{"id":"https://openalex.org/W4308521149","doi":"https://doi.org/10.21437/iberspeech.2022-45","title":"Online Multichannel Speech Enhancement combining Statistical Signal Processing and Deep Neural Networks: A Ph.D. Thesis Overview","display_name":"Online Multichannel Speech Enhancement combining Statistical Signal Processing and Deep Neural Networks: A Ph.D. Thesis Overview","publication_year":2022,"publication_date":"2022-11-08","ids":{"openalex":"https://openalex.org/W4308521149","doi":"https://doi.org/10.21437/iberspeech.2022-45"},"language":"en","primary_location":{"id":"doi:10.21437/iberspeech.2022-45","is_oa":false,"landing_page_url":"https://doi.org/10.21437/iberspeech.2022-45","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IberSPEECH 2022","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://digibug.ugr.es/bitstream/10481/88765/1/martindonas22b_iberspeech.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064609638","display_name":"Juan M. Mart\u00edn-Do\u00f1as","orcid":"https://orcid.org/0000-0003-4874-0166"},"institutions":[{"id":"https://openalex.org/I173304897","display_name":"Universidad de Granada","ror":"https://ror.org/04njjy449","country_code":"ES","type":"education","lineage":["https://openalex.org/I173304897"]},{"id":"https://openalex.org/I4210092551","display_name":"Vicomtech","ror":"https://ror.org/0023sah13","country_code":"ES","type":"facility","lineage":["https://openalex.org/I4210092551"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Juan Manuel Mart\u00edn-Do\u00f1as","raw_affiliation_strings":["Dept. de Teor\u00eda de la Se\u00f1al, Telem\u00e1tica y Comunicaciones, Universidad de Granada, Spain","Fundaci\u00f3n Vicomtech, Basque Research and Technology Alliance (BRTA), Mikeletegi 57, 20009 Donostia-San Sebasti\u00e1n, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. de Teor\u00eda de la Se\u00f1al, Telem\u00e1tica y Comunicaciones, Universidad de Granada, Spain","institution_ids":["https://openalex.org/I173304897"]},{"raw_affiliation_string":"Fundaci\u00f3n Vicomtech, Basque Research and Technology Alliance (BRTA), Mikeletegi 57, 20009 Donostia-San Sebasti\u00e1n, Spain","institution_ids":["https://openalex.org/I4210092551"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078514616","display_name":"Antonio M. Peinado","orcid":"https://orcid.org/0000-0001-8214-6676"},"institutions":[{"id":"https://openalex.org/I173304897","display_name":"Universidad de Granada","ror":"https://ror.org/04njjy449","country_code":"ES","type":"education","lineage":["https://openalex.org/I173304897"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Antonio M. Peinado","raw_affiliation_strings":["Dept. de Teor\u00eda de la Se\u00f1al, Telem\u00e1tica y Comunicaciones, Universidad de Granada, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. de Teor\u00eda de la Se\u00f1al, Telem\u00e1tica y Comunicaciones, Universidad de Granada, Spain","institution_ids":["https://openalex.org/I173304897"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024291487","display_name":"\u00c1ngel M. G\u00f3mez","orcid":"https://orcid.org/0000-0002-9995-3068"},"institutions":[{"id":"https://openalex.org/I173304897","display_name":"Universidad de Granada","ror":"https://ror.org/04njjy449","country_code":"ES","type":"education","lineage":["https://openalex.org/I173304897"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Angel M. Gomez","raw_affiliation_strings":["Dept. de Teor\u00eda de la Se\u00f1al, Telem\u00e1tica y Comunicaciones, Universidad de Granada, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. de Teor\u00eda de la Se\u00f1al, Telem\u00e1tica y Comunicaciones, Universidad de Granada, Spain","institution_ids":["https://openalex.org/I173304897"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.12538558,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"221","last_page":"225"},"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9976999759674072,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8221435546875},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.751656174659729},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.7212923169136047},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6089790463447571},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.6080907583236694},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.521074652671814},{"id":"https://openalex.org/keywords/signal-processing","display_name":"Signal processing","score":0.5183206796646118},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.4612520933151245},{"id":"https://openalex.org/keywords/mobile-device","display_name":"Mobile device","score":0.4576839506626129},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.45724913477897644},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4462255835533142},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.4216506779193878},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3966892957687378},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.3918915390968323},{"id":"https://openalex.org/keywords/digital-signal-processing","display_name":"Digital signal processing","score":0.1839582622051239},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10350513458251953}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8221435546875},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.751656174659729},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.7212923169136047},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6089790463447571},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.6080907583236694},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.521074652671814},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.5183206796646118},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.4612520933151245},{"id":"https://openalex.org/C186967261","wikidata":"https://www.wikidata.org/wiki/Q5082128","display_name":"Mobile device","level":2,"score":0.4576839506626129},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.45724913477897644},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4462255835533142},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.4216506779193878},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3966892957687378},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.3918915390968323},{"id":"https://openalex.org/C84462506","wikidata":"https://www.wikidata.org/wiki/Q173142","display_name":"Digital signal processing","level":2,"score":0.1839582622051239},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10350513458251953},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/iberspeech.2022-45","is_oa":false,"landing_page_url":"https://doi.org/10.21437/iberspeech.2022-45","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IberSPEECH 2022","raw_type":"proceedings-article"},{"id":"pmh:oai:digibug.ugr.es:10481/88765","is_oa":true,"landing_page_url":"https://hdl.handle.net/10481/88765","pdf_url":"https://digibug.ugr.es/bitstream/10481/88765/1/martindonas22b_iberspeech.pdf","source":{"id":"https://openalex.org/S4306400567","display_name":"Institutional Repository of the University of Granada (University of Granada)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I173304897","host_organization_name":"Universidad de Granada","host_organization_lineage":["https://openalex.org/I173304897"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:digibug.ugr.es:10481/88765","is_oa":true,"landing_page_url":"https://hdl.handle.net/10481/88765","pdf_url":"https://digibug.ugr.es/bitstream/10481/88765/1/martindonas22b_iberspeech.pdf","source":{"id":"https://openalex.org/S4306400567","display_name":"Institutional Repository of the University of Granada (University of Granada)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I173304897","host_organization_name":"Universidad de Granada","host_organization_lineage":["https://openalex.org/I173304897"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4308521149.pdf"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W1495679096","https://openalex.org/W2020997493","https://openalex.org/W2044893557","https://openalex.org/W2061074721","https://openalex.org/W2069681747","https://openalex.org/W2141998673","https://openalex.org/W2146324387","https://openalex.org/W2507780144","https://openalex.org/W2516001803","https://openalex.org/W2558649592","https://openalex.org/W2559260703","https://openalex.org/W2568308529","https://openalex.org/W2591810467","https://openalex.org/W2743121184","https://openalex.org/W2749510669","https://openalex.org/W2752530932","https://openalex.org/W2781659627","https://openalex.org/W2807518508","https://openalex.org/W2892110446","https://openalex.org/W2892163332","https://openalex.org/W2901548412","https://openalex.org/W2903522566","https://openalex.org/W2945191446","https://openalex.org/W2951183478","https://openalex.org/W2962866211","https://openalex.org/W2963488660","https://openalex.org/W2964058413","https://openalex.org/W2972757492","https://openalex.org/W2982456909","https://openalex.org/W2982471419","https://openalex.org/W3098606562","https://openalex.org/W3109458322","https://openalex.org/W3123070063"],"related_works":["https://openalex.org/W1986772939","https://openalex.org/W2037635165","https://openalex.org/W2738829087","https://openalex.org/W2542062716","https://openalex.org/W2380771148","https://openalex.org/W1505346162","https://openalex.org/W2348931051","https://openalex.org/W4200562864","https://openalex.org/W2132495960","https://openalex.org/W2120771489"],"abstract_inverted_index":{"Speech-related":[0],"applications":[1],"on":[2,100],"mobile":[3,19,50,106],"devices":[4,20,124],"require":[5],"highperformance":[6],"speech":[7,43,47,71,107,126,142,163,180],"enhancement":[8,44,127],"algorithms":[9,45],"to":[10,27,59,157,190],"tackle":[11],"challenging,":[12],"noisy":[13,102,117],"real-world":[14],"environments.":[15],"In":[16],"addition,":[17],"current":[18],"often":[21],"embed":[22],"several":[23],"microphones,":[24],"allowing":[25,188],"them":[26],"exploit":[28,158],"spatial":[29],"information.":[30],"The":[31,52],"main":[32],"goal":[33],"of":[34,40,69,82,137],"this":[35],"Thesis":[36],"is":[37],"the":[38,61,67,70,83,135,169],"development":[39],"online":[41],"multichannel":[42,56],"for":[46,125,141,178],"services":[48],"in":[49,79,116],"devices.":[51],"proposed":[53,170],"techniques":[54,171],"use":[55],"signal":[57,151],"processing":[58,143,152,181],"increase":[60],"noise":[62],"reduction":[63],"performance":[64],"without":[65],"degrading":[66],"quality":[68,193],"signal.":[72],"Moreover,":[73,132],"deep":[74,138,154],"neural":[75],"networks":[76],"are":[77],"applied":[78],"specific":[80],"parts":[81],"algorithm":[84],"where":[85,104],"modeling":[86],"by":[87],"classical":[88],"methods":[89,140,156],"would":[90],"be,":[91],"otherwise,":[92],"unfeasible":[93],"or":[94],"very":[95,183],"limiting.":[96],"Our":[97,147],"contributions":[98,148],"focus":[99],"different":[101],"environments":[103,120],"these":[105],"technologies":[108],"can":[109],"be":[110],"applied.":[111],"These":[112],"include":[113],"dualmicrophone":[114],"smartphones":[115],"and":[118,121,128,153,161,194],"reverberant":[119],"general":[122],"multi-microphone":[123],"target":[129],"source":[130],"separation.":[131],"we":[133],"study":[134],"training":[136],"learning":[139,155],"using":[144],"perceptual":[145,192],"considerations.":[146],"successfully":[149],"integrate":[150],"spectral,":[159],"spatial,":[160],"temporal":[162],"features":[164],"jointly.":[165],"As":[166],"a":[167,175],"result,":[168],"provide":[172],"us":[173,189],"with":[174],"manifold":[176],"framework":[177],"robust":[179],"under":[182],"challenging":[184],"acoustic":[185],"environments,":[186],"thus":[187],"improve":[191],"intelligibility":[195],"measures.":[196]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
