{"id":"https://openalex.org/W4393241166","doi":"https://doi.org/10.1109/taslp.2024.3382504","title":"Speaker Distance Estimation in Enclosures From Single-Channel Audio","display_name":"Speaker Distance Estimation in Enclosures From Single-Channel Audio","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4393241166","doi":"https://doi.org/10.1109/taslp.2024.3382504"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2024.3382504","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3382504","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/10480456.pdf","source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/10480456.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036731350","display_name":"Michael Neri","orcid":"https://orcid.org/0000-0002-6212-9139"},"institutions":[{"id":"https://openalex.org/I119003972","display_name":"Roma Tre University","ror":"https://ror.org/05vf0dg29","country_code":"IT","type":"education","lineage":["https://openalex.org/I119003972"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Michael Neri","raw_affiliation_strings":["Department of Industrial, Electronic, and Mechanical Engineering, Roma Tre University, Rome, Italy"],"raw_orcid":"https://orcid.org/0000-0002-6212-9139","affiliations":[{"raw_affiliation_string":"Department of Industrial, Electronic, and Mechanical Engineering, Roma Tre University, Rome, Italy","institution_ids":["https://openalex.org/I119003972"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010846139","display_name":"Archontis Politis","orcid":"https://orcid.org/0000-0002-0595-2356"},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Archontis Politis","raw_affiliation_strings":["Faculty of Information Technology and Communication Sciences, Tampere University, Tampere, Finland"],"raw_orcid":"https://orcid.org/0000-0002-0595-2356","affiliations":[{"raw_affiliation_string":"Faculty of Information Technology and Communication Sciences, Tampere University, Tampere, Finland","institution_ids":["https://openalex.org/I166825849"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025199613","display_name":"Daniel Krause","orcid":"https://orcid.org/0000-0003-2704-636X"},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Daniel Aleksander Krause","raw_affiliation_strings":["Faculty of Information Technology and Communication Sciences, Tampere University, Tampere, Finland"],"raw_orcid":"https://orcid.org/0000-0003-2704-636X","affiliations":[{"raw_affiliation_string":"Faculty of Information Technology and Communication Sciences, Tampere University, Tampere, Finland","institution_ids":["https://openalex.org/I166825849"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028830723","display_name":"Marco Carli","orcid":"https://orcid.org/0000-0002-7489-3767"},"institutions":[{"id":"https://openalex.org/I119003972","display_name":"Roma Tre University","ror":"https://ror.org/05vf0dg29","country_code":"IT","type":"education","lineage":["https://openalex.org/I119003972"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Marco Carli","raw_affiliation_strings":["Department of Industrial, Electronic, and Mechanical Engineering, Roma Tre University, Rome, Italy"],"raw_orcid":"https://orcid.org/0000-0002-7489-3767","affiliations":[{"raw_affiliation_string":"Department of Industrial, Electronic, and Mechanical Engineering, Roma Tre University, Rome, Italy","institution_ids":["https://openalex.org/I119003972"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049691461","display_name":"Tuomas Virtanen","orcid":"https://orcid.org/0000-0002-4604-9729"},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Tuomas Virtanen","raw_affiliation_strings":["Faculty of Information Technology and Communication Sciences, Tampere University, Tampere, Finland"],"raw_orcid":"https://orcid.org/0000-0002-4604-9729","affiliations":[{"raw_affiliation_string":"Faculty of Information Technology and Communication Sciences, Tampere University, Tampere, Finland","institution_ids":["https://openalex.org/I166825849"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5036731350"],"corresponding_institution_ids":["https://openalex.org/I119003972"],"apc_list":null,"apc_paid":null,"fwci":6.5764,"has_fulltext":true,"cited_by_count":20,"citation_normalized_percentile":{"value":0.97460637,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"32","issue":null,"first_page":"2242","last_page":"2254"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9962999820709229,"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":0.9962999820709229,"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":0.9731000065803528,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9304999709129333,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/channel","display_name":"Channel (broadcasting)","score":0.7132043838500977},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5514534115791321},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4823133945465088},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.30327844619750977}],"concepts":[{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.7132043838500977},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5514534115791321},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4823133945465088},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.30327844619750977}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/taslp.2024.3382504","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3382504","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/10480456.pdf","source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2403.17514","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.17514","pdf_url":"https://arxiv.org/pdf/2403.17514","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"pmh:oai:iris.uniroma3.it:11590/469287","is_oa":true,"landing_page_url":"https://hdl.handle.net/11590/469287","pdf_url":null,"source":{"id":"https://openalex.org/S4377196120","display_name":"Iris (Roma Tre University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I119003972","host_organization_name":"Roma Tre University","host_organization_lineage":["https://openalex.org/I119003972"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:trepo.tuni.fi:10024/227077","is_oa":true,"landing_page_url":"https://trepo.tuni.fi/handle/10024/227077","pdf_url":null,"source":{"id":"https://openalex.org/S7407055260","display_name":"Trepo - Institutional Repository of Tampere University","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":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/taslp.2024.3382504","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3382504","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/10480456.pdf","source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4393241166.pdf","grobid_xml":"https://content.openalex.org/works/W4393241166.grobid-xml"},"referenced_works_count":53,"referenced_works":["https://openalex.org/W126779258","https://openalex.org/W1967178846","https://openalex.org/W1968834101","https://openalex.org/W1978659076","https://openalex.org/W1993329755","https://openalex.org/W2022347952","https://openalex.org/W2041491517","https://openalex.org/W2043217973","https://openalex.org/W2070126272","https://openalex.org/W2082120918","https://openalex.org/W2109689830","https://openalex.org/W2133923349","https://openalex.org/W2137418464","https://openalex.org/W2162607306","https://openalex.org/W2163013496","https://openalex.org/W2541714600","https://openalex.org/W2565911560","https://openalex.org/W2567880309","https://openalex.org/W2794209590","https://openalex.org/W2800383133","https://openalex.org/W2810934215","https://openalex.org/W2899564885","https://openalex.org/W2901920206","https://openalex.org/W2903426563","https://openalex.org/W2933305660","https://openalex.org/W2938901746","https://openalex.org/W2972541922","https://openalex.org/W2982341288","https://openalex.org/W2997297221","https://openalex.org/W3000352666","https://openalex.org/W3032514799","https://openalex.org/W3104896896","https://openalex.org/W3127686677","https://openalex.org/W3144042318","https://openalex.org/W3186050523","https://openalex.org/W3202467894","https://openalex.org/W4205221070","https://openalex.org/W4206633762","https://openalex.org/W4296070366","https://openalex.org/W4307782669","https://openalex.org/W4312920378","https://openalex.org/W4313061427","https://openalex.org/W4315926819","https://openalex.org/W4385245566","https://openalex.org/W4386763492","https://openalex.org/W4390096820","https://openalex.org/W6605165268","https://openalex.org/W6685562342","https://openalex.org/W6729017730","https://openalex.org/W6757154246","https://openalex.org/W6801320650","https://openalex.org/W6838853441","https://openalex.org/W6853532597"],"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/W4391913857","https://openalex.org/W2350741829","https://openalex.org/W2530322880"],"abstract_inverted_index":{"Distance":[0],"estimation":[1,72],"from":[2,73],"audio":[3,74,121],"plays":[4],"a":[5,28,66,77,167],"crucial":[6],"role":[7],"in":[8,61,123,166,182,189],"various":[9],"applications,":[10],"such":[11],"as":[12],"acoustic":[13],"scene":[14],"analysis,":[15],"sound":[16,55],"source":[17,56],"localization,":[18],"and":[19,42,97,140,151,197,217],"room":[20,132],"modeling.":[21],"Most":[22],"studies":[23],"predominantly":[24],"center":[25],"on":[26,49,94,143],"employing":[27],"classification":[29],"approach,":[30],"where":[31,193],"distances":[32],"are":[33,199],"discretized":[34],"into":[35],"distinct":[36],"categories,":[37],"enabling":[38],"smoother":[39],"model":[40,91,158],"training":[41],"achieving":[43],"higher":[44],"accuracy":[45],"but":[46],"imposing":[47],"restrictions":[48],"the":[50,53,90,110,157,172,183,190],"precision":[51],"of":[52,112,129,163,178,205],"obtained":[54],"position.":[57],"Towards":[58],"this":[59,62],"direction,":[60],"paper":[63],"we":[64,116,213],"propose":[65],"novel":[67],"approach":[68],"for":[69],"continuous":[70],"distance":[71],"signals":[75],"using":[76,120],"convolutional":[78],"recurrent":[79],"neural":[80],"network":[81],"with":[82,126,137],"an":[83,160,175,202],"attention":[84,87],"module.":[85],"The":[86,186],"mechanism":[88],"enables":[89],"to":[92,103],"focus":[93],"relevant":[95],"temporal":[96],"spectral":[98],"features,":[99],"enhancing":[100],"its":[101],"ability":[102],"capture":[104],"fine-grained":[105],"distance-related":[106],"information.":[107],"To":[108],"evaluate":[109],"effectiveness":[111],"our":[113],"proposed":[114],"method,":[115],"conduct":[117],"extensive":[118],"experiments":[119],"recordings":[122],"controlled":[124],"environments":[125],"three":[127],"levels":[128],"realism":[130],"(synthetic":[131],"impulse":[133],"response,":[134],"measured":[135],"response":[136],"convolved":[138],"speech,":[139],"real":[141,191],"recordings)":[142],"four":[144],"datasets":[145,219],"(our":[146],"synthetic":[147,169,218],"dataset,":[148],"QMULTIMIT,":[149],"VoiceHome-2,":[150],"STARSS23).":[152],"Experimental":[153],"results":[154,173],"show":[155],"that":[156],"achieves":[159],"absolute":[161,176,203],"error":[162,177,204],"0.11":[164],"meters":[165,181],"noiseless":[168],"scenario.":[170,185],"Moreover,":[171],"showed":[174],"about":[179],"1.30":[180],"hybrid":[184],"algorithm's":[187],"performance":[188],"scenario,":[192],"unpredictable":[194],"environmental":[195],"factors":[196],"noise":[198],"prevalent,":[200],"yields":[201],"approximately":[206],"0.50":[207],"meters.":[208],"For":[209],"reproducible":[210],"research":[211],"purposes":[212],"make":[214],"model,":[215],"code,":[216],"available":[220],"at":[221],"https://github.com/michaelneri/audio-distance-estimation":[222]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":16},{"year":2024,"cited_by_count":3}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}