{"id":"https://openalex.org/W4401609309","doi":"https://doi.org/10.1109/icasspw62465.2024.10627424","title":"A Lightweight Dual-Stage Framework for Personalized Speech Enhancement Based on Deepfilternet2","display_name":"A Lightweight Dual-Stage Framework for Personalized Speech Enhancement Based on Deepfilternet2","publication_year":2024,"publication_date":"2024-04-14","ids":{"openalex":"https://openalex.org/W4401609309","doi":"https://doi.org/10.1109/icasspw62465.2024.10627424"},"language":"en","primary_location":{"id":"doi:10.1109/icasspw62465.2024.10627424","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw62465.2024.10627424","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://telecom-paris.hal.science/hal-04541350/document","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018626055","display_name":"T. Serre","orcid":"https://orcid.org/0000-0003-0846-0039"},"institutions":[{"id":"https://openalex.org/I4210121626","display_name":"Signal Processing (United States)","ror":"https://ror.org/021gzyw51","country_code":"US","type":"company","lineage":["https://openalex.org/I4210121626"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Thomas Serre","raw_affiliation_strings":["Orosound, Signal Processing Lab"],"affiliations":[{"raw_affiliation_string":"Orosound, Signal Processing Lab","institution_ids":["https://openalex.org/I4210121626"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082784886","display_name":"Mathieu Fontaine","orcid":"https://orcid.org/0000-0002-7657-6271"},"institutions":[{"id":"https://openalex.org/I4210121626","display_name":"Signal Processing (United States)","ror":"https://ror.org/021gzyw51","country_code":"US","type":"company","lineage":["https://openalex.org/I4210121626"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mathieu Fontaine","raw_affiliation_strings":["Orosound, Signal Processing Lab"],"affiliations":[{"raw_affiliation_string":"Orosound, Signal Processing Lab","institution_ids":["https://openalex.org/I4210121626"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033795981","display_name":"\u00c9ric Benhaim","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165912","display_name":"Laboratoire Traitement et Communication de l\u2019Information","ror":"https://ror.org/057er4c39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I12356871","https://openalex.org/I4210145102","https://openalex.org/I4210145102","https://openalex.org/I4210165912"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"\u00c9ric Benhaim","raw_affiliation_strings":["Institut Polytechnique de Paris,LTCI, Télécom Paris"],"affiliations":[{"raw_affiliation_string":"Institut Polytechnique de Paris,LTCI, Télécom Paris","institution_ids":["https://openalex.org/I4210165912"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5095699420","display_name":"Geoffroy Dutour","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165912","display_name":"Laboratoire Traitement et Communication de l\u2019Information","ror":"https://ror.org/057er4c39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I12356871","https://openalex.org/I4210145102","https://openalex.org/I4210145102","https://openalex.org/I4210165912"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Geoffroy Dutour","raw_affiliation_strings":["Institut Polytechnique de Paris,LTCI, Télécom Paris"],"affiliations":[{"raw_affiliation_string":"Institut Polytechnique de Paris,LTCI, Télécom Paris","institution_ids":["https://openalex.org/I4210165912"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060031161","display_name":"Slim Essid","orcid":"https://orcid.org/0000-0002-0028-327X"},"institutions":[{"id":"https://openalex.org/I4210121626","display_name":"Signal Processing (United States)","ror":"https://ror.org/021gzyw51","country_code":"US","type":"company","lineage":["https://openalex.org/I4210121626"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Slim Essid","raw_affiliation_strings":["Orosound, Signal Processing Lab"],"affiliations":[{"raw_affiliation_string":"Orosound, Signal Processing Lab","institution_ids":["https://openalex.org/I4210121626"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5018626055"],"corresponding_institution_ids":["https://openalex.org/I4210121626"],"apc_list":null,"apc_paid":null,"fwci":0.366,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.5466413,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"780","last_page":"784"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech 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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech 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"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9764999747276306,"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/T13289","display_name":"Infant Health and Development","score":0.9186999797821045,"subfield":{"id":"https://openalex.org/subfields/3611","display_name":"Pharmacy"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6680847406387329},{"id":"https://openalex.org/keywords/stage","display_name":"Stage (stratigraphy)","score":0.6059989929199219},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5938323736190796},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.5698395371437073},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3272291421890259},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.195465087890625},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.06151682138442993}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6680847406387329},{"id":"https://openalex.org/C146357865","wikidata":"https://www.wikidata.org/wiki/Q1123245","display_name":"Stage (stratigraphy)","level":2,"score":0.6059989929199219},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5938323736190796},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.5698395371437073},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3272291421890259},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.195465087890625},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.06151682138442993},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icasspw62465.2024.10627424","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw62465.2024.10627424","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-04541350v1","is_oa":true,"landing_page_url":"https://telecom-paris.hal.science/hal-04541350","pdf_url":"https://telecom-paris.hal.science/hal-04541350/document","source":{"id":"https://openalex.org/S4406922461","display_name":"SPIRE - Sciences Po Institutional REpository","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":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ICASSP, Apr 2024, Seoul (Korea), South Korea. ⟨10.1109/ICASSPW62465.2024.10627424⟩","raw_type":"Conference papers"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-04541350v1","is_oa":true,"landing_page_url":"https://telecom-paris.hal.science/hal-04541350","pdf_url":"https://telecom-paris.hal.science/hal-04541350/document","source":{"id":"https://openalex.org/S4406922461","display_name":"SPIRE - Sciences Po Institutional REpository","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":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ICASSP, Apr 2024, Seoul (Korea), South Korea. ⟨10.1109/ICASSPW62465.2024.10627424⟩","raw_type":"Conference papers"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4401609309.pdf"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W2890964092","https://openalex.org/W2939771864","https://openalex.org/W2951130829","https://openalex.org/W2973062255","https://openalex.org/W3015306128","https://openalex.org/W3016361963","https://openalex.org/W3024869864","https://openalex.org/W3030437843","https://openalex.org/W3096090308","https://openalex.org/W3097653961","https://openalex.org/W3103434036","https://openalex.org/W3161140524","https://openalex.org/W3161480375","https://openalex.org/W3162534564","https://openalex.org/W3198543387","https://openalex.org/W3206706278","https://openalex.org/W3213188934","https://openalex.org/W4224919629","https://openalex.org/W4226185896","https://openalex.org/W4312570973","https://openalex.org/W4372346771","https://openalex.org/W4372349226","https://openalex.org/W4392908343","https://openalex.org/W6771467084"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W3096184950","https://openalex.org/W4231424160","https://openalex.org/W2275432853"],"abstract_inverted_index":{"Isolating":[0],"the":[1,30,92,98,101,105,131],"desired":[2],"speaker\u2019s":[3,31],"voice":[4],"amidst":[5],"multiple":[6],"speakers":[7],"in":[8],"a":[9,14,58,63,75,112,120],"noisy":[10],"acoustic":[11],"context":[12],"is":[13],"challenging":[15],"task.":[16,122],"Personalized":[17],"speech":[18],"enhancement":[19,107],"(PSE)":[20],"endeavours":[21],"to":[22,61,119],"achieve":[23],"this":[24,54],"by":[25,44],"leveraging":[26],"prior":[27],"knowledge":[28],"of":[29,88,100,133],"voice.":[32],"Recent":[33],"research":[34],"efforts":[35],"have":[36],"yielded":[37],"promising":[38],"PSE":[39,121],"models,":[40],"albeit":[41],"often":[42],"accompanied":[43],"computationally":[45],"intensive":[46],"architectures,":[47],"unsuitable":[48],"for":[49,79,97],"resource-constrained":[50],"embedded":[51],"devices.":[52],"In":[53],"paper,":[55],"we":[56],"introduce":[57],"novel":[59],"method":[60,128],"personalize":[62],"lightweight":[64],"dual-stage":[65,106],"Speech":[66],"Enhancement":[67],"(SE)":[68],"model":[69,77],"and":[70],"implement":[71],"it":[72],"within":[73,91,104],"DeepFilterNet2,":[74],"SE":[76],"renowned":[78],"its":[80],"state-of-the-art":[81],"performance.":[82],"We":[83,109,123],"seek":[84],"an":[85],"optimal":[86],"integration":[87,99],"speaker":[89,102],"information":[90],"model,":[93],"exploring":[94],"different":[95],"positions":[96],"embeddings":[103],"architecture.":[108],"also":[110],"investigate":[111],"tailored":[113],"training":[114],"strategy":[115],"when":[116],"adapting":[117],"DeepFilterNet2":[118,134],"show":[124],"that":[125],"our":[126],"personalization":[127],"greatly":[129],"improves":[130],"performances":[132],"while":[135],"preserving":[136],"minimal":[137],"computational":[138],"overhead.":[139]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-11T14:59:36.786465","created_date":"2025-10-10T00:00:00"}