{"id":"https://openalex.org/W4405975163","doi":"https://doi.org/10.1109/msp.2024.3451653","title":"Microphone Array Signal Processing and Deep Learning for Speech Enhancement: Combining model-based and data-driven approaches to parameter estimation and filtering","display_name":"Microphone Array Signal Processing and Deep Learning for Speech Enhancement: Combining model-based and data-driven approaches to parameter estimation and filtering","publication_year":2024,"publication_date":"2024-11-01","ids":{"openalex":"https://openalex.org/W4405975163","doi":"https://doi.org/10.1109/msp.2024.3451653"},"language":"en","primary_location":{"id":"doi:10.1109/msp.2024.3451653","is_oa":false,"landing_page_url":"https://doi.org/10.1109/msp.2024.3451653","pdf_url":null,"source":{"id":"https://openalex.org/S120977877","display_name":"IEEE Signal Processing Magazine","issn_l":"1053-5888","issn":["1053-5888","1558-0792"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Magazine","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2501.07215","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082075598","display_name":"Reinhold Haeb\u2010Umbach","orcid":"https://orcid.org/0000-0001-9468-7330"},"institutions":[{"id":"https://openalex.org/I206945453","display_name":"Paderborn University","ror":"https://ror.org/058kzsd48","country_code":"DE","type":"education","lineage":["https://openalex.org/I206945453"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Reinhold Haeb-Umbach","raw_affiliation_strings":["Paderborn University, Paderborn, Germany"],"raw_orcid":"https://orcid.org/0000-0001-9468-7330","affiliations":[{"raw_affiliation_string":"Paderborn University, Paderborn, Germany","institution_ids":["https://openalex.org/I206945453"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021240106","display_name":"Tomohiro Nakatani","orcid":"https://orcid.org/0000-0002-7487-7150"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomohiro Nakatani","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"raw_orcid":"https://orcid.org/0000-0002-7487-7150","affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023868166","display_name":"Marc Delcroix","orcid":"https://orcid.org/0000-0002-5175-7834"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Marc Delcroix","raw_affiliation_strings":["NTT Communication Science Laboratories, Kyoto, Japan"],"raw_orcid":"https://orcid.org/0000-0002-5175-7834","affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064522438","display_name":"Christoph Boeddeker","orcid":"https://orcid.org/0000-0002-8701-1567"},"institutions":[{"id":"https://openalex.org/I206945453","display_name":"Paderborn University","ror":"https://ror.org/058kzsd48","country_code":"DE","type":"education","lineage":["https://openalex.org/I206945453"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Christoph Boeddeker","raw_affiliation_strings":["Paderborn University, Paderborn, Germany"],"raw_orcid":"https://orcid.org/0000-0002-8701-1567","affiliations":[{"raw_affiliation_string":"Paderborn University, Paderborn, Germany","institution_ids":["https://openalex.org/I206945453"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070624983","display_name":"Tsubasa Ochiai","orcid":"https://orcid.org/0000-0002-2519-2032"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tsubasa Ochiai","raw_affiliation_strings":["NTT Communication Science Laboratories, Kyoto, Japan"],"raw_orcid":"https://orcid.org/0000-0002-2519-2032","affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5082075598"],"corresponding_institution_ids":["https://openalex.org/I206945453"],"apc_list":null,"apc_paid":null,"fwci":3.2882,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.93240736,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"41","issue":"6","first_page":"12","last_page":"23"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9988999962806702,"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":0.9988999962806702,"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":0.9610000252723694,"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/T12759","display_name":"Vehicle Noise and Vibration Control","score":0.9438999891281128,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7573028802871704},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6299553513526917},{"id":"https://openalex.org/keywords/signal-processing","display_name":"Signal processing","score":0.5879507064819336},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.5744595527648926},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5638208389282227},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.5470021367073059},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.5050142407417297},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4988706111907959},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4918644428253174},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.4760984182357788},{"id":"https://openalex.org/keywords/estimation-theory","display_name":"Estimation theory","score":0.43582648038864136},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39588022232055664},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.3293302357196808},{"id":"https://openalex.org/keywords/digital-signal-processing","display_name":"Digital signal processing","score":0.16161683201789856},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.15999606251716614},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.14947497844696045}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7573028802871704},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6299553513526917},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.5879507064819336},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.5744595527648926},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5638208389282227},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.5470021367073059},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.5050142407417297},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4988706111907959},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4918644428253174},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.4760984182357788},{"id":"https://openalex.org/C167928553","wikidata":"https://www.wikidata.org/wiki/Q1376021","display_name":"Estimation theory","level":2,"score":0.43582648038864136},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39588022232055664},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.3293302357196808},{"id":"https://openalex.org/C84462506","wikidata":"https://www.wikidata.org/wiki/Q173142","display_name":"Digital signal processing","level":2,"score":0.16161683201789856},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.15999606251716614},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.14947497844696045},{"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/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/msp.2024.3451653","is_oa":false,"landing_page_url":"https://doi.org/10.1109/msp.2024.3451653","pdf_url":null,"source":{"id":"https://openalex.org/S120977877","display_name":"IEEE Signal Processing Magazine","issn_l":"1053-5888","issn":["1053-5888","1558-0792"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Magazine","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2501.07215","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2501.07215","pdf_url":"https://arxiv.org/pdf/2501.07215","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2501.07215","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2501.07215","pdf_url":"https://arxiv.org/pdf/2501.07215","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4405975163.pdf"},"referenced_works_count":53,"referenced_works":["https://openalex.org/W1584645830","https://openalex.org/W1987906574","https://openalex.org/W1997109056","https://openalex.org/W2014768838","https://openalex.org/W2042071805","https://openalex.org/W2044893557","https://openalex.org/W2128653836","https://openalex.org/W2131968171","https://openalex.org/W2141783538","https://openalex.org/W2154070811","https://openalex.org/W2168729028","https://openalex.org/W2398042854","https://openalex.org/W2398972335","https://openalex.org/W2408744528","https://openalex.org/W2517616541","https://openalex.org/W2559260703","https://openalex.org/W2563666542","https://openalex.org/W2568308529","https://openalex.org/W2702006285","https://openalex.org/W2734774145","https://openalex.org/W2747732471","https://openalex.org/W2892163332","https://openalex.org/W2899515918","https://openalex.org/W2900212944","https://openalex.org/W2902796441","https://openalex.org/W2933708090","https://openalex.org/W2946521785","https://openalex.org/W2952218014","https://openalex.org/W2962866211","https://openalex.org/W2972460025","https://openalex.org/W2982471419","https://openalex.org/W3008762051","https://openalex.org/W3016232124","https://openalex.org/W3020336359","https://openalex.org/W3025260599","https://openalex.org/W3032514799","https://openalex.org/W3147539069","https://openalex.org/W3162341667","https://openalex.org/W3163217847","https://openalex.org/W3163391314","https://openalex.org/W3171278394","https://openalex.org/W3197832224","https://openalex.org/W3207360934","https://openalex.org/W4236697647","https://openalex.org/W4296068789","https://openalex.org/W4312219134","https://openalex.org/W4312806213","https://openalex.org/W4316660723","https://openalex.org/W4385756463","https://openalex.org/W4389315128","https://openalex.org/W4389722573","https://openalex.org/W6784499681","https://openalex.org/W6856127113"],"related_works":["https://openalex.org/W2120771489","https://openalex.org/W2051376034","https://openalex.org/W3211091508","https://openalex.org/W2955597484","https://openalex.org/W3110551121","https://openalex.org/W193702574","https://openalex.org/W2289868279","https://openalex.org/W72660888","https://openalex.org/W1546240199","https://openalex.org/W2969585518"],"abstract_inverted_index":{"Multichannel":[0],"acoustic":[1],"signal":[2,18,25,80],"processing":[3,81],"is":[4],"a":[5,16],"well-established":[6],"and":[7,19,62,68,82,104],"powerful":[8],"tool":[9],"to":[10,52,65,74,86],"exploit":[11],"the":[12,28,38,45,71,76,93],"spatial":[13,34],"diversity":[14],"between":[15],"target":[17],"nontarget":[20],"or":[21],"noise":[22,100],"sources":[23],"for":[24,31],"enhancement.":[26],"However,":[27],"textbook":[29],"solutions":[30],"optimal":[32],"data-dependent":[33],"filtering":[35],"rest":[36],"on":[37],"knowledge":[39],"of":[40,44,78],"second-order":[41],"statistical":[42],"moments":[43],"signals,":[46],"which":[47],"have":[48],"traditionally":[49],"been":[50],"difficult":[51],"acquire.":[53],"In":[54],"this":[55],"contribution,":[56],"we":[57],"compare":[58],"model-based,":[59],"purely":[60],"data-driven,":[61],"hybrid":[63],"approaches":[64],"parameter":[66],"estimation":[67],"filtering,":[69],"where":[70],"latter":[72],"tries":[73],"combine":[75],"benefits":[77],"model-based":[79],"data-driven":[83],"deep":[84],"learning":[85],"overcome":[87],"their":[88],"individual":[89],"deficiencies.":[90],"We":[91],"illustrate":[92],"underlying":[94],"design":[95],"principles":[96],"with":[97],"examples":[98],"from":[99],"reduction,":[101],"source":[102],"separation,":[103],"dereverberation.":[105]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":4}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-01-02T00:00:00"}