{"id":"https://openalex.org/W2336830395","doi":"https://doi.org/10.1109/icassp.2016.7471630","title":"Estimating direct-to-reverberant ratio mapped from power spectral density using deep neural network","display_name":"Estimating direct-to-reverberant ratio mapped from power spectral density using deep neural network","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2336830395","doi":"https://doi.org/10.1109/icassp.2016.7471630","mag":"2336830395"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7471630","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7471630","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 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/A5069841141","display_name":"Yusuke Hioka","orcid":"https://orcid.org/0000-0003-3380-9677"},"institutions":[{"id":"https://openalex.org/I154130895","display_name":"University of Auckland","ror":"https://ror.org/03b94tp07","country_code":"NZ","type":"education","lineage":["https://openalex.org/I154130895"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Yusuke Hioka","raw_affiliation_strings":["Department of Mechanical Engineering, University of Auckland, Auckland, New Zealand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering, University of Auckland, Auckland, New Zealand","institution_ids":["https://openalex.org/I154130895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046170826","display_name":"Kenta Niwa","orcid":"https://orcid.org/0000-0002-6911-0238"},"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":"Kenta Niwa","raw_affiliation_strings":["NTT Corporation, NTT Media Intelligence Laboratories, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation, NTT Media Intelligence Laboratories, Tokyo, Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5105,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.62462621,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"2","issue":null,"first_page":"26","last_page":"30"},"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9975000023841858,"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/T10822","display_name":"Acoustic Wave Phenomena Research","score":0.9965000152587891,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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/reverberation","display_name":"Reverberation","score":0.9060506820678711},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6335368752479553},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.6144009828567505},{"id":"https://openalex.org/keywords/spectral-density","display_name":"Spectral density","score":0.60687255859375},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5995627641677856},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.5906270146369934},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5721864104270935},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.5613387823104858},{"id":"https://openalex.org/keywords/signal-to-noise-ratio","display_name":"Signal-to-noise ratio (imaging)","score":0.5369337201118469},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5109378695487976},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4276866316795349},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.41896364092826843},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3872523903846741},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36802369356155396},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.21045538783073425},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.11429288983345032}],"concepts":[{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.9060506820678711},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6335368752479553},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.6144009828567505},{"id":"https://openalex.org/C168110828","wikidata":"https://www.wikidata.org/wiki/Q1331626","display_name":"Spectral density","level":2,"score":0.60687255859375},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5995627641677856},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.5906270146369934},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5721864104270935},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.5613387823104858},{"id":"https://openalex.org/C13944312","wikidata":"https://www.wikidata.org/wiki/Q7512748","display_name":"Signal-to-noise ratio (imaging)","level":2,"score":0.5369337201118469},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5109378695487976},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4276866316795349},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.41896364092826843},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3872523903846741},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36802369356155396},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.21045538783073425},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.11429288983345032},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2016.7471630","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7471630","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:researchspace.auckland.ac.nz:2292/28586","is_oa":false,"landing_page_url":"https://hdl.handle.net/2292/28586","pdf_url":null,"source":{"id":"https://openalex.org/S7407055463","display_name":"ResearchSpace (University of Auckland)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I154130895","host_organization_name":"University of Auckland","host_organization_lineage":["https://openalex.org/I154130895"],"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":"Conference Item"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Life in Land","id":"https://metadata.un.org/sdg/15","score":0.41999998688697815}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1506558619","https://openalex.org/W1546802369","https://openalex.org/W1558898279","https://openalex.org/W1917460721","https://openalex.org/W1974605121","https://openalex.org/W2044617339","https://openalex.org/W2072128103","https://openalex.org/W2099973374","https://openalex.org/W2104695149","https://openalex.org/W2109689830","https://openalex.org/W2116064496","https://openalex.org/W2133923349","https://openalex.org/W2136922672","https://openalex.org/W2145354827","https://openalex.org/W2161336374","https://openalex.org/W2162607306","https://openalex.org/W2172491908","https://openalex.org/W2295687657","https://openalex.org/W4231109964","https://openalex.org/W4249052411","https://openalex.org/W4296927107","https://openalex.org/W6640103097","https://openalex.org/W6683785785"],"related_works":["https://openalex.org/W1562475690","https://openalex.org/W1488529827","https://openalex.org/W4389082013","https://openalex.org/W1879255185","https://openalex.org/W2120442551","https://openalex.org/W2769861442","https://openalex.org/W1980506188","https://openalex.org/W2900122540","https://openalex.org/W4240587264","https://openalex.org/W2011788874"],"abstract_inverted_index":{"A":[0],"new":[1],"attempt":[2],"for":[3],"estimating":[4],"the":[5,11,17,23,32,36,64,71],"direct-to-reverberant":[6],"ratio":[7],"(DRR)":[8],"by":[9],"mapping":[10],"power":[12],"spectral":[13],"density":[14],"(PSD)":[15],"of":[16,52,73],"direct":[18],"sound":[19],"and":[20,76],"reverberation":[21],"using":[22,42,49],"deep":[24],"neural":[25],"network":[26],"is":[27,67],"reported.":[28],"The":[29,46],"method":[30,66],"finds":[31],"correct":[33],"DRR":[34,74],"from":[35],"PSD":[37],"estimated":[38],"with":[39],"an":[40],"algorithm":[41],"a":[43,50,53],"microphone":[44],"array.":[45],"experimental":[47],"results":[48],"recording":[51],"reverberant":[54],"speech":[55],"signal,":[56],"which":[57],"included":[58],"various":[59,79],"environmental":[60],"noise,":[61],"reveal":[62],"that":[63],"proposed":[65],"effective":[68],"in":[69],"improving":[70],"accuracy":[72],"estimation":[75],"robust":[77],"against":[78],"noise.":[80]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}