{"id":"https://openalex.org/W4280569506","doi":"https://doi.org/10.1109/slt54892.2023.10022350","title":"Joint Optimization of Diffusion Probabilistic-Based Multichannel Speech Enhancement with Far-Field Speaker Verification","display_name":"Joint Optimization of Diffusion Probabilistic-Based Multichannel Speech Enhancement with Far-Field Speaker Verification","publication_year":2023,"publication_date":"2023-01-09","ids":{"openalex":"https://openalex.org/W4280569506","doi":"https://doi.org/10.1109/slt54892.2023.10022350"},"language":"en","primary_location":{"id":"doi:10.1109/slt54892.2023.10022350","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10022350","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","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 IEEE Spoken Language Technology Workshop (SLT)","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/A5048477278","display_name":"Sandipana Dowerah","orcid":"https://orcid.org/0000-0002-1559-4505"},"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/I90183372","display_name":"Universit\u00e9 de Lorraine","ror":"https://ror.org/04vfs2w97","country_code":"FR","type":"education","lineage":["https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Sandipana Dowerah","raw_affiliation_strings":["Université de Lorraine, CNRS,Nancy,France,F-54000"],"affiliations":[{"raw_affiliation_string":"Université de Lorraine, CNRS,Nancy,France,F-54000","institution_ids":["https://openalex.org/I90183372","https://openalex.org/I1294671590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064988262","display_name":"Romain Serizel","orcid":"https://orcid.org/0000-0002-6848-0114"},"institutions":[{"id":"https://openalex.org/I90183372","display_name":"Universit\u00e9 de Lorraine","ror":"https://ror.org/04vfs2w97","country_code":"FR","type":"education","lineage":["https://openalex.org/I90183372"]},{"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"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Romain Serizel","raw_affiliation_strings":["Université de Lorraine, CNRS,Nancy,France,F-54000"],"affiliations":[{"raw_affiliation_string":"Université de Lorraine, CNRS,Nancy,France,F-54000","institution_ids":["https://openalex.org/I90183372","https://openalex.org/I1294671590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030903462","display_name":"Denis Jouvet","orcid":null},"institutions":[{"id":"https://openalex.org/I90183372","display_name":"Universit\u00e9 de Lorraine","ror":"https://ror.org/04vfs2w97","country_code":"FR","type":"education","lineage":["https://openalex.org/I90183372"]},{"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"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Denis Jouvet","raw_affiliation_strings":["Université de Lorraine, CNRS,Nancy,France,F-54000"],"affiliations":[{"raw_affiliation_string":"Université de Lorraine, CNRS,Nancy,France,F-54000","institution_ids":["https://openalex.org/I90183372","https://openalex.org/I1294671590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030850681","display_name":"Mohammad Mohammadamini","orcid":null},"institutions":[{"id":"https://openalex.org/I4210119991","display_name":"Laboratoire Informatique d'Avignon","ror":"https://ror.org/02n399288","country_code":"FR","type":"facility","lineage":["https://openalex.org/I198415970","https://openalex.org/I4210119991"]},{"id":"https://openalex.org/I198415970","display_name":"Universit\u00e9 d'Avignon et des Pays de Vaucluse","ror":"https://ror.org/00mfpxb84","country_code":"FR","type":"education","lineage":["https://openalex.org/I198415970"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Mohammad Mohammadamini","raw_affiliation_strings":["University of Avignon,Laboratoire Informatique d'Avignon,France"],"affiliations":[{"raw_affiliation_string":"University of Avignon,Laboratoire Informatique d'Avignon,France","institution_ids":["https://openalex.org/I4210119991","https://openalex.org/I198415970"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017334281","display_name":"Driss Matrouf","orcid":null},"institutions":[{"id":"https://openalex.org/I198415970","display_name":"Universit\u00e9 d'Avignon et des Pays de Vaucluse","ror":"https://ror.org/00mfpxb84","country_code":"FR","type":"education","lineage":["https://openalex.org/I198415970"]},{"id":"https://openalex.org/I4210119991","display_name":"Laboratoire Informatique d'Avignon","ror":"https://ror.org/02n399288","country_code":"FR","type":"facility","lineage":["https://openalex.org/I198415970","https://openalex.org/I4210119991"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Driss Matrouf","raw_affiliation_strings":["University of Avignon,Laboratoire Informatique d'Avignon,France"],"affiliations":[{"raw_affiliation_string":"University of Avignon,Laboratoire Informatique d'Avignon,France","institution_ids":["https://openalex.org/I4210119991","https://openalex.org/I198415970"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5048477278"],"corresponding_institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I90183372"],"apc_list":null,"apc_paid":null,"fwci":0.3837,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.72327044,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"428","last_page":"435"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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":0.9991999864578247,"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/T11309","display_name":"Music and Audio Processing","score":0.9972000122070312,"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":0.823166012763977},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6951523423194885},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5966002345085144},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.536675751209259},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.5184842944145203},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4338723123073578},{"id":"https://openalex.org/keywords/directivity","display_name":"Directivity","score":0.43352073431015015},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.4149567484855652},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.364124596118927},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.16702523827552795},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.14244800806045532},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11787942051887512},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08873316645622253}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.823166012763977},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6951523423194885},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5966002345085144},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.536675751209259},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.5184842944145203},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4338723123073578},{"id":"https://openalex.org/C189039984","wikidata":"https://www.wikidata.org/wiki/Q8225412","display_name":"Directivity","level":3,"score":0.43352073431015015},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.4149567484855652},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.364124596118927},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.16702523827552795},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.14244800806045532},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11787942051887512},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08873316645622253},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C21822782","wikidata":"https://www.wikidata.org/wiki/Q131214","display_name":"Antenna (radio)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt54892.2023.10022350","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10022350","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","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 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":57,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1821462560","https://openalex.org/W1901129140","https://openalex.org/W2069681747","https://openalex.org/W2072118886","https://openalex.org/W2107223151","https://openalex.org/W2129069237","https://openalex.org/W2148613904","https://openalex.org/W2398042854","https://openalex.org/W2405774341","https://openalex.org/W2576001467","https://openalex.org/W2763188033","https://openalex.org/W2770119437","https://openalex.org/W2799831802","https://openalex.org/W2889224938","https://openalex.org/W2890964092","https://openalex.org/W2939777271","https://openalex.org/W2959300817","https://openalex.org/W2972311940","https://openalex.org/W2972425344","https://openalex.org/W2972526647","https://openalex.org/W2972992051","https://openalex.org/W2978904488","https://openalex.org/W2982242214","https://openalex.org/W3024869864","https://openalex.org/W3025515949","https://openalex.org/W3025783616","https://openalex.org/W3036167779","https://openalex.org/W3105013723","https://openalex.org/W3110257065","https://openalex.org/W3123097577","https://openalex.org/W3172148458","https://openalex.org/W3173852682","https://openalex.org/W3184410885","https://openalex.org/W3208015123","https://openalex.org/W4221144097","https://openalex.org/W4281485406","https://openalex.org/W6638523607","https://openalex.org/W6639824700","https://openalex.org/W6668037159","https://openalex.org/W6676227212","https://openalex.org/W6713658392","https://openalex.org/W6731788669","https://openalex.org/W6746278845","https://openalex.org/W6754087068","https://openalex.org/W6754496211","https://openalex.org/W6762178257","https://openalex.org/W6765775151","https://openalex.org/W6768020872","https://openalex.org/W6778946027","https://openalex.org/W6779823529","https://openalex.org/W6782760101","https://openalex.org/W6786375611","https://openalex.org/W6795261426","https://openalex.org/W6795986329","https://openalex.org/W6798721538","https://openalex.org/W6838250458"],"related_works":["https://openalex.org/W1656519308","https://openalex.org/W2042717753","https://openalex.org/W2022849831","https://openalex.org/W2037265366","https://openalex.org/W2026603686","https://openalex.org/W2331622705","https://openalex.org/W2391832549","https://openalex.org/W1499578372","https://openalex.org/W2368849850","https://openalex.org/W2088447702"],"abstract_inverted_index":{"Smart":[0],"devices":[1],"using":[2],"speaker":[3,24,59,86],"verification":[4,25,60,87],"are":[5],"getting":[6],"equipped":[7],"with":[8],"multiple":[9],"microphones,":[10],"improving":[11],"spatial":[12],"ambiguity":[13],"and":[14,39,85,97,129],"directivity.":[15],"However,":[16],"unlike":[17],"other":[18],"speech-based":[19],"applications,":[20],"the":[21,32,57,76,82,90,109,124],"performance":[22],"of":[23,35],"degrades":[26],"in":[27,62],"far-field":[28,64],"scenarios":[29],"due":[30],"to":[31,111],"adverse":[33],"effects":[34],"a":[36,45,54,63,71],"noisy":[37],"environment":[38],"room":[40],"reverberation.":[41],"This":[42],"paper":[43],"presents":[44],"novel":[46],"diffusion":[47],"probabilistic":[48],"models-based":[49],"multichannel":[50],"speech":[51,83],"enhancement":[52,84],"as":[53],"front-end":[55],"for":[56,115],"ECAPA-TDNN":[58],"system":[61],"noisy-reverberant":[65],"scenario.":[66],"The":[67],"proposed":[68],"approach":[69],"incorporates":[70],"two-stage":[72],"training":[73],"approach.":[74],"In":[75,89],"first":[77],"stage,":[78,92],"we":[79,93],"individually":[80],"train":[81],"modules.":[88],"second":[91],"combined":[94],"both":[95],"modules":[96],"trained":[98],"them":[99],"jointly.":[100],"We":[101],"use":[102],"similarity-preserving":[103],"knowledge":[104],"distillation":[105],"loss":[106],"that":[107],"guides":[108],"network":[110],"produce":[112],"similar":[113],"activation":[114],"enhanced":[116],"signals":[117],"like":[118],"clean":[119],"signals.":[120],"Joint":[121],"optimization":[122],"achieved":[123],"best":[125],"results":[126],"on":[127],"synthetic":[128],"VOiCES":[130],"datasets.":[131]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}