{"id":"https://openalex.org/W4312827992","doi":"https://doi.org/10.1109/icpr56361.2022.9956138","title":"ARawNet: A Lightweight Solution for Leveraging Raw Waveforms in Spoof Speech Detection","display_name":"ARawNet: A Lightweight Solution for Leveraging Raw Waveforms in Spoof Speech Detection","publication_year":2022,"publication_date":"2022-08-21","ids":{"openalex":"https://openalex.org/W4312827992","doi":"https://doi.org/10.1109/icpr56361.2022.9956138"},"language":"en","primary_location":{"id":"doi:10.1109/icpr56361.2022.9956138","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr56361.2022.9956138","pdf_url":null,"source":{"id":"https://openalex.org/S4363607731","display_name":"2022 26th International Conference on Pattern Recognition (ICPR)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"2022 26th International Conference on Pattern Recognition (ICPR)","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/A5053454559","display_name":"Zhongwei Teng","orcid":null},"institutions":[{"id":"https://openalex.org/I200719446","display_name":"Vanderbilt University","ror":"https://ror.org/02vm5rt34","country_code":"US","type":"education","lineage":["https://openalex.org/I200719446"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zhongwei Teng","raw_affiliation_strings":["Vanderbilt University,Dept. of Computer Science","Dept. of Computer Science, Vanderbilt University"],"affiliations":[{"raw_affiliation_string":"Vanderbilt University,Dept. of Computer Science","institution_ids":["https://openalex.org/I200719446"]},{"raw_affiliation_string":"Dept. of Computer Science, Vanderbilt University","institution_ids":["https://openalex.org/I200719446"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077880708","display_name":"Quchen Fu","orcid":"https://orcid.org/0000-0002-4996-5335"},"institutions":[{"id":"https://openalex.org/I200719446","display_name":"Vanderbilt University","ror":"https://ror.org/02vm5rt34","country_code":"US","type":"education","lineage":["https://openalex.org/I200719446"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Quchen Fu","raw_affiliation_strings":["Vanderbilt University,Dept. of Computer Science","Dept. of Computer Science, Vanderbilt University"],"affiliations":[{"raw_affiliation_string":"Vanderbilt University,Dept. of Computer Science","institution_ids":["https://openalex.org/I200719446"]},{"raw_affiliation_string":"Dept. of Computer Science, Vanderbilt University","institution_ids":["https://openalex.org/I200719446"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023026501","display_name":"Jules White","orcid":"https://orcid.org/0000-0002-6331-2365"},"institutions":[{"id":"https://openalex.org/I200719446","display_name":"Vanderbilt University","ror":"https://ror.org/02vm5rt34","country_code":"US","type":"education","lineage":["https://openalex.org/I200719446"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jules White","raw_affiliation_strings":["Vanderbilt University,Dept. of Computer Science","Dept. of Computer Science, Vanderbilt University"],"affiliations":[{"raw_affiliation_string":"Vanderbilt University,Dept. of Computer Science","institution_ids":["https://openalex.org/I200719446"]},{"raw_affiliation_string":"Dept. of Computer Science, Vanderbilt University","institution_ids":["https://openalex.org/I200719446"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003384228","display_name":"Maria Powell","orcid":"https://orcid.org/0000-0002-6643-8991"},"institutions":[{"id":"https://openalex.org/I901861585","display_name":"Vanderbilt University Medical Center","ror":"https://ror.org/05dq2gs74","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I4210162197","https://openalex.org/I901861585"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Maria E. Powell","raw_affiliation_strings":["Vanderbilt University Medical Center,Dept. of Otolaryngology–Head and Neck Surgery"],"affiliations":[{"raw_affiliation_string":"Vanderbilt University Medical Center,Dept. of Otolaryngology–Head and Neck Surgery","institution_ids":["https://openalex.org/I901861585"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082548649","display_name":"Douglas C. Schmidt","orcid":"https://orcid.org/0000-0002-7389-4995"},"institutions":[{"id":"https://openalex.org/I200719446","display_name":"Vanderbilt University","ror":"https://ror.org/02vm5rt34","country_code":"US","type":"education","lineage":["https://openalex.org/I200719446"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Douglas C. Schmidt","raw_affiliation_strings":["Vanderbilt University,Dept. of Computer Science","Dept. of Computer Science, Vanderbilt University"],"affiliations":[{"raw_affiliation_string":"Vanderbilt University,Dept. of Computer Science","institution_ids":["https://openalex.org/I200719446"]},{"raw_affiliation_string":"Dept. of Computer Science, Vanderbilt University","institution_ids":["https://openalex.org/I200719446"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5053454559"],"corresponding_institution_ids":["https://openalex.org/I200719446"],"apc_list":null,"apc_paid":null,"fwci":0.2081,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.44173894,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"692","last_page":"698"},"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":0.9998000264167786,"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":0.9990000128746033,"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":0.8743538856506348},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.7280675768852234},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6128875017166138},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6093847751617432},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5883016586303711},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.5828388929367065},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5035340189933777},{"id":"https://openalex.org/keywords/complement","display_name":"Complement (music)","score":0.4906972646713257},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.45514988899230957},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4036157727241516},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34572088718414307},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34544503688812256}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8743538856506348},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.7280675768852234},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6128875017166138},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6093847751617432},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5883016586303711},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.5828388929367065},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5035340189933777},{"id":"https://openalex.org/C112313634","wikidata":"https://www.wikidata.org/wiki/Q7886648","display_name":"Complement (music)","level":5,"score":0.4906972646713257},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.45514988899230957},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4036157727241516},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34572088718414307},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34544503688812256},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C127716648","wikidata":"https://www.wikidata.org/wiki/Q104053","display_name":"Phenotype","level":3,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C188082640","wikidata":"https://www.wikidata.org/wiki/Q1780899","display_name":"Complementation","level":4,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icpr56361.2022.9956138","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr56361.2022.9956138","pdf_url":null,"source":{"id":"https://openalex.org/S4363607731","display_name":"2022 26th International Conference on Pattern Recognition (ICPR)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"2022 26th International Conference on Pattern Recognition (ICPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.550000011920929}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1487641199","https://openalex.org/W2093231248","https://openalex.org/W2168249605","https://openalex.org/W2651834199","https://openalex.org/W2799053639","https://openalex.org/W2804619531","https://openalex.org/W2808706139","https://openalex.org/W2889151164","https://openalex.org/W2890964092","https://openalex.org/W2936802426","https://openalex.org/W2962896155","https://openalex.org/W2963508548","https://openalex.org/W2964052309","https://openalex.org/W2967606780","https://openalex.org/W2972909277","https://openalex.org/W2973049979","https://openalex.org/W3007948068","https://openalex.org/W3024869864","https://openalex.org/W3034794073","https://openalex.org/W3041561163","https://openalex.org/W3161011913","https://openalex.org/W3163596559","https://openalex.org/W3167533889","https://openalex.org/W3196368020","https://openalex.org/W4287372095","https://openalex.org/W6629354409","https://openalex.org/W6752030128","https://openalex.org/W6752888775","https://openalex.org/W6776390925","https://openalex.org/W6789403026"],"related_works":["https://openalex.org/W642007152","https://openalex.org/W2401827384","https://openalex.org/W2355290951","https://openalex.org/W4304187160","https://openalex.org/W2052688117","https://openalex.org/W2552102772","https://openalex.org/W4294771049","https://openalex.org/W1523214805","https://openalex.org/W2168417340","https://openalex.org/W4229451372"],"abstract_inverted_index":{"An":[0],"emerging":[1],"trend":[2],"in":[3,48,63,175],"audio":[4],"processing":[5],"is":[6,114,131],"capturing":[7],"low-level":[8],"speech":[9,27,30,37,69,106],"representations":[10,15],"from":[11,58,101,149],"raw":[12,84,102],"waveforms.":[13],"These":[14],"have":[16],"shown":[17],"promising":[18],"results":[19,57],"on":[20],"a":[21,121,154,178],"variety":[22],"of":[23,79,111,162,168,181],"tasks,":[24,65],"such":[25,66],"as":[26,67],"recognition":[28],"and":[29,83,138,141,145],"separation.":[31],"Compared":[32],"to":[33,94],"handcrafted":[34,71,81,96],"features,":[35],"learning":[36],"features":[38,72,82,97,99],"via":[39],"backpropagation":[40],"can":[41,117,158],"potentially":[42],"provide":[43],"the":[44,112,134,160],"model":[45,93,130],"greater":[46],"flexibility":[47],"how":[49],"it":[50,116],"represents":[51],"data":[52],"for":[53,104,165,177],"different":[54],"tasks.":[55],"However,":[56],"empirical":[59],"studies":[60],"show":[61],"that,":[62],"some":[64],"spoof":[68,105,169],"detection,":[70],"still":[73],"currently":[74],"outperform":[75],"learned":[76,100],"features.":[77],"Instead":[78],"evaluating":[80],"waveforms":[85,103],"independently,":[86],"this":[87,150],"paper":[88],"proposes":[89],"an":[90],"Auxiliary":[91,128],"Rawnet":[92,129],"complement":[95],"with":[98],"detection.":[107],"A":[108],"key":[109],"benefit":[110],"approach":[113],"that":[115,153],"improve":[118],"accuracy":[119],"at":[120],"relatively":[122],"low":[123],"computational":[124,183],"cost.":[125],"The":[126],"proposed":[127],"tested":[132],"using":[133],"ASVspoof":[135],"2019":[136],"dataset":[137,151],"pooled":[139],"EER":[140],"min-tDCF":[142],"are":[143],"1.11%":[144],"0.03645":[146],"respectively.":[147],"Results":[148],"indicate":[152],"lightweight":[155],"waveform":[156],"encoder":[157],"boost":[159],"performance":[161],"handcrafted-features-based":[163],"encoders":[164],"10":[166],"types":[167],"attacks,":[170,174],"including":[171],"3":[172],"challenging":[173],"exchange":[176],"small":[179],"amount":[180],"additional":[182],"work.":[184]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}