{"id":"https://openalex.org/W3092531824","doi":"https://doi.org/10.1109/mmsp48831.2020.9287061","title":"Wavelet Scattering Transform and CNN for Closed Set Speaker Identification","display_name":"Wavelet Scattering Transform and CNN for Closed Set Speaker Identification","publication_year":2020,"publication_date":"2020-09-21","ids":{"openalex":"https://openalex.org/W3092531824","doi":"https://doi.org/10.1109/mmsp48831.2020.9287061","mag":"3092531824"},"language":"en","primary_location":{"id":"doi:10.1109/mmsp48831.2020.9287061","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp48831.2020.9287061","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE 22nd International Workshop on Multimedia Signal Processing (MMSP)","raw_type":"proceedings-article"},"type":"preprint","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/A5003253477","display_name":"Wajdi Ghezaiel","orcid":null},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I194210350","display_name":"\u00c9cole Nationale Sup\u00e9rieure d'Ing\u00e9nieurs de Caen","ror":"https://ror.org/01fpqqe90","country_code":"FR","type":"education","lineage":["https://openalex.org/I194210350","https://openalex.org/I4210105918"]},{"id":"https://openalex.org/I98702875","display_name":"Universit\u00e9 de Caen Normandie","ror":"https://ror.org/051kpcy16","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210105918","https://openalex.org/I98702875"]},{"id":"https://openalex.org/I4210105918","display_name":"Normandie Universit\u00e9","ror":"https://ror.org/01k40cz91","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210105918"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Wajdi GHEZAIEL","raw_affiliation_strings":["ENSICAEN, UNICAEN CNRS NormaSTIC, Normandie Univ, Caen, France"],"affiliations":[{"raw_affiliation_string":"ENSICAEN, UNICAEN CNRS NormaSTIC, Normandie Univ, Caen, France","institution_ids":["https://openalex.org/I98702875","https://openalex.org/I194210350","https://openalex.org/I4210105918","https://openalex.org/I1294671590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067287623","display_name":"Luc Brun","orcid":"https://orcid.org/0000-0002-1658-0527"},"institutions":[{"id":"https://openalex.org/I98702875","display_name":"Universit\u00e9 de Caen Normandie","ror":"https://ror.org/051kpcy16","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210105918","https://openalex.org/I98702875"]},{"id":"https://openalex.org/I4210105918","display_name":"Normandie Universit\u00e9","ror":"https://ror.org/01k40cz91","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210105918"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I194210350","display_name":"\u00c9cole Nationale Sup\u00e9rieure d'Ing\u00e9nieurs de Caen","ror":"https://ror.org/01fpqqe90","country_code":"FR","type":"education","lineage":["https://openalex.org/I194210350","https://openalex.org/I4210105918"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Luc BRUN","raw_affiliation_strings":["ENSICAEN, UNICAEN CNRS Greyc, Normandie Univ, Caen, France"],"affiliations":[{"raw_affiliation_string":"ENSICAEN, UNICAEN CNRS Greyc, Normandie Univ, Caen, France","institution_ids":["https://openalex.org/I98702875","https://openalex.org/I194210350","https://openalex.org/I4210105918","https://openalex.org/I1294671590"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062753174","display_name":"Olivier L\u00e9zoray","orcid":"https://orcid.org/0000-0003-0540-543X"},"institutions":[{"id":"https://openalex.org/I98702875","display_name":"Universit\u00e9 de Caen Normandie","ror":"https://ror.org/051kpcy16","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210105918","https://openalex.org/I98702875"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210105918","display_name":"Normandie Universit\u00e9","ror":"https://ror.org/01k40cz91","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210105918"]},{"id":"https://openalex.org/I194210350","display_name":"\u00c9cole Nationale Sup\u00e9rieure d'Ing\u00e9nieurs de Caen","ror":"https://ror.org/01fpqqe90","country_code":"FR","type":"education","lineage":["https://openalex.org/I194210350","https://openalex.org/I4210105918"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Olivier LEZORAY","raw_affiliation_strings":["ENSICAEN, UNICAEN CNRS Greyc, Normandie Univ, Caen, France"],"affiliations":[{"raw_affiliation_string":"ENSICAEN, UNICAEN CNRS Greyc, Normandie Univ, Caen, France","institution_ids":["https://openalex.org/I98702875","https://openalex.org/I194210350","https://openalex.org/I4210105918","https://openalex.org/I1294671590"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5003253477"],"corresponding_institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I194210350","https://openalex.org/I98702875","https://openalex.org/I4210105918"],"apc_list":null,"apc_paid":null,"fwci":1.90917413,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.87846944,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"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":0.9991999864578247,"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":0.9950000047683716,"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":0.7861120700836182},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6672675609588623},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6269803643226624},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.5913208723068237},{"id":"https://openalex.org/keywords/wavelet-transform","display_name":"Wavelet transform","score":0.5867881178855896},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5818887948989868},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5754663944244385},{"id":"https://openalex.org/keywords/wavelet","display_name":"Wavelet","score":0.562957763671875},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5555242300033569},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5194153785705566},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4873986840248108},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.4864673316478729},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.4276726245880127},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.427243173122406}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7861120700836182},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6672675609588623},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6269803643226624},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.5913208723068237},{"id":"https://openalex.org/C196216189","wikidata":"https://www.wikidata.org/wiki/Q2867","display_name":"Wavelet transform","level":3,"score":0.5867881178855896},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5818887948989868},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5754663944244385},{"id":"https://openalex.org/C47432892","wikidata":"https://www.wikidata.org/wiki/Q831390","display_name":"Wavelet","level":2,"score":0.562957763671875},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5555242300033569},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5194153785705566},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4873986840248108},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.4864673316478729},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.4276726245880127},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.427243173122406},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mmsp48831.2020.9287061","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp48831.2020.9287061","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE 22nd International Workshop on Multimedia Signal Processing (MMSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5199999809265137,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320307804","display_name":"BP","ror":"https://ror.org/051659894"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W67277430","https://openalex.org/W128628490","https://openalex.org/W1494198834","https://openalex.org/W1538131130","https://openalex.org/W1748509159","https://openalex.org/W1946791388","https://openalex.org/W1994906459","https://openalex.org/W1995562189","https://openalex.org/W2041823554","https://openalex.org/W2046056978","https://openalex.org/W2059511347","https://openalex.org/W2072072671","https://openalex.org/W2093231248","https://openalex.org/W2117130368","https://openalex.org/W2121812409","https://openalex.org/W2150769028","https://openalex.org/W2154833897","https://openalex.org/W2163605009","https://openalex.org/W2183016404","https://openalex.org/W2400549570","https://openalex.org/W2603142085","https://openalex.org/W2726515241","https://openalex.org/W2760938034","https://openalex.org/W2770454110","https://openalex.org/W2802973008","https://openalex.org/W2885329609","https://openalex.org/W2890964092","https://openalex.org/W2963888223","https://openalex.org/W2964052309","https://openalex.org/W6605273041","https://openalex.org/W6632100814","https://openalex.org/W6637723767","https://openalex.org/W6662018943","https://openalex.org/W6684191040","https://openalex.org/W6754496211"],"related_works":["https://openalex.org/W3204184292","https://openalex.org/W3176564347","https://openalex.org/W1985458517","https://openalex.org/W2355833770","https://openalex.org/W3031039437","https://openalex.org/W3095877357","https://openalex.org/W183202219","https://openalex.org/W10861731","https://openalex.org/W2072565696","https://openalex.org/W2077021924"],"abstract_inverted_index":{"In":[0],"real":[1],"world":[2],"applications,":[3],"the":[4,13,17,20,91,100],"performances":[5],"of":[6,15,22,53,58,90,94,136],"speaker":[7,32,79,129],"identification":[8,33],"systems":[9],"degrade":[10],"due":[11],"to":[12],"reduction":[14],"both":[16],"amount":[18,52],"and":[19,98,119],"quality":[21],"speech":[23],"utterance.":[24],"For":[25],"that":[26,111],"particular":[27],"purpose,":[28],"we":[29,66],"propose":[30,67],"a":[31,49,56,68,87,95,104,128,133],"system":[34],"where":[35],"short":[36,137],"utterances":[37],"with":[38,132],"few":[39],"training":[40,139],"examples":[41],"are":[42],"used":[43],"for":[44,77,127],"person":[45],"identification.":[46,80],"Therefore,":[47],"only":[48],"very":[50],"small":[51,134],"data":[54],"involving":[55],"sentence":[57],"2-4":[59],"seconds":[60],"is":[61],"used.":[62],"To":[63],"achieve":[64],"this,":[65],"novel":[69],"raw":[70],"waveform":[71],"end-to-end":[72],"convolutional":[73],"neural":[74],"network":[75],"(CNN)":[76],"text-independent":[78],"We":[81],"use":[82],"wavelet":[83,116],"scattering":[84,117],"transform":[85,118],"as":[86],"fixed":[88],"initialization":[89],"first":[92],"layers":[93,102],"CNN":[96,120],"network,":[97],"learn":[99],"remaining":[101],"in":[103],"supervised":[105],"manner.":[106],"The":[107],"conducted":[108],"experiments":[109],"show":[110],"our":[112],"hybrid":[113],"architecture":[114],"combining":[115],"can":[121],"successfully":[122],"perform":[123],"efficient":[124],"feature":[125],"extraction":[126],"identification,":[130],"even":[131],"number":[135],"duration":[138],"samples.":[140]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}