{"id":"https://openalex.org/W2799831802","doi":"https://doi.org/10.1109/icassp.2018.8462365","title":"Dereverberation and Beamforming in Far-Field Speaker Recognition","display_name":"Dereverberation and Beamforming in Far-Field Speaker Recognition","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2799831802","doi":"https://doi.org/10.1109/icassp.2018.8462365","mag":"2799831802"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8462365","is_oa":false,"landing_page_url":"http://doi.org/10.1109/icassp.2018.8462365","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":"conference-paper","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/A5055201620","display_name":"Ladislav Mo\u0161ner","orcid":"https://orcid.org/0000-0001-8175-2244"},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Ladislav Mosner","raw_affiliation_strings":["Brno University of Technology, Speech FIT and IT4I Center of Excellence, Czechia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brno University of Technology, Speech FIT and IT4I Center of Excellence, Czechia","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076315361","display_name":"Pavel Mat\u011bjka","orcid":null},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Pavel Matejka","raw_affiliation_strings":["Brno University of Technology, Speech FIT and IT4I Center of Excellence, Czechia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brno University of Technology, Speech FIT and IT4I Center of Excellence, Czechia","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075269577","display_name":"Ond\u0159ej Novotn\u00fd","orcid":"https://orcid.org/0000-0001-6258-9971"},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Ondrej Novotny","raw_affiliation_strings":["Brno University of Technology, Speech FIT and IT4I Center of Excellence, Czechia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brno University of Technology, Speech FIT and IT4I Center of Excellence, Czechia","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045539248","display_name":"Ja\u0148 \u010cernock\u00fd","orcid":"https://orcid.org/0000-0002-8800-0210"},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Jan Honza Cernocky","raw_affiliation_strings":["Brno University of Technology, Speech FIT and IT4I Center of Excellence, Czechia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brno University of Technology, Speech FIT and IT4I Center of Excellence, Czechia","institution_ids":["https://openalex.org/I60587646"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I60587646"],"apc_list":null,"apc_paid":null,"fwci":3.4276,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.93728357,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"5254","last_page":"5258"},"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":0.9995999932289124,"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":0.9991999864578247,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.8000321984291077},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6258294582366943},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.6129482984542847},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5722139477729797},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.2154105305671692},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10422924160957336}],"concepts":[{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.8000321984291077},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6258294582366943},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.6129482984542847},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5722139477729797},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.2154105305671692},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10422924160957336},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2018.8462365","is_oa":false,"landing_page_url":"http://doi.org/10.1109/icassp.2018.8462365","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"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5699999928474426,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1504755800","https://openalex.org/W1973669708","https://openalex.org/W1982728343","https://openalex.org/W1983812858","https://openalex.org/W2039716246","https://openalex.org/W2053150333","https://openalex.org/W2066561607","https://openalex.org/W2073017590","https://openalex.org/W2116635162","https://openalex.org/W2117678320","https://openalex.org/W2136818536","https://openalex.org/W2148613904","https://openalex.org/W2150678643","https://openalex.org/W2150769028","https://openalex.org/W2158143227","https://openalex.org/W2164502538","https://openalex.org/W2168729028","https://openalex.org/W2398042854","https://openalex.org/W2591810467","https://openalex.org/W2963064586","https://openalex.org/W6668868699"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2963170046","https://openalex.org/W2376244802","https://openalex.org/W4311414679","https://openalex.org/W2390279801","https://openalex.org/W2923631784","https://openalex.org/W818226659","https://openalex.org/W2358668433","https://openalex.org/W2158075901","https://openalex.org/W2376932109"],"abstract_inverted_index":{"This":[0],"paper":[1],"deals":[2],"with":[3,20,70,74],"far-field":[4,119],"speaker":[5,36,112],"recognition.":[6],"On":[7],"a":[8,17,111],"corpus":[9],"of":[10,32],"NIST":[11],"SRE":[12],"2010":[13],"data":[14],"retransmitted":[15],"in":[16,117],"real":[18],"room":[19,27],"multiple":[21],"microphones,":[22],"we":[23],"first":[24],"demonstrate":[25],"how":[26],"acoustics":[28],"cause":[29],"significant":[30],"degradation":[31],"state-of-the-art":[33],"i-vector":[34],"based":[35,67],"recognition":[37,113],"system.":[38],"We":[39,60],"then":[40],"investigate":[41],"several":[42],"techniques":[43],"to":[44,58],"improve":[45],"the":[46,88,100,118],"performances":[47],"ranging":[48],"from":[49],"probabilistic":[50],"linear":[51],"discriminant":[52],"analysis":[53],"(PLDA)":[54],"re-training,":[55],"through":[56],"dereverberation,":[57],"beamforming.":[59],"found":[61],"that":[62,110],"weighted":[63],"prediction":[64],"error":[65],"(WPE)":[66],"dereverberation":[68],"combined":[69],"generalized":[71],"eigenvalue":[72],"beamformer":[73],"power-spectral":[75],"density":[76],"(PSD)":[77],"weighting":[78],"masks":[79],"generated":[80],"by":[81,96],"neural":[82],"networks":[83],"(NN)":[84],"provides":[85],"results":[86],"approaching":[87],"clean":[89],"close-microphone":[90],"setup.":[91],"Further":[92],"improvement":[93],"was":[94],"obtained":[95],"re-training":[97],"PLDA":[98],"or":[99],"mask-generating":[101],"NNs":[102],"on":[103],"simulated":[104],"target":[105],"data.":[106],"The":[107],"work":[108],"shows":[109],"system":[114],"working":[115],"robustly":[116],"scenario":[120],"can":[121],"be":[122],"developed.":[123]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":6}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}