{"id":"https://openalex.org/W2770454110","doi":"https://doi.org/10.1109/icassp.2018.8462165","title":"Towards Directly Modeling Raw Speech Signal for Speaker Verification Using CNNS","display_name":"Towards Directly Modeling Raw Speech Signal for Speaker Verification Using CNNS","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2770454110","doi":"https://doi.org/10.1109/icassp.2018.8462165","mag":"2770454110"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8462165","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462165","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://infoscience.epfl.ch/record/232478","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047091215","display_name":"Hannah Muckenhirn","orcid":null},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Hannah Muckenhirn","raw_affiliation_strings":["Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne, Lausanne, Switzerland"],"affiliations":[{"raw_affiliation_string":"Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne, Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043551083","display_name":"Mathew Magimai.-Doss","orcid":"https://orcid.org/0000-0002-8714-1409"},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Mathew Magimai.-Doss","raw_affiliation_strings":["Idiap Research Institute, Martigny, Switzerland"],"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024068031","display_name":"Sebastien Marcell","orcid":null},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Sebastien Marcell","raw_affiliation_strings":["Idiap Research Institute, Martigny, Switzerland"],"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5047091215"],"corresponding_institution_ids":["https://openalex.org/I5124864"],"apc_list":null,"apc_paid":null,"fwci":13.7079,"has_fulltext":false,"cited_by_count":130,"citation_normalized_percentile":{"value":0.98932893,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"4884","last_page":"4888"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9965000152587891,"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/speech-recognition","display_name":"Speech recognition","score":0.8086541891098022},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.808099627494812},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.7647943496704102},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6546677350997925},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.5550833940505981},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5510490536689758},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5376632809638977},{"id":"https://openalex.org/keywords/spoofing-attack","display_name":"Spoofing attack","score":0.45448634028434753},{"id":"https://openalex.org/keywords/filter-bank","display_name":"Filter bank","score":0.4464091658592224},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4403442144393921},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4155801236629486},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.41356873512268066},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4071660339832306},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.33619827032089233},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3242897391319275}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8086541891098022},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.808099627494812},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.7647943496704102},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6546677350997925},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.5550833940505981},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5510490536689758},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5376632809638977},{"id":"https://openalex.org/C167900197","wikidata":"https://www.wikidata.org/wiki/Q11081100","display_name":"Spoofing attack","level":2,"score":0.45448634028434753},{"id":"https://openalex.org/C100515483","wikidata":"https://www.wikidata.org/wiki/Q3268235","display_name":"Filter bank","level":3,"score":0.4464091658592224},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4403442144393921},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4155801236629486},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.41356873512268066},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4071660339832306},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.33619827032089233},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3242897391319275},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp.2018.8462165","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462165","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:infoscience.epfl.ch:232478","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/232478","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"pmh:oai:infoscience.epfl.ch:256305","is_oa":true,"landing_page_url":"http://publications.idiap.ch/index.php/publications/showcite/Muckenhirn_Idiap-RR-30-2017","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://infoscience.epfl.ch/record/256305","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:infoscience.epfl.ch:232478","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/232478","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.6899999976158142}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W23669922","https://openalex.org/W753012316","https://openalex.org/W1666984270","https://openalex.org/W1999405202","https://openalex.org/W2041823554","https://openalex.org/W2046056978","https://openalex.org/W2049586080","https://openalex.org/W2107638917","https://openalex.org/W2114925438","https://openalex.org/W2121812409","https://openalex.org/W2122702209","https://openalex.org/W2123811694","https://openalex.org/W2134689131","https://openalex.org/W2147147599","https://openalex.org/W2150769028","https://openalex.org/W2161964681","https://openalex.org/W2172179449","https://openalex.org/W2261689926","https://openalex.org/W2398826216","https://openalex.org/W2399733683","https://openalex.org/W2408093180","https://openalex.org/W2513345070","https://openalex.org/W2592641653","https://openalex.org/W2726515241","https://openalex.org/W2738359832","https://openalex.org/W2747238065","https://openalex.org/W2963175699","https://openalex.org/W3106050203","https://openalex.org/W4322615131","https://openalex.org/W6622239757","https://openalex.org/W6637061625","https://openalex.org/W6677390740","https://openalex.org/W6678535692","https://openalex.org/W6679730647","https://openalex.org/W6724411756"],"related_works":["https://openalex.org/W2547760228","https://openalex.org/W2836844603","https://openalex.org/W3173366380","https://openalex.org/W2766680336","https://openalex.org/W2133320490","https://openalex.org/W4289830142","https://openalex.org/W3150393935","https://openalex.org/W1497065097","https://openalex.org/W1963976507","https://openalex.org/W2980055100"],"abstract_inverted_index":{"Speaker":[0],"verification":[1,48,87,102],"systems":[2,149],"traditionally":[3],"extract":[4],"and":[5,42,77,89,119,133,179],"model":[6,29,183],"cepstral":[7],"features":[8],"or":[9],"filter":[10],"bank":[11],"energies":[12],"from":[13,57],"the":[14,22,58,85,100,106,110,121,131,140,157,160,166,188],"speech":[15,32,38,59,75,129,135,189],"signal.":[16],"In":[17],"this":[18,145],"paper,":[19],"inspired":[20],"by":[21,104,114],"success":[23],"of":[24,109,130,156],"neural":[25],"network-based":[26],"approaches":[27],"to":[28,79,84,151,170,182],"directly":[30,55],"raw":[31,74],"signal":[33,60,76,190],"for":[34,96,191],"applications":[35],"such":[36],"as":[37,72],"recognition,":[39],"emotion":[40],"recognition":[41],"anti-spoofing,":[43],"we":[44],"propose":[45],"a":[46,65,93,124],"speaker":[47,51,67,86,94,98,101,111,132,192],"approach":[49,146],"where":[50],"discriminative":[52,125],"information":[53,171,186],"is":[54],"learned":[56],"by:":[61],"(a)":[62],"first":[63,161],"training":[64],"CNN-based":[66],"identification":[68,112],"system":[69,103,113,122],"that":[70,144,165],"takes":[71],"input":[73],"learns":[78],"classify":[80],"on":[81,139],"speakers":[82],"(unknown":[83],"system);":[88],"then":[90],"(b)":[91],"building":[92],"detector":[95],"each":[97],"in":[99,123,159,172,187],"replacing":[105],"output":[107],"layer":[108,163],"two":[115],"outputs":[116],"(genuine,":[117],"impostor),":[118],"adapting":[120],"manner":[126],"with":[127],"enrollment":[128],"impostor":[134],"data.":[136],"Our":[137],"investigations":[138],"Voxforge":[141],"database":[142],"shows":[143,164],"can":[147],"yield":[148],"competitive":[150],"state-of-the-art":[152],"systems.":[153],"An":[154],"analysis":[155],"filters":[158,167],"convolution":[162],"give":[168],"emphasis":[169],"low":[173],"frequency":[174,185],"regions":[175],"(below":[176],"1000":[177],"Hz)":[178],"implicitly":[180],"learn":[181],"fundamental":[184],"discrimination.":[193]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":15},{"year":2022,"cited_by_count":17},{"year":2021,"cited_by_count":21},{"year":2020,"cited_by_count":30},{"year":2019,"cited_by_count":17},{"year":2018,"cited_by_count":13}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}