{"id":"https://openalex.org/W3096084197","doi":"https://doi.org/10.21437/interspeech.2020-1011","title":"Improved RawNet with Feature Map Scaling for Text-Independent Speaker Verification Using Raw Waveforms","display_name":"Improved RawNet with Feature Map Scaling for Text-Independent Speaker Verification Using Raw Waveforms","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3096084197","doi":"https://doi.org/10.21437/interspeech.2020-1011","mag":"3096084197"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-1011","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1011","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","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/A5091834525","display_name":"Jee-weon Jung","orcid":"https://orcid.org/0000-0003-0505-2988"},"institutions":[{"id":"https://openalex.org/I124633538","display_name":"University of Seoul","ror":"https://ror.org/05en5nh73","country_code":"KR","type":"education","lineage":["https://openalex.org/I124633538"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jee-weon Jung","raw_affiliation_strings":["School of Computer Science, University of Seoul, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Seoul, Republic of Korea","institution_ids":["https://openalex.org/I124633538"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028147662","display_name":"Seung-bin Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I124633538","display_name":"University of Seoul","ror":"https://ror.org/05en5nh73","country_code":"KR","type":"education","lineage":["https://openalex.org/I124633538"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seung-bin Kim","raw_affiliation_strings":["School of Computer Science, University of Seoul, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Seoul, Republic of Korea","institution_ids":["https://openalex.org/I124633538"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103211980","display_name":"Hye-jin Shim","orcid":null},"institutions":[{"id":"https://openalex.org/I124633538","display_name":"University of Seoul","ror":"https://ror.org/05en5nh73","country_code":"KR","type":"education","lineage":["https://openalex.org/I124633538"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hye-jin Shim","raw_affiliation_strings":["School of Computer Science, University of Seoul, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Seoul, Republic of Korea","institution_ids":["https://openalex.org/I124633538"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101866564","display_name":"Ju-ho Kim","orcid":"https://orcid.org/0009-0001-4055-4564"},"institutions":[{"id":"https://openalex.org/I124633538","display_name":"University of Seoul","ror":"https://ror.org/05en5nh73","country_code":"KR","type":"education","lineage":["https://openalex.org/I124633538"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Ju-ho Kim","raw_affiliation_strings":["School of Computer Science, University of Seoul, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Seoul, Republic of Korea","institution_ids":["https://openalex.org/I124633538"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030475312","display_name":"Ha-Jin Yu","orcid":"https://orcid.org/0000-0003-3657-0665"},"institutions":[{"id":"https://openalex.org/I124633538","display_name":"University of Seoul","ror":"https://ror.org/05en5nh73","country_code":"KR","type":"education","lineage":["https://openalex.org/I124633538"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Ha-Jin Yu","raw_affiliation_strings":["School of Computer Science, University of Seoul, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Seoul, Republic of Korea","institution_ids":["https://openalex.org/I124633538"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5030475312"],"corresponding_institution_ids":["https://openalex.org/I124633538"],"apc_list":null,"apc_paid":null,"fwci":7.8106,"has_fulltext":false,"cited_by_count":93,"citation_normalized_percentile":{"value":0.97892782,"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":"1496","last_page":"1500"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991000294685364,"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":0.9991000294685364,"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":0.9915000200271606,"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":0.9754999876022339,"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":0.7879742383956909},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.7693785429000854},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6374020576477051},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.6230946779251099},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.617689847946167},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5809876322746277},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4896741211414337},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46750888228416443},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4535069465637207},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.4402746558189392},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.35922956466674805},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09147748351097107},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.06862989068031311}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7879742383956909},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.7693785429000854},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6374020576477051},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.6230946779251099},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.617689847946167},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5809876322746277},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4896741211414337},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46750888228416443},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4535069465637207},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.4402746558189392},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.35922956466674805},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09147748351097107},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.06862989068031311},{"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/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2020-1011","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1011","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W2046056978","https://openalex.org/W2133564696","https://openalex.org/W2302255633","https://openalex.org/W2327501763","https://openalex.org/W2520774990","https://openalex.org/W2726515241","https://openalex.org/W2770454110","https://openalex.org/W2785523195","https://openalex.org/W2794506738","https://openalex.org/W2808631503","https://openalex.org/W2884585870","https://openalex.org/W2889151164","https://openalex.org/W2889519245","https://openalex.org/W2890964092","https://openalex.org/W2916104401","https://openalex.org/W2951758756","https://openalex.org/W2963865582","https://openalex.org/W2964052309","https://openalex.org/W2972369255","https://openalex.org/W2972894903","https://openalex.org/W2972909277","https://openalex.org/W2973149080","https://openalex.org/W2981087920","https://openalex.org/W2999547272","https://openalex.org/W4289547844","https://openalex.org/W4289750118","https://openalex.org/W4295312788","https://openalex.org/W4309845474","https://openalex.org/W4385245566","https://openalex.org/W4394666973"],"related_works":["https://openalex.org/W1521299571","https://openalex.org/W3096066489","https://openalex.org/W3141593045","https://openalex.org/W2134501921","https://openalex.org/W3048257020","https://openalex.org/W204267554","https://openalex.org/W2147062549","https://openalex.org/W215245425","https://openalex.org/W4252590334","https://openalex.org/W4317103504"],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,72],"deep":[3],"learning":[4],"have":[5],"facilitated":[6],"the":[7,29,68,84,95,100,107,112,115,119,124,132,139],"design":[8],"of":[9,70,103,114],"speaker":[10,22],"verification":[11],"systems":[12],"that":[13,54],"directly":[14],"input":[15],"raw":[16,25],"waveforms.For":[17],"example,":[18],"RawNet":[19,40],"[1]":[20],"extracts":[21],"embeddings":[23],"from":[24],"waveforms,":[26],"which":[27],"simplifies":[28],"process":[30],"pipeline":[31],"and":[32,118,141],"demonstrates":[33],"competitive":[34],"performance.In":[35],"this":[36],"study,":[37],"we":[38,80,92],"improve":[39],"by":[41,128],"scaling":[42],"feature":[43,75,85],"maps":[44],"using":[45,138],"various":[46],"methods.The":[47],"proposed":[48,116],"mechanism":[49],"utilizes":[50],"a":[51,56,62,73,77],"scale":[52,78,83],"vector":[53,63],"adopts":[55],"sigmoid":[57],"non-linear":[58],"function.It":[59],"refers":[60],"to":[61,67,82,131],"with":[64,99],"dimensionality":[65],"equal":[66,125],"number":[69],"filters":[71],"given":[74],"map.Using":[76],"vector,":[79],"propose":[81],"map":[86],"multiplicatively,":[87],"additively,":[88],"or":[89],"both.In":[90],"addition,":[91],"investigate":[93],"replacing":[94],"first":[96],"convolution":[97],"layer":[98,102],"sinc-convolution":[101],"SincNet.Experiments":[104],"performed":[105],"on":[106],"VoxCeleb1":[108],"evaluation":[109,135],"dataset":[110],"demonstrate":[111],"effectiveness":[113],"methods,":[117],"best":[120],"performing":[121],"system":[122],"reduces":[123],"error":[126],"rate":[127],"half":[129],"compared":[130],"original":[133],"RawNet.Expanded":[134],"results":[136],"obtained":[137],"VoxCeleb1-E":[140],"VoxCeleb-H":[142],"protocols":[143],"marginally":[144],"outperform":[145],"existing":[146],"state-ofthe-art":[147],"systems.":[148]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":22},{"year":2023,"cited_by_count":17},{"year":2022,"cited_by_count":20},{"year":2021,"cited_by_count":15},{"year":2020,"cited_by_count":4}],"updated_date":"2026-03-05T09:29:38.588285","created_date":"2025-10-10T00:00:00"}