{"id":"https://openalex.org/W4388820470","doi":"https://doi.org/10.1109/apsipaasc58517.2023.10317476","title":"Modeling Suprasegmental Information Using Finite Difference Network for End-to-End Speaker Verification","display_name":"Modeling Suprasegmental Information Using Finite Difference Network for End-to-End Speaker Verification","publication_year":2023,"publication_date":"2023-10-31","ids":{"openalex":"https://openalex.org/W4388820470","doi":"https://doi.org/10.1109/apsipaasc58517.2023.10317476"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc58517.2023.10317476","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/apsipaasc58517.2023.10317476","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5101470389","display_name":"Jin Li","orcid":"https://orcid.org/0009-0006-2316-9169"},"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":"Jin Li","raw_affiliation_strings":["The Hong Kong Polytechnic University,Dept. of Electronic and Information Engineering,Hong Kong SAR,China","Dept. of Electronic and Information Engineering, The Hong Kong Polytechnic University, Hong Kong SAR, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University,Dept. of Electronic and Information Engineering,Hong Kong SAR,China","institution_ids":["https://openalex.org/I14243506"]},{"raw_affiliation_string":"Dept. of Electronic and Information Engineering, The Hong Kong Polytechnic University, Hong Kong SAR, China","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","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,Dept. of Electronic and Information Engineering,Hong Kong SAR,China","Dept. of Electronic and Information Engineering, The Hong Kong Polytechnic University, Hong Kong SAR, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University,Dept. of Electronic and Information Engineering,Hong Kong SAR,China","institution_ids":["https://openalex.org/I14243506"]},{"raw_affiliation_string":"Dept. of Electronic and Information Engineering, The Hong Kong Polytechnic University, Hong Kong SAR, China","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062053942","display_name":"Nan Yan","orcid":"https://orcid.org/0000-0002-1613-9301"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nan Yan","raw_affiliation_strings":["Shenzhen Institute of Advanced Technology,Chinese Academy of Sciences,Shenzhen,China","Chinese Academy of Sciences, Shenzhen Institute of Advanced Technology, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Institute of Advanced Technology,Chinese Academy of Sciences,Shenzhen,China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]},{"raw_affiliation_string":"Chinese Academy of Sciences, Shenzhen Institute of Advanced Technology, Shenzhen, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100363663","display_name":"Lan Wang","orcid":"https://orcid.org/0000-0003-0506-1606"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lan Wang","raw_affiliation_strings":["Shenzhen Institute of Advanced Technology,Chinese Academy of Sciences,Shenzhen,China","Chinese Academy of Sciences, Shenzhen Institute of Advanced Technology, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Institute of Advanced Technology,Chinese Academy of Sciences,Shenzhen,China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]},{"raw_affiliation_string":"Chinese Academy of Sciences, Shenzhen Institute of Advanced Technology, Shenzhen, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"119","last_page":"124"},"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":0.9991000294685364,"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":0.9962000250816345,"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":0.7730770111083984},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.6485235095024109},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.6300029158592224},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.6130428910255432},{"id":"https://openalex.org/keywords/front-and-back-ends","display_name":"Front and back ends","score":0.5538917779922485},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5239073038101196},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4900728464126587},{"id":"https://openalex.org/keywords/pitch-accent","display_name":"Pitch accent","score":0.47718489170074463},{"id":"https://openalex.org/keywords/intonation","display_name":"Intonation (linguistics)","score":0.45547178387641907},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42195001244544983},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.3537401258945465},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33221668004989624},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.11467248201370239}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7730770111083984},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6485235095024109},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.6300029158592224},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.6130428910255432},{"id":"https://openalex.org/C53016008","wikidata":"https://www.wikidata.org/wiki/Q620167","display_name":"Front and back ends","level":2,"score":0.5538917779922485},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5239073038101196},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4900728464126587},{"id":"https://openalex.org/C2777672088","wikidata":"https://www.wikidata.org/wiki/Q1441804","display_name":"Pitch accent","level":3,"score":0.47718489170074463},{"id":"https://openalex.org/C2781045179","wikidata":"https://www.wikidata.org/wiki/Q5576720","display_name":"Intonation (linguistics)","level":2,"score":0.45547178387641907},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42195001244544983},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.3537401258945465},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33221668004989624},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11467248201370239},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc58517.2023.10317476","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/apsipaasc58517.2023.10317476","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"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":35,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1978714678","https://openalex.org/W2079282303","https://openalex.org/W2108636611","https://openalex.org/W2109622017","https://openalex.org/W2117678320","https://openalex.org/W2123107571","https://openalex.org/W2174564468","https://openalex.org/W2219249508","https://openalex.org/W2726515241","https://openalex.org/W2770454110","https://openalex.org/W2808631503","https://openalex.org/W2884643232","https://openalex.org/W2890964092","https://openalex.org/W2916104401","https://openalex.org/W2922937143","https://openalex.org/W2964052309","https://openalex.org/W2969985801","https://openalex.org/W2972909277","https://openalex.org/W2973049979","https://openalex.org/W3004940340","https://openalex.org/W3024869864","https://openalex.org/W3094735979","https://openalex.org/W3096084197","https://openalex.org/W3097435397","https://openalex.org/W3167533889","https://openalex.org/W3197716055","https://openalex.org/W3197940657","https://openalex.org/W3204977014","https://openalex.org/W4224916701","https://openalex.org/W4256451564","https://openalex.org/W4297841773","https://openalex.org/W6631190155","https://openalex.org/W6685293847","https://openalex.org/W6688816777"],"related_works":["https://openalex.org/W1965454423","https://openalex.org/W2028501571","https://openalex.org/W2052542215","https://openalex.org/W2036564641","https://openalex.org/W2476379844","https://openalex.org/W2743005163","https://openalex.org/W2478962818","https://openalex.org/W646712735","https://openalex.org/W2381837697","https://openalex.org/W2737178166"],"abstract_inverted_index":{"In":[0],"recent":[1],"years,":[2],"using":[3],"raw":[4],"waveforms":[5],"as":[6,50],"input":[7],"to":[8,44,132],"deep":[9],"networks":[10],"has":[11],"been":[12],"widely":[13],"explored":[14],"for":[15,136],"speaker":[16,138],"verification":[17],"systems":[18],"that":[19,35,56,68,107],"process":[20],"speech":[21],"signals":[22],"at":[23],"the":[24,36,46,51,71,77,87,103,115,129],"segmental":[25,72,109],"level.":[26],"A":[27],"critical":[28],"issue":[29],"of":[30,91,117],"such":[31,49],"an":[32,118],"approach":[33],"is":[34,84,128],"front-end":[37],"network":[38],"with":[39],"a":[40,65],"small":[41],"kernel":[42],"fails":[43],"capture":[45,70],"suprasegmental":[47,74,82,94,111,134],"information,":[48],"intonation":[52],"patterns":[53],"and":[54,73,110],"prosody":[55],"span":[57],"longer":[58],"than":[59],"one":[60],"second.":[61],"This":[62],"paper":[63],"proposes":[64],"novel":[66],"framework":[67],"can":[69,113],"information":[75,83,135],"after":[76],"first":[78,130],"convolutional":[79],"layer.":[80],"Concretely,":[81],"obtained":[85],"from":[86],"first-order":[88],"finite":[89],"difference":[90],"two":[92],"consecutive":[93],"envelopes":[95],"estimated":[96],"by":[97,121],"Hilbert":[98],"transforms.":[99],"Experimental":[100],"evaluations":[101],"on":[102],"Voxceleb":[104],"dataset":[105],"show":[106],"combining":[108],"features":[112],"reduce":[114],"EER":[116],"end-to-end":[119,137],"system":[120],"27%.":[122],"To":[123],"our":[124],"best":[125],"knowledge,":[126],"this":[127],"attempt":[131],"incorporate":[133],"verification.":[139]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}
