{"id":"https://openalex.org/W4386763492","doi":"https://doi.org/10.1109/waspaa58266.2023.10248087","title":"Single-Channel Speaker Distance Estimation in Reverberant Environments","display_name":"Single-Channel Speaker Distance Estimation in Reverberant Environments","publication_year":2023,"publication_date":"2023-09-15","ids":{"openalex":"https://openalex.org/W4386763492","doi":"https://doi.org/10.1109/waspaa58266.2023.10248087"},"language":"en","primary_location":{"id":"doi:10.1109/waspaa58266.2023.10248087","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa58266.2023.10248087","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","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/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":["Roma Tre University,Department of Industrial, Electronic, and Mechanical Engineering,Rome","Department of Industrial, Electronic, and Mechanical Engineering, Roma Tre University, Rome"],"affiliations":[{"raw_affiliation_string":"Roma Tre University,Department of Industrial, Electronic, and Mechanical Engineering,Rome","institution_ids":["https://openalex.org/I119003972"]},{"raw_affiliation_string":"Department of Industrial, Electronic, and Mechanical Engineering, Roma Tre University, Rome","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":["Tampere University,Faculty of Information Technology and Communication Sciences,Tampere","Faculty of Information Technology and Communication Sciences, Tampere University, Tampere"],"affiliations":[{"raw_affiliation_string":"Tampere University,Faculty of Information Technology and Communication Sciences,Tampere","institution_ids":["https://openalex.org/I166825849"]},{"raw_affiliation_string":"Faculty of Information Technology and Communication Sciences, Tampere University, Tampere","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 Krause","raw_affiliation_strings":["Tampere University,Faculty of Information Technology and Communication Sciences,Tampere","Faculty of Information Technology and Communication Sciences, Tampere University, Tampere"],"affiliations":[{"raw_affiliation_string":"Tampere University,Faculty of Information Technology and Communication Sciences,Tampere","institution_ids":["https://openalex.org/I166825849"]},{"raw_affiliation_string":"Faculty of Information Technology and Communication Sciences, Tampere University, Tampere","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":["Roma Tre University,Department of Industrial, Electronic, and Mechanical Engineering,Rome","Department of Industrial, Electronic, and Mechanical Engineering, Roma Tre University, Rome"],"affiliations":[{"raw_affiliation_string":"Roma Tre University,Department of Industrial, Electronic, and Mechanical Engineering,Rome","institution_ids":["https://openalex.org/I119003972"]},{"raw_affiliation_string":"Department of Industrial, Electronic, and Mechanical Engineering, Roma Tre University, Rome","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":["Tampere University,Faculty of Information Technology and Communication Sciences,Tampere","Faculty of Information Technology and Communication Sciences, Tampere University, Tampere"],"affiliations":[{"raw_affiliation_string":"Tampere University,Faculty of Information Technology and Communication Sciences,Tampere","institution_ids":["https://openalex.org/I166825849"]},{"raw_affiliation_string":"Faculty of Information Technology and Communication Sciences, Tampere University, Tampere","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":1.345,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.81854165,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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/T11309","display_name":"Music and Audio Processing","score":0.9987000226974487,"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":0.998199999332428,"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":0.7814655303955078},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.7291253209114075},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.6814463138580322},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5931509137153625},{"id":"https://openalex.org/keywords/multilateration","display_name":"Multilateration","score":0.5537279844284058},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5490421056747437},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5214495062828064},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.49702194333076477},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.48692405223846436},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.47990405559539795},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4715476334095001},{"id":"https://openalex.org/keywords/background-noise","display_name":"Background noise","score":0.4577223062515259},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45766499638557434},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4568212628364563},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.45320984721183777},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4399097263813019},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36247608065605164},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.3309425711631775},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.18007171154022217},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.15845417976379395},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10239747166633606},{"id":"https://openalex.org/keywords/sound-pressure","display_name":"Sound pressure","score":0.09792295098304749}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7814655303955078},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.7291253209114075},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.6814463138580322},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5931509137153625},{"id":"https://openalex.org/C104037064","wikidata":"https://www.wikidata.org/wiki/Q1640884","display_name":"Multilateration","level":3,"score":0.5537279844284058},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5490421056747437},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5214495062828064},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.49702194333076477},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.48692405223846436},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.47990405559539795},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4715476334095001},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.4577223062515259},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45766499638557434},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4568212628364563},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.45320984721183777},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4399097263813019},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36247608065605164},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.3309425711631775},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.18007171154022217},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.15845417976379395},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10239747166633606},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.09792295098304749},{"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/waspaa58266.2023.10248087","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa58266.2023.10248087","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"},{"id":"pmh:oai:iris.uniroma3.it:11590/456327","is_oa":false,"landing_page_url":"https://hdl.handle.net/11590/456327","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:trepo.tuni.fi:10024/208862","is_oa":false,"landing_page_url":"https://trepo.tuni.fi/handle/10024/208862","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1965159237","https://openalex.org/W1967178846","https://openalex.org/W1991139021","https://openalex.org/W1993329755","https://openalex.org/W2005679925","https://openalex.org/W2109689830","https://openalex.org/W2120442551","https://openalex.org/W2133923349","https://openalex.org/W2157252316","https://openalex.org/W2162607306","https://openalex.org/W2163013496","https://openalex.org/W2176412452","https://openalex.org/W2207100718","https://openalex.org/W2541714600","https://openalex.org/W2561713757","https://openalex.org/W2794209590","https://openalex.org/W2810934215","https://openalex.org/W2963285578","https://openalex.org/W2972541922","https://openalex.org/W2982341288","https://openalex.org/W2997297221","https://openalex.org/W3000352666","https://openalex.org/W3104896896","https://openalex.org/W3113688134","https://openalex.org/W3127686677","https://openalex.org/W3171278394","https://openalex.org/W3186050523","https://openalex.org/W4296070366","https://openalex.org/W4307694777","https://openalex.org/W4307782669","https://openalex.org/W4312920378","https://openalex.org/W6678141335","https://openalex.org/W6688315975","https://openalex.org/W6729017730","https://openalex.org/W6789826613","https://openalex.org/W6801320650"],"related_works":["https://openalex.org/W2017747885","https://openalex.org/W4205598619","https://openalex.org/W2026749086","https://openalex.org/W2060436938","https://openalex.org/W2086623225","https://openalex.org/W585264039","https://openalex.org/W1491017269","https://openalex.org/W2515660636","https://openalex.org/W4229917028","https://openalex.org/W2184591685"],"abstract_inverted_index":{"We":[0],"introduce":[1],"the":[2,27,53,58,71,103,106,114,122,130,138,141],"novel":[3,30],"task":[4],"of":[5,57,73,84,105,113,116,140],"continuous-valued":[6],"speaker":[7,35],"distance":[8,36],"estimation":[9],"which":[10],"focuses":[11],"on":[12,23,70],"estimating":[13,34],"non-discrete":[14],"distances":[15],"between":[16,132],"a":[17,41,62,93,111],"sound":[18],"source":[19],"and":[20,55,134],"microphone,":[21],"based":[22],"audio":[24,59],"captured":[25],"by":[26,82],"microphone.":[28],"A":[29],"learning-based":[31],"approach":[32],"for":[33],"in":[37,68,75],"reverberant":[38],"environments":[39],"from":[40,92,121],"single":[42],"omnidirectional":[43],"microphone":[44],"is":[45,99],"proposed.":[46],"Using":[47],"common":[48],"acoustic":[49],"features,":[50],"such":[51],"as":[52],"magnitude":[54],"phase":[56],"spectrogram,":[60],"with":[61,89],"convolutional":[63],"recurrent":[64],"neural":[65],"network":[66],"results":[67],"errors":[69],"order":[72],"centimeters":[74],"noiseless":[76,135],"audios.":[77],"Experiments":[78],"are":[79],"carried":[80],"out":[81],"means":[83],"an":[85],"image-source":[86],"room":[87],"simulator":[88],"convolved":[90],"speeches":[91],"public":[94],"dataset.":[95],"An":[96],"ablation":[97],"study":[98,112],"performed":[100],"to":[101],"demonstrate":[102],"effectiveness":[104],"proposed":[107],"feature":[108],"set.":[109],"Finally,":[110],"impact":[115],"real":[117],"background":[118],"noise,":[119],"extracted":[120],"WHAM!":[123],"dataset":[124],"at":[125],"different":[126],"signal-to-noise":[127],"ratios":[128],"highlights":[129],"discrepancy":[131],"noisy":[133],"scenarios,":[136],"underlining":[137],"difficulty":[139],"problem.":[142]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}