{"id":"https://openalex.org/W4386764837","doi":"https://doi.org/10.1109/waspaa58266.2023.10248186","title":"Blind Room Acoustic Parameters Estimation Using Mobile Audio Transformer","display_name":"Blind Room Acoustic Parameters Estimation Using Mobile Audio Transformer","publication_year":2023,"publication_date":"2023-09-15","ids":{"openalex":"https://openalex.org/W4386764837","doi":"https://doi.org/10.1109/waspaa58266.2023.10248186"},"language":"en","primary_location":{"id":"doi:10.1109/waspaa58266.2023.10248186","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa58266.2023.10248186","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","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/A5086089081","display_name":"Shivam Saini","orcid":"https://orcid.org/0009-0002-3981-2260"},"institutions":[{"id":"https://openalex.org/I4210146936","display_name":"Huawei Technologies (United States)","ror":"https://ror.org/03jyqk712","country_code":"US","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210146936"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shivam Saini","raw_affiliation_strings":["Huawei Technologies GmbH,DE","Huawei Technologies GmbH, DE","IKT, Leibniz University, Hannover, DE"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Technologies GmbH,DE","institution_ids":["https://openalex.org/I4210146936"]},{"raw_affiliation_string":"Huawei Technologies GmbH, DE","institution_ids":["https://openalex.org/I4210146936"]},{"raw_affiliation_string":"IKT, Leibniz University, Hannover, DE","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056813963","display_name":"J\u00fcrgen Peissig","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"J\u00fcrgen Peissig","raw_affiliation_strings":["Leibniz University,IKT,Hannover,DE","IKT, Leibniz University, Hannover, DE"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Leibniz University,IKT,Hannover,DE","institution_ids":[]},{"raw_affiliation_string":"IKT, Leibniz University, Hannover, DE","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.4166,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.92256326,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":98},"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/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/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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":0.9977999925613403,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7103944420814514},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5899466276168823},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.549224853515625},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.4633382558822632},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.44490742683410645},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3465292453765869},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.30725550651550293},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.12773504853248596},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10161533951759338}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7103944420814514},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5899466276168823},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.549224853515625},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.4633382558822632},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.44490742683410645},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3465292453765869},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.30725550651550293},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.12773504853248596},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10161533951759338},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/waspaa58266.2023.10248186","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa58266.2023.10248186","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","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":33,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1557831657","https://openalex.org/W2086381917","https://openalex.org/W2172491908","https://openalex.org/W2180309746","https://openalex.org/W2696967604","https://openalex.org/W2736172179","https://openalex.org/W2898519127","https://openalex.org/W2900429685","https://openalex.org/W2901243971","https://openalex.org/W2982059757","https://openalex.org/W2982083293","https://openalex.org/W2990121692","https://openalex.org/W3015235644","https://openalex.org/W3096810680","https://openalex.org/W3099610051","https://openalex.org/W3196974791","https://openalex.org/W3205475937","https://openalex.org/W4224918210","https://openalex.org/W4281756776","https://openalex.org/W4286910290","https://openalex.org/W4287635775","https://openalex.org/W4300978573","https://openalex.org/W4312264056","https://openalex.org/W4312333591","https://openalex.org/W4320459518","https://openalex.org/W6633301432","https://openalex.org/W6770403232","https://openalex.org/W6783938587","https://openalex.org/W6802648153","https://openalex.org/W6839178539","https://openalex.org/W6844713038","https://openalex.org/W6850117044"],"related_works":["https://openalex.org/W1656519308","https://openalex.org/W2042717753","https://openalex.org/W1911859126","https://openalex.org/W2120730869","https://openalex.org/W2541680182","https://openalex.org/W2118508889","https://openalex.org/W2166699153","https://openalex.org/W2109142991","https://openalex.org/W1781713806","https://openalex.org/W2350061705"],"abstract_inverted_index":{"For":[0],"an":[1,10,61,88],"accurate":[2],"representation":[3],"of":[4,22,41,52,87,136],"a":[5,72],"virtual":[6],"sound":[7],"source":[8,28,54],"in":[9,117,134],"Augmented":[11],"Reality":[12],"environment,":[13],"it":[14],"is":[15,29,92],"crucial":[16],"to":[17,30,64,78,107],"understand":[18],"the":[19,23,27,42,50,53,85,102,113,126,130],"acoustic":[20,121],"properties":[21],"current":[24],"room":[25],"where":[26],"be":[31],"rendered.":[32],"Reverberation":[33],"Time":[34],"(RT60)":[35],"and":[36,69,81,110,119,140],"Clarity":[37],"(C50)":[38],"are":[39],"two":[40],"most":[43],"significant":[44],"parameters":[45,67],"that":[46,125],"could":[47],"negatively":[48],"impact":[49],"plausibility":[51],"when":[55],"estimated":[56],"incorrectly.":[57],"We":[58,100],"propose":[59],"using":[60],"audio":[62],"transformer":[63],"estimate":[65],"these":[66],"blindly":[68],"solely":[70],"from":[71],"single-channel":[73],"noisy":[74],"speech":[75],"signal.":[76],"Furthermore,":[77],"ensure":[79],"efficiency":[80],"minimum":[82],"computational":[83],"complexity,":[84,137],"use":[86],"efficient":[89],"lightweight":[90],"architecture":[91],"proposed":[93,103,127],"for":[94,97],"its":[95,108],"suitability":[96],"mobile-friendly":[98],"applications.":[99],"evaluate":[101],"model":[104,128],"with":[105],"regard":[106],"complexity":[109],"accuracy":[111],"against":[112],"existing":[114],"state-of-the-art":[115],"approaches":[116],"unseen":[118],"real":[120],"settings.":[122],"Results":[123],"demonstrate":[124],"surpasses":[129],"traditional":[131],"CNN":[132],"models":[133],"terms":[135],"size,":[138],"speed,":[139],"precision.":[141]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":4}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}