{"id":"https://openalex.org/W2938515563","doi":"https://doi.org/10.1109/icassp.2019.8682951","title":"Blind Room Volume Estimation from Single-channel Noisy Speech","display_name":"Blind Room Volume Estimation from Single-channel Noisy Speech","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2938515563","doi":"https://doi.org/10.1109/icassp.2019.8682951","mag":"2938515563"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8682951","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682951","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://research.aalto.fi/en/publications/39fd37ce-af0a-4e60-89e3-0caabdc50842","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102747203","display_name":"Andrea Genovese","orcid":"https://orcid.org/0000-0002-7796-0849"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Andrea F. Genovese","raw_affiliation_strings":["New York University, NY, USA"],"affiliations":[{"raw_affiliation_string":"New York University, NY, USA","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036868085","display_name":"Hannes Gamper","orcid":"https://orcid.org/0000-0002-2148-6367"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hannes Gamper","raw_affiliation_strings":["Microsoft Research Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033040947","display_name":"Ville Pulkki","orcid":"https://orcid.org/0000-0003-3460-9677"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Ville Pulkki","raw_affiliation_strings":["Aalto University, Espoo, Finland"],"affiliations":[{"raw_affiliation_string":"Aalto University, Espoo, Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057559622","display_name":"Nikunj Raghuvanshi","orcid":"https://orcid.org/0000-0002-9154-5625"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nikunj Raghuvanshi","raw_affiliation_strings":["Microsoft Research Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007425970","display_name":"Ivan Tashev","orcid":"https://orcid.org/0000-0002-2263-2047"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ivan J. Tashev","raw_affiliation_strings":["Microsoft Research Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5102747203"],"corresponding_institution_ids":["https://openalex.org/I57206974"],"apc_list":null,"apc_paid":null,"fwci":3.0213,"has_fulltext":true,"cited_by_count":34,"citation_normalized_percentile":{"value":0.92027529,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"231","last_page":"235"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9991000294685364,"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":0.9968000054359436,"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":0.7072975039482117},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.679481565952301},{"id":"https://openalex.org/keywords/ranging","display_name":"Ranging","score":0.6306397914886475},{"id":"https://openalex.org/keywords/volume","display_name":"Volume (thermodynamics)","score":0.6226271390914917},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5753370523452759},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5435720086097717},{"id":"https://openalex.org/keywords/estimation-theory","display_name":"Estimation theory","score":0.50297611951828},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.48078006505966187},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.43470901250839233},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.4117394983768463},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.29945600032806396},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.20737504959106445},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1819424331188202},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14622551202774048}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7072975039482117},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.679481565952301},{"id":"https://openalex.org/C115051666","wikidata":"https://www.wikidata.org/wiki/Q6522493","display_name":"Ranging","level":2,"score":0.6306397914886475},{"id":"https://openalex.org/C20556612","wikidata":"https://www.wikidata.org/wiki/Q4469374","display_name":"Volume (thermodynamics)","level":2,"score":0.6226271390914917},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5753370523452759},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5435720086097717},{"id":"https://openalex.org/C167928553","wikidata":"https://www.wikidata.org/wiki/Q1376021","display_name":"Estimation theory","level":2,"score":0.50297611951828},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.48078006505966187},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.43470901250839233},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.4117394983768463},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29945600032806396},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.20737504959106445},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1819424331188202},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14622551202774048},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2019.8682951","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682951","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:aaltodoc.aalto.fi:123456789/38242","is_oa":true,"landing_page_url":"https://research.aalto.fi/en/publications/39fd37ce-af0a-4e60-89e3-0caabdc50842","pdf_url":null,"source":{"id":"https://openalex.org/S4306401662","display_name":"Aaltodoc (Aalto University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9927081","host_organization_name":"Aalto University","host_organization_lineage":["https://openalex.org/I9927081"],"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":null,"raw_type":"acceptedVersion"}],"best_oa_location":{"id":"pmh:oai:aaltodoc.aalto.fi:123456789/38242","is_oa":true,"landing_page_url":"https://research.aalto.fi/en/publications/39fd37ce-af0a-4e60-89e3-0caabdc50842","pdf_url":null,"source":{"id":"https://openalex.org/S4306401662","display_name":"Aaltodoc (Aalto University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9927081","host_organization_name":"Aalto University","host_organization_lineage":["https://openalex.org/I9927081"],"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":null,"raw_type":"acceptedVersion"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W190060899","https://openalex.org/W1522301498","https://openalex.org/W1552481752","https://openalex.org/W1557831657","https://openalex.org/W1608599857","https://openalex.org/W1968834101","https://openalex.org/W1989314204","https://openalex.org/W2074604179","https://openalex.org/W2079751837","https://openalex.org/W2136682440","https://openalex.org/W2144313611","https://openalex.org/W2163605009","https://openalex.org/W2172491908","https://openalex.org/W2219941891","https://openalex.org/W2252509312","https://openalex.org/W2410879554","https://openalex.org/W2513383847","https://openalex.org/W2565077543","https://openalex.org/W2764284591","https://openalex.org/W2801757532","https://openalex.org/W2803981468","https://openalex.org/W2900429685","https://openalex.org/W2964121744","https://openalex.org/W2970850616","https://openalex.org/W3146186587","https://openalex.org/W4231225162","https://openalex.org/W4296927107","https://openalex.org/W6631190155","https://openalex.org/W6633230799","https://openalex.org/W6633301432","https://openalex.org/W6636438496","https://openalex.org/W6684191040","https://openalex.org/W6691759596","https://openalex.org/W6745746767","https://openalex.org/W6929136294"],"related_works":["https://openalex.org/W2783354812","https://openalex.org/W4384112194","https://openalex.org/W2103009189","https://openalex.org/W4312958259","https://openalex.org/W2349383066","https://openalex.org/W1969901537","https://openalex.org/W4328132048","https://openalex.org/W4308259661","https://openalex.org/W1639545646","https://openalex.org/W2376202349"],"abstract_inverted_index":{"Recent":[0],"work":[1],"on":[2],"acoustic":[3,20],"parameter":[4],"estimation":[5],"indicates":[6],"that":[7],"geometric":[8],"room":[9,44],"volume":[10,24,45],"can":[11],"be":[12],"useful":[13],"for":[14,74],"modeling":[15],"the":[16,43,53,71],"character":[17],"of":[18,55,68],"an":[19],"environment.":[21],"However,":[22],"estimating":[23],"from":[25,47,79],"audio":[26],"signals":[27,51],"remains":[28],"a":[29,36,66],"challenging":[30],"problem.":[31],"Here":[32],"we":[33],"propose":[34],"using":[35],"convolutional":[37],"neural":[38],"network":[39],"model":[40,58],"to":[41,61,70,82],"estimate":[42],"blindly":[46],"reverberant":[48],"single-channel":[49],"speech":[50],"in":[52,77],"presence":[54],"noise.":[56],"The":[57],"is":[59],"shown":[60],"produce":[62],"estimates":[63],"within":[64],"approximately":[65],"factor":[67],"two":[69],"true":[72],"value,":[73],"rooms":[75],"ranging":[76],"size":[78],"small":[80],"offices":[81],"large":[83],"concert":[84],"halls.":[85]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":1}],"updated_date":"2026-04-02T15:55:50.835912","created_date":"2025-10-10T00:00:00"}
