute for Infocomm Research,Singapore","Department of Electrical and Computer Engineering, National University of Singapore, Singapore","Institute for Infocomm Research, A*STAR, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"A*STAR,Institute for Infocomm Research,Singapore","institution_ids":["https://openalex.org/I115228651","https://openalex.org/I3005327000"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"Institute for Infocomm Research, A*STAR, Singapore","institution_ids":["https://openalex.org/I115228651","https://openalex.org/I3005327000"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029637694","display_name":"Rohan Kumar Das","orcid":"https://orcid.org/0000-0002-1332-3357","observed_orcids":["https://orcid.org/0000-0002-1332-3357"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rohan Kumar Das","raw_affiliation_strings":["Fortemedia Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fortemedia Singapore, Singapore","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004287909","display_name":"Kong Aik Lee","orcid":"https://orcid.org/0000-0001-9133-3000","observed_orcids":["https://orcid.org/0000-0001-9133-3000"]},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Kong Aik Lee","raw_affiliation_strings":["A*STAR,Institute for Infocomm Research,Singapore","Institute for Infocomm Research, A*STAR, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"A*STAR,Institute for Infocomm Research,Singapore","institution_ids":["https://openalex.org/I115228651","https://openalex.org/I3005327000"]},{"raw_affiliation_string":"Institute for Infocomm Research, A*STAR, Singapore","institution_ids":["https://openalex.org/I115228651","https://openalex.org/I3005327000"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":"https://orcid.org/0000-0001-9158-9401","observed_orcids":["https://orcid.org/0000-0001-9158-9401"]},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]},{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN","SG"],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":["National University of Singapore,Department of Electrical and Computer Engineering,Singapore","Department of Electrical and Computer Engineering, National University of Singapore, Singapore","The Chinese University of Hong Kong, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore,Department of Electrical and Computer Engineering,Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"The Chinese University of Hong Kong, Shenzhen, China","institution_ids":["https://openalex.org/I4210116924"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":8.8572,"has_fulltext":false,"cited_by_count":79,"citation_normalized_percentile":{"value":0.98538397,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"7517","last_page":"7521"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9990000128746033,"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":0.9990000128746033,"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":0.0005000000237487257,"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/T10828","display_name":"Biometric Identification and Security","score":0.0,"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/text-independent-speaker-verification","display_name":"text-independent speaker verification","score":0.9919999837875366},{"id":"https://openalex.org/keywords/time-delay-neural-networks","display_name":"time-delay neural networks","score":0.972000002861023},{"id":"https://openalex.org/keywords/short-utterances","display_name":"short utterances","score":0.9110000133514404},{"id":"https://openalex.org/keywords/dual-path-architecture","display_name":"dual-path architecture","score":0.7699999809265137},{"id":"https://openalex.org/keywords/convolutional-neural-networks","display_name":"convolutional neural networks","score":0.8159999847412109},{"id":"https://openalex.org/keywords/parameter-reduction","display_name":"parameter reduction","score":0.6050000190734863},{"id":"https://openalex.org/keywords/voxceleb","display_name":"VoxCeleb","score":0.8289999961853027}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8218994140625},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.7457060813903809},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7130618095397949},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5849494934082031},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.566461443901062},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5394547581672668},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5252323150634766},{"id":"https://openalex.org/C175202392","wikidata":"https://www.wikidata.org/wiki/Q2434543","display_name":"Time delay neural network","level":3,"score":0.47465163469314575},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.41205552220344543},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37865227460861206},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33498215675354004},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.11104393005371094},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08264365792274475}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747021","doi":"https://doi.org/10.1109/icassp43922.2022.9747021","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747021","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320334971","display_name":"Science and Engineering Research Council","ror":"https://ror.org/00zgdb249"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W79762229","https://openalex.org/W2129244720","https://openalex.org/W2406312423","https://openalex.org/W2407080277","https://openalex.org/W2544860310","https://openalex.org/W2612434969","https://openalex.org/W2726515241","https://openalex.org/W2746742816","https://openalex.org/W2748488820","https://openalex.org/W2751695221","https://openalex.org/W2752782242","https://openalex.org/W2784874046","https://openalex.org/W2808631503","https://openalex.org/W2888968865","https://openalex.org/W2928165649","https://openalex.org/W2936774411","https://openalex.org/W2944012040","https://openalex.org/W2972657845","https://openalex.org/W2973003853","https://openalex.org/W3008911072","https://openalex.org/W3013020904","https://openalex.org/W3024869864","https://openalex.org/W3034552520","https://openalex.org/W3095079700","https://openalex.org/W3095678104","https://openalex.org/W3097073596","https://openalex.org/W3097244734","https://openalex.org/W3097741049","https://openalex.org/W3141035251","https://openalex.org/W3142516134","https://openalex.org/W3174649707","https://openalex.org/W4205654098","https://openalex.org/W4225682608","https://openalex.org/W6761176859"],"related_works":["https://openalex.org/W7156359747","https://openalex.org/W4226090390","https://openalex.org/W4411484849","https://openalex.org/W4396982346","https://openalex.org/W3024869864","https://openalex.org/W4416338057","https://openalex.org/W4414392520","https://openalex.org/W2955210370","https://openalex.org/W4400615830","https://openalex.org/W4313219781"],"abstract_inverted_index":{"The":[0],"time":[1],"delay":[2],"neural":[3,12,77],"network":[4,78],"(TDNN)":[5],"represents":[6],"one":[7],"of":[8,11,24,40,74],"the":[9,28,38,83,87,93,109],"state-of-the-art":[10,100],"solutions":[13],"to":[14,26,114],"text-independent":[15],"speaker":[16,29,118],"verification.":[17],"However,":[18],"they":[19],"require":[20],"a":[21,55,68,75],"large":[22],"number":[23],"filters":[25],"capture":[27],"characteristics":[30],"at":[31,64],"any":[32],"local":[33],"frequency":[34],"region.":[35],"In":[36],"addition,":[37],"performance":[39,101],"such":[41],"systems":[42],"may":[43],"degrade":[44],"under":[45],"short":[46,121],"utterance":[47],"scenarios.":[48],"To":[49],"address":[50],"these":[51],"issues,":[52],"we":[53,61],"propose":[54],"multi-scale":[56],"frequency-channel":[57],"attention":[58],"(MFA),":[59],"where":[60],"characterize":[62],"speakers":[63],"different":[65],"scales":[66],"through":[67],"novel":[69],"dual-path":[70],"design":[71],"which":[72],"consists":[73],"convolutional":[76],"and":[79,90,105],"TDNN.":[80],"We":[81],"evaluate":[82],"proposed":[84,94],"MFA":[85,97,110],"on":[86],"VoxCeleb":[88],"database":[89],"observe":[91],"that":[92],"framework":[95],"with":[96,120],"can":[98],"achieve":[99],"while":[102],"reducing":[103],"parameters":[104],"computation":[106],"complexity.":[107],"Further,":[108],"mechanism":[111],"is":[112],"found":[113],"be":[115],"effective":[116],"for":[117],"verification":[119],"test":[122],"utterances.":[123]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":16},{"year":2024,"cited_by_count":31},{"year":2023,"cited_by_count":22},{"year":2022,"cited_by_count":5}],"updated_date":"2026-10-30T12:39:25.321706","created_date":"2022-04-03T00:00:00"}