{"id":"https://openalex.org/W4416799490","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249384","title":"Spatial Audio Signal Enhancement: A Multi-Output MVDR Method in the Spherical Harmonic-Domain","display_name":"Spatial Audio Signal Enhancement: A Multi-Output MVDR Method in the Spherical Harmonic-Domain","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416799490","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249384"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249384","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249384","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5100320799","display_name":"Huawei Zhang","orcid":"https://orcid.org/0000-0002-4537-2217"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Huawei Zhang","raw_affiliation_strings":["The Australian National University,Audio & Acoustic Signal Processing Group,Canberra,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Australian National University,Audio & Acoustic Signal Processing Group,Canberra,Australia","institution_ids":["https://openalex.org/I118347636"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100720924","display_name":"Jihui Zhang","orcid":"https://orcid.org/0000-0001-6817-139X"},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"The University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jihui Zhang","raw_affiliation_strings":["School of Electrical Engineering and Computer Science, The University of Queensland,Brisbane,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering and Computer Science, The University of Queensland,Brisbane,Australia","institution_ids":["https://openalex.org/I165143802"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085744068","display_name":"Huiyuan Sun","orcid":"https://orcid.org/0000-0001-7287-5461"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Huiyuan Sun","raw_affiliation_strings":["The Australian National University,Audio & Acoustic Signal Processing Group,Canberra,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Australian National University,Audio & Acoustic Signal Processing Group,Canberra,Australia","institution_ids":["https://openalex.org/I118347636"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058898992","display_name":"Prasanga N. Samarasinghe","orcid":"https://orcid.org/0000-0002-5589-4203"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Prasanga Samarasinghe","raw_affiliation_strings":["The Australian National University,Audio & Acoustic Signal Processing Group,Canberra,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Australian National University,Audio & Acoustic Signal Processing Group,Canberra,Australia","institution_ids":["https://openalex.org/I118347636"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.38872898,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"513","last_page":"518"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.8876000046730042,"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":0.8876000046730042,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.07530000060796738,"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"}},{"id":"https://openalex.org/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.023900000378489494,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.6011999845504761},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4936000108718872},{"id":"https://openalex.org/keywords/harmonic","display_name":"Harmonic","score":0.4729999899864197},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.47099998593330383},{"id":"https://openalex.org/keywords/spherical-harmonics","display_name":"Spherical harmonics","score":0.4634000062942505},{"id":"https://openalex.org/keywords/signal-to-noise-ratio","display_name":"Signal-to-noise ratio (imaging)","score":0.4262999892234802},{"id":"https://openalex.org/keywords/signal-processing","display_name":"Signal processing","score":0.40709999203681946},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.3732999861240387},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.35519999265670776}],"concepts":[{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.6011999845504761},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5630999803543091},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5400999784469604},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4936000108718872},{"id":"https://openalex.org/C127934551","wikidata":"https://www.wikidata.org/wiki/Q1148098","display_name":"Harmonic","level":2,"score":0.4729999899864197},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.47099998593330383},{"id":"https://openalex.org/C3768446","wikidata":"https://www.wikidata.org/wiki/Q877100","display_name":"Spherical harmonics","level":2,"score":0.4634000062942505},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.4456000030040741},{"id":"https://openalex.org/C13944312","wikidata":"https://www.wikidata.org/wiki/Q7512748","display_name":"Signal-to-noise ratio (imaging)","level":2,"score":0.4262999892234802},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.40709999203681946},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.3732999861240387},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3619000017642975},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.35519999265670776},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3528999984264374},{"id":"https://openalex.org/C131770355","wikidata":"https://www.wikidata.org/wiki/Q876215","display_name":"Harmonic analysis","level":2,"score":0.3425000011920929},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.33640000224113464},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.33160001039505005},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.32120001316070557},{"id":"https://openalex.org/C165646398","wikidata":"https://www.wikidata.org/wiki/Q3755281","display_name":"Minimum-variance unbiased estimator","level":3,"score":0.31679999828338623},{"id":"https://openalex.org/C157138929","wikidata":"https://www.wikidata.org/wiki/Q570","display_name":"Loudspeaker","level":2,"score":0.3107999861240387},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.30489999055862427},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.29649999737739563},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.2833999991416931},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.2734000086784363},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.2653999924659729},{"id":"https://openalex.org/C167928553","wikidata":"https://www.wikidata.org/wiki/Q1376021","display_name":"Estimation theory","level":2,"score":0.2603999972343445},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2578999996185303}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249384","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249384","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8875222463","display_name":"Listening to Nature: Transforming Bioacoustics through Spatial Audio","funder_award_id":"DE230101567","funder_id":"https://openalex.org/F4320334704","funder_display_name":"Australian Research Council"}],"funders":[{"id":"https://openalex.org/F4320334704","display_name":"Australian Research Council","ror":"https://ror.org/05mmh0f86"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1503775994","https://openalex.org/W1919482273","https://openalex.org/W1969110495","https://openalex.org/W1987850385","https://openalex.org/W2007162393","https://openalex.org/W2060108923","https://openalex.org/W2117678320","https://openalex.org/W2144649911","https://openalex.org/W2289898380","https://openalex.org/W2616802817","https://openalex.org/W2787530354","https://openalex.org/W2899838214","https://openalex.org/W2973133192","https://openalex.org/W2996335241","https://openalex.org/W3047232705","https://openalex.org/W3094665499","https://openalex.org/W3105563130","https://openalex.org/W4286111250","https://openalex.org/W4286582029","https://openalex.org/W4312245440","https://openalex.org/W4385225525","https://openalex.org/W4388118608","https://openalex.org/W4389084404","https://openalex.org/W4389228078"],"related_works":[],"abstract_inverted_index":{"Spatial":[0],"audio":[1],"signal":[2,50],"enhancement":[3],"aims":[4],"to":[5,57,96],"reduce":[6],"interfering":[7],"source":[8],"contributions":[9],"while":[10],"preserving":[11],"the":[12,72,88,101],"desired":[13],"sound":[14],"field":[15],"with":[16],"its":[17],"spatial":[18,49],"cues.":[19],"Existing":[20],"methods":[21],"generally":[22],"rely":[23],"on":[24],"impractical":[25,31],"assumptions":[26],"(e.g.":[27],"accurate":[28],"estimations":[29],"of":[30],"information)":[32],"or":[33],"have":[34],"limited":[35],"applicability.":[36],"This":[37],"paper":[38],"presents":[39],"a":[40,92,97],"spherical":[41],"harmonic":[42],"(SH)-domain":[43],"minimum":[44],"variance":[45],"distortionless":[46],"response":[47],"(MVDR)-based":[48],"enhancer":[51],"using":[52],"Relative":[53],"Harmonic":[54],"Coefficients":[55],"(ReHCs)":[56],"extract":[58],"clean":[59],"SH":[60],"coefficients":[61],"from":[62],"noisy":[63],"recordings":[64],"in":[65,91],"reverberant":[66,93],"environments.":[67],"A":[68],"simulation":[69],"study":[70],"shows":[71],"proposed":[73],"method":[74,99],"achieves":[75],"lower":[76],"estimation":[77],"error,":[78],"higher":[79],"speech-distortion-ratio":[80],"(SDR),":[81],"and":[82],"comparable":[83],"noise":[84],"reduction":[85],"(NR)":[86],"within":[87],"sweet":[89],"area":[90],"environment,":[94],"compared":[95],"beamforming-andprojection":[98],"as":[100],"baseline.":[102]},"counts_by_year":[],"updated_date":"2026-06-22T08:00:12.763002","created_date":"2025-11-28T00:00:00"}