{"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":"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/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":true,"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"],"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"],"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"],"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"],"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":4,"corresponding_author_ids":["https://openalex.org/A5023403634"],"corresponding_institution_ids":["https://openalex.org/I108108428","https://openalex.org/I1332092204","https://openalex.org/I177738480"],"apc_list":null,"apc_paid":null,"fwci":0.5161,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.62256548,"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,":[2,101],"such":[3,29],"as":[4,16,18],"reverberation":[5],"time":[6,109,122],"<tex":[7,12,76,84,103,111,116,123,146,183],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[8,13,77,85,104,112,117,124,147,184],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$(T_{60})$</tex>":[9],"and":[10,31,56,70,93,98,120,161,173,186,194,208],"clarity":[11],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$(C_{80})$</tex>":[14],",":[15,106,114,119,126],"well":[17],"the":[19,65,91,96,150,158,178,181],"speech":[20,143,166],"transmission":[21],"index":[22],"(STI),":[23],"are":[24,33,87,210],"essential":[25],"in":[26,37,79],"acoustics.":[27],"However,":[28],"parameters":[30,47,160,175,203],"STI":[32,97,162],"difficult":[34],"to":[35,89,145],"obtain":[36],"everyday":[38],"places":[39],"where":[40],"people":[41],"exist.":[42],"Blind":[43],"estimation":[44],"for":[45,74,135,149],"those":[46,213],"without":[48],"measuring":[49],"room":[50],"impulse":[51],"response":[52],"(RIR)":[53],"is":[54],"necessary":[55],"challenging.":[57],"This":[58],"paper":[59],"proposes":[60],"a":[61,141],"method":[62],"based":[63],"on":[64],"modulation":[66],"transfer":[67],"function":[68],"(MTF)":[69],"Schroeder's":[71],"RIR":[72],"model":[73],"estimating":[75,157],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$T_{60}\\mathrm{s}$</tex>":[78,86,148],"seven-octave":[80],"bands.":[81],"The":[82,168,201],"estimated":[83,174,182],"used":[88],"approximate":[90],"MTF":[92],"RIR.":[94],"Consequently,":[95],"five":[99,159],"room-acoustic":[100],"including":[102],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$T_{60}$</tex>":[105,185],"early":[107],"decay":[108],"(EDT),":[110],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$C_{80}$</tex>":[113],"Deutlichkeit":[115],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$(D_{50})$</tex>":[118],"center":[121],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$(T_{s})$</tex>":[125],"can":[127,188],"be":[128,189],"estimated.":[129],"We":[130],"deploy":[131],"convolutional":[132],"neural":[133],"networks":[134],"mapping":[136],"temporal":[137],"amplitude":[138],"envelopes":[139],"of":[140,180],"reverberated":[142,165],"signal":[144],"sub-bands.":[151],"Simulations":[152],"were":[153,204],"carried":[154],"out":[155],"by":[156,191],"from":[163,215],"unseen":[164],"signals.":[167],"root-mean-square":[169],"errors":[170],"between":[171],"ground-truths":[172],"suggest":[176],"that":[177],"accuracy":[179],"STIs":[187],"improved":[190],"about":[192],"40%":[193],"25%":[195],"compared":[196],"with":[197,212],"previous":[198],"methods,":[199],"respectively.":[200],"other":[202],"also":[205],"correctly":[206],"estimated,":[207],"they":[209],"comparable":[211],"obtained":[214],"standard":[216],"measurements.":[217]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}