{"id":"https://openalex.org/W4408353207","doi":"https://doi.org/10.1109/icassp49660.2025.10887842","title":"Blind Estimation of Sub-band Acoustic Parameters from Ambisonics Recordings using Spectro-Spatial Covariance Features","display_name":"Blind Estimation of Sub-band Acoustic Parameters from Ambisonics Recordings using Spectro-Spatial Covariance Features","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353207","doi":"https://doi.org/10.1109/icassp49660.2025.10887842"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10887842","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887842","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5113122402","display_name":"Hanyu Meng","orcid":null},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Hanyu Meng","raw_affiliation_strings":["University of New South Wales"],"affiliations":[{"raw_affiliation_string":"University of New South Wales","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116594404","display_name":"Jeroen Breebaar","orcid":null},"institutions":[{"id":"https://openalex.org/I4210119568","display_name":"National Acoustic Laboratories","ror":"https://ror.org/02swxtp23","country_code":"AU","type":"facility","lineage":["https://openalex.org/I4210119568"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jeroen Breebaar","raw_affiliation_strings":["Dolby Laboratories,Australia"],"affiliations":[{"raw_affiliation_string":"Dolby Laboratories,Australia","institution_ids":["https://openalex.org/I4210119568"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025180534","display_name":"Jeremy G. Stoddard","orcid":"https://orcid.org/0000-0001-8363-1489"},"institutions":[{"id":"https://openalex.org/I4210119568","display_name":"National Acoustic Laboratories","ror":"https://ror.org/02swxtp23","country_code":"AU","type":"facility","lineage":["https://openalex.org/I4210119568"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jeremy Stoddard","raw_affiliation_strings":["Dolby Laboratories,Australia"],"affiliations":[{"raw_affiliation_string":"Dolby Laboratories,Australia","institution_ids":["https://openalex.org/I4210119568"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032689109","display_name":"Vidhyasaharan Sethu","orcid":"https://orcid.org/0000-0001-8492-1787"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Vidhyasaharan Sethu","raw_affiliation_strings":["University of New South Wales"],"affiliations":[{"raw_affiliation_string":"University of New South Wales","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028116210","display_name":"Eliathamby Ambikairajah","orcid":"https://orcid.org/0000-0003-4673-6534"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Eliathamby Ambikairajah","raw_affiliation_strings":["University of New South Wales"],"affiliations":[{"raw_affiliation_string":"University of New South Wales","institution_ids":["https://openalex.org/I31746571"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5113122402"],"corresponding_institution_ids":["https://openalex.org/I31746571"],"apc_list":null,"apc_paid":null,"fwci":4.7229,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.93919646,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11447","display_name":"Blind Source Separation Techniques","score":0.991599977016449,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.991599977016449,"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/T10860","display_name":"Speech and Audio Processing","score":0.9886999726295471,"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.9656000137329102,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/ambisonics","display_name":"Ambisonics","score":0.9261195063591003},{"id":"https://openalex.org/keywords/covariance","display_name":"Covariance","score":0.6946083903312683},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5870993137359619},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.532367467880249},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.4683610200881958},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41412627696990967},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41203632950782776},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.37773656845092773},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.2530241012573242},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.24305999279022217},{"id":"https://openalex.org/keywords/loudspeaker","display_name":"Loudspeaker","score":0.131750226020813},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12766540050506592},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08523431420326233}],"concepts":[{"id":"https://openalex.org/C47726159","wikidata":"https://www.wikidata.org/wiki/Q457547","display_name":"Ambisonics","level":3,"score":0.9261195063591003},{"id":"https://openalex.org/C178650346","wikidata":"https://www.wikidata.org/wiki/Q201984","display_name":"Covariance","level":2,"score":0.6946083903312683},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5870993137359619},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.532367467880249},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.4683610200881958},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41412627696990967},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41203632950782776},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.37773656845092773},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.2530241012573242},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24305999279022217},{"id":"https://openalex.org/C157138929","wikidata":"https://www.wikidata.org/wiki/Q570","display_name":"Loudspeaker","level":2,"score":0.131750226020813},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12766540050506592},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08523431420326233},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10887842","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887842","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W35747644","https://openalex.org/W1974605121","https://openalex.org/W2054326086","https://openalex.org/W2079572437","https://openalex.org/W2084529785","https://openalex.org/W2410879554","https://openalex.org/W2509978695","https://openalex.org/W2805466703","https://openalex.org/W2900429685","https://openalex.org/W2917254586","https://openalex.org/W2982059757","https://openalex.org/W3015235644","https://openalex.org/W3081461453","https://openalex.org/W3083274258","https://openalex.org/W3097930518","https://openalex.org/W3129370657","https://openalex.org/W3132554485","https://openalex.org/W3185499768","https://openalex.org/W3201480196","https://openalex.org/W4206377423","https://openalex.org/W4213377681","https://openalex.org/W4285256146","https://openalex.org/W4293363567","https://openalex.org/W4372269163","https://openalex.org/W4382632381","https://openalex.org/W4385822571","https://openalex.org/W4402112007","https://openalex.org/W6633823725","https://openalex.org/W6745746767","https://openalex.org/W6780226713","https://openalex.org/W6866415093"],"related_works":["https://openalex.org/W62656364","https://openalex.org/W4387871131","https://openalex.org/W2403497458","https://openalex.org/W2305368260","https://openalex.org/W3108333885","https://openalex.org/W1978521983","https://openalex.org/W3216979959","https://openalex.org/W4251115075","https://openalex.org/W2305616225","https://openalex.org/W1990262973"],"abstract_inverted_index":{"Estimating":[0],"frequency-varying":[1],"acoustic":[2,93,144],"parameters":[3],"is":[4],"essential":[5],"for":[6,90,103,134,141],"enhancing":[7],"immersive":[8],"perception":[9],"in":[10],"realistic":[11],"spatial":[12,66],"audio":[13],"creation.":[14],"In":[15],"this":[16],"paper,":[17],"we":[18,96],"propose":[19],"a":[20,51,99,110,135],"unified":[21],"framework":[22,49],"that":[23],"blindly":[24],"estimates":[25],"reverberation":[26],"time":[27],"(T60),":[28],"direct-to-reverberant":[29],"ratio":[30],"(DRR),":[31],"and":[32,121,132],"clarity":[33],"(C50)":[34],"across":[35],"10":[36],"frequency":[37],"bands":[38],"using":[39],"first-order":[40],"Ambisonics":[41],"(FOA)":[42],"speech":[43],"recordings":[44],"as":[45,63,65],"inputs.":[46],"The":[47],"proposed":[48],"utilizes":[50],"novel":[52,100],"feature":[53,108],"named":[54],"Spectro-Spatial":[55],"Covariance":[56],"Vector":[57],"(SSCV),":[58],"efficiently":[59],"representing":[60],"temporal,":[61],"spectral":[62,81],"well":[64],"information":[67],"of":[68,138],"the":[69,106,116],"FOA":[70],"signal.":[71],"Our":[72],"models":[73],"significantly":[74],"outperform":[75],"existing":[76],"single-channel":[77],"methods":[78],"with":[79,109],"only":[80],"information,":[82],"reducing":[83],"estimation":[84,130],"errors":[85,131],"by":[86],"more":[87],"than":[88],"half":[89],"all":[91,142],"three":[92],"parameters.":[94,145],"Additionally,":[95],"introduce":[97],"FOA-Conv3D,":[98],"back-end":[101],"network":[102,119,125],"effectively":[104],"utilising":[105],"SSCV":[107],"3D":[111],"convolutional":[112,117,123],"encoder.":[113],"FOA-Conv3D":[114],"outperforms":[115],"neural":[118,124],"(CNN)":[120],"recurrent":[122],"(CRNN)":[126],"backends,":[127],"achieving":[128],"lower":[129],"accounting":[133],"higher":[136],"proportion":[137],"variance":[139],"(PoV)":[140],"3":[143]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2025-12-28T23:10:05.387466","created_date":"2025-10-10T00:00:00"}