{"id":"https://openalex.org/W3136189587","doi":"https://doi.org/10.23919/eusipco54536.2021.9616044","title":"Blind Estimation of Room Acoustic Parameters and Speech Transmission Index using MTF-based CNNs","display_name":"Blind Estimation of Room Acoustic Parameters and Speech Transmission Index using MTF-based CNNs","publication_year":2021,"publication_date":"2021-08-23","ids":{"openalex":"https://openalex.org/W3136189587","doi":"https://doi.org/10.23919/eusipco54536.2021.9616044","mag":"3136189587"},"language":"en","primary_location":{"id":"doi:10.23919/eusipco54536.2021.9616044","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco54536.2021.9616044","pdf_url":null,"source":{"id":"https://openalex.org/S4363607854","display_name":"2021 29th European Signal Processing Conference (EUSIPCO)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 29th European Signal Processing Conference (EUSIPCO)","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/A5023403634","display_name":"Suradej Duangpummet","orcid":"https://orcid.org/0000-0001-7145-880X"},"institutions":[{"id":"https://openalex.org/I108108428","display_name":"Thammasat University","ror":"https://ror.org/002yp7f20","country_code":"TH","type":"education","lineage":["https://openalex.org/I108108428"]},{"id":"https://openalex.org/I1332092204","display_name":"National Science and Technology Development Agency","ror":"https://ror.org/04vy95b61","country_code":"TH","type":"government","lineage":["https://openalex.org/I1332092204"]},{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]}],"countries":["JP","TH"],"is_corresponding":false,"raw_author_name":"Suradej Duangpummet","raw_affiliation_strings":["National Science and Technology Development Agency, Thailand","School of Information Science, Japan Advanced Institute of Science and Technology, Japan","Sirindhorn International Institute of Technology, Thammasat University, Thailand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Science and Technology Development Agency, Thailand","institution_ids":["https://openalex.org/I1332092204"]},{"raw_affiliation_string":"School of Information Science, Japan Advanced Institute of Science and Technology, Japan","institution_ids":["https://openalex.org/I177738480"]},{"raw_affiliation_string":"Sirindhorn International Institute of Technology, Thammasat University, Thailand","institution_ids":["https://openalex.org/I108108428"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084460378","display_name":"Jessada Karnjana","orcid":"https://orcid.org/0000-0001-9168-0096"},"institutions":[{"id":"https://openalex.org/I1332092204","display_name":"National Science and Technology Development Agency","ror":"https://ror.org/04vy95b61","country_code":"TH","type":"government","lineage":["https://openalex.org/I1332092204"]}],"countries":["TH"],"is_corresponding":false,"raw_author_name":"Jessada Karnjana","raw_affiliation_strings":["National Science and Technology Development Agency, Thailand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Science and Technology Development Agency, Thailand","institution_ids":["https://openalex.org/I1332092204"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068885712","display_name":"Waree Kongprawechnon","orcid":"https://orcid.org/0000-0002-2057-6352"},"institutions":[{"id":"https://openalex.org/I108108428","display_name":"Thammasat University","ror":"https://ror.org/002yp7f20","country_code":"TH","type":"education","lineage":["https://openalex.org/I108108428"]}],"countries":["TH"],"is_corresponding":false,"raw_author_name":"Waree Kongprawechnon","raw_affiliation_strings":["Sirindhorn International Institute of Technology, Thammasat University, Thailand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sirindhorn International Institute of Technology, Thammasat University, Thailand","institution_ids":["https://openalex.org/I108108428"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014199725","display_name":"Masashi Unoki","orcid":"https://orcid.org/0000-0002-6605-2052"},"institutions":[{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masashi Unoki","raw_affiliation_strings":["School of Information Science, Japan Advanced Institute of Science and Technology, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science, Japan Advanced Institute of Science and Technology, Japan","institution_ids":["https://openalex.org/I177738480"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5439,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.59152402,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"181","last_page":"185"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9983000159263611,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9976000189781189,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4801751673221588},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.40783607959747314},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40740156173706055}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4801751673221588},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.40783607959747314},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40740156173706055}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/eusipco54536.2021.9616044","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco54536.2021.9616044","pdf_url":null,"source":{"id":"https://openalex.org/S4363607854","display_name":"2021 29th European Signal Processing Conference (EUSIPCO)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 29th European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G190845862","display_name":null,"funder_award_id":"201605002","funder_id":"https://openalex.org/F4320325628","funder_display_name":"Ministry of Internal Affairs and Communications"}],"funders":[{"id":"https://openalex.org/F4320325628","display_name":"Ministry of Internal Affairs and Communications","ror":"https://ror.org/00vs1pz50"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1594471552","https://openalex.org/W1973279071","https://openalex.org/W2038728370","https://openalex.org/W2154785654","https://openalex.org/W2296434735","https://openalex.org/W2410879554","https://openalex.org/W2889830381","https://openalex.org/W2900429685","https://openalex.org/W2970850616","https://openalex.org/W3010749659","https://openalex.org/W3096810680","https://openalex.org/W4231225162","https://openalex.org/W6660115656","https://openalex.org/W6682502993"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W2350741829","https://openalex.org/W2530322880","https://openalex.org/W1596801655"],"abstract_inverted_index":{"Room":[0],"acoustic":[1],"parameters,":[2,85],"such":[3,21],"as":[4,8,10],"reverberation":[5],"time$(T_{60})$and":[6],"clarity$(C_{80})$,":[7],"well":[9],"the":[11,57,75,80,114,122,142,145],"speech":[12,111,130],"transmission":[13],"index":[14],"(STI),":[15],"are":[16,25,170],"essential":[17],"in":[18,29],"acoustics.":[19],"However,":[20],"parameters":[22,39,124,139,163],"and":[23,48,62,77,82,92,125,137,154,168],"STI":[24,81,126],"difficult":[26],"to":[27,73],"obtain":[28],"everyday":[30],"places":[31],"where":[32],"people":[33],"exist.":[34],"Blind":[35],"estimation":[36],"for":[37,66,103],"those":[38,173],"without":[40],"measuring":[41],"room":[42],"impulse":[43],"response":[44],"(RIR)":[45],"is":[46],"necessary":[47],"challenging.":[49],"This":[50],"paper":[51],"proposes":[52],"a":[53,109],"method":[54],"based":[55],"on":[56],"modulation":[58],"transfer":[59],"function":[60],"(MTF)":[61],"Schroeder's":[63],"RIR":[64],"model":[65],"estimating$T_{60}\\mathrm{s}$in":[67],"seven-octave":[68],"bands.":[69],"The":[70,132,161],"estimated$T_{60}\\mathrm{s}$are":[71],"used":[72],"approximate":[74],"MTF":[76],"RIR.":[78],"Consequently,":[79],"five":[83,123],"room-acoustic":[84],"including$T_{60}$,":[86],"early":[87],"decay":[88],"time":[89],"(EDT),$C_{80}$,":[90],"Deutlichkeit$(D_{50})$,":[91],"center":[93],"time$(T_{s})$,":[94],"can":[95,148],"be":[96,149],"estimated.":[97],"We":[98],"deploy":[99],"convolutional":[100],"neural":[101],"networks":[102],"mapping":[104],"temporal":[105],"amplitude":[106],"envelopes":[107],"of":[108,144],"reverberated":[110,129],"signal":[112],"to$T_{60}\\mathrm{s}$for":[113],"sub-bands.":[115],"Simulations":[116],"were":[117,164],"carried":[118],"out":[119],"by":[120,151],"estimating":[121],"from":[127,175],"unseen":[128],"signals.":[131],"root-mean-square":[133],"errors":[134],"between":[135],"ground-truths":[136],"estimated":[138],"suggest":[140],"that":[141],"accuracy":[143],"estimated$T_{60}$and":[146],"STIs":[147],"improved":[150],"about":[152],"40%":[153],"25%":[155],"compared":[156],"with":[157,172],"previous":[158],"methods,":[159],"respectively.":[160],"other":[162],"also":[165],"correctly":[166],"estimated,":[167],"they":[169],"comparable":[171],"obtained":[174],"standard":[176],"measurements.":[177]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}