{"id":"https://openalex.org/W3117307355","doi":"https://doi.org/10.1109/mmsp48831.2020.9287131","title":"Time Difference of Arrival Estimation with Deep Learning \u2013 From Acoustic Simulations to Recorded Data","display_name":"Time Difference of Arrival Estimation with Deep Learning \u2013 From Acoustic Simulations to Recorded Data","publication_year":2020,"publication_date":"2020-09-21","ids":{"openalex":"https://openalex.org/W3117307355","doi":"https://doi.org/10.1109/mmsp48831.2020.9287131","mag":"3117307355"},"language":"en","primary_location":{"id":"doi:10.1109/mmsp48831.2020.9287131","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp48831.2020.9287131","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE 22nd International Workshop on Multimedia Signal Processing (MMSP)","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/A5075555953","display_name":"Pasi Pertil\u00e4","orcid":"https://orcid.org/0000-0003-1413-6091"},"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":true,"raw_author_name":"Pasi Pertila","raw_affiliation_strings":["Faculty of Information Technology and Communication Sciences (ITC), Tampere University, Finland"],"affiliations":[{"raw_affiliation_string":"Faculty of Information Technology and Communication Sciences (ITC), Tampere University, Finland","institution_ids":["https://openalex.org/I166825849"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058140225","display_name":"Mikko Parviainen","orcid":"https://orcid.org/0000-0003-2128-8173"},"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":"Mikko Parviainen","raw_affiliation_strings":["Faculty of Information Technology and Communication Sciences (ITC), Tampere University, Finland"],"affiliations":[{"raw_affiliation_string":"Faculty of Information Technology and Communication Sciences (ITC), Tampere University, Finland","institution_ids":["https://openalex.org/I166825849"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029558987","display_name":"Ville Myllyl\u00e4","orcid":"https://orcid.org/0000-0003-3356-3670"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ville Myllyla","raw_affiliation_strings":["Terminal Research & Development, Huawei Technologies, Tampere, Finland"],"affiliations":[{"raw_affiliation_string":"Terminal Research & Development, Huawei Technologies, Tampere, Finland","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022564878","display_name":"Anu Huttunen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anu Huttunen","raw_affiliation_strings":["Terminal Research & Development, Huawei Technologies, Tampere, Finland"],"affiliations":[{"raw_affiliation_string":"Terminal Research & Development, Huawei Technologies, Tampere, Finland","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001433137","display_name":"P. Jarske","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Petri Jarske","raw_affiliation_strings":["Terminal Research & Development, Huawei Technologies, Tampere, Finland"],"affiliations":[{"raw_affiliation_string":"Terminal Research & Development, Huawei Technologies, Tampere, Finland","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5075555953"],"corresponding_institution_ids":["https://openalex.org/I166825849"],"apc_list":null,"apc_paid":null,"fwci":0.3044,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.56848104,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9994000196456909,"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":0.996999979019165,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/multilateration","display_name":"Multilateration","score":0.9100491404533386},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7742936611175537},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.7387174963951111},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.6708875298500061},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.6059293150901794},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4585028290748596},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4425407350063324},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42727744579315186},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.42691928148269653},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.26275020837783813}],"concepts":[{"id":"https://openalex.org/C104037064","wikidata":"https://www.wikidata.org/wiki/Q1640884","display_name":"Multilateration","level":3,"score":0.9100491404533386},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7742936611175537},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.7387174963951111},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.6708875298500061},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.6059293150901794},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4585028290748596},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4425407350063324},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42727744579315186},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.42691928148269653},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.26275020837783813},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/mmsp48831.2020.9287131","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp48831.2020.9287131","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE 22nd International Workshop on Multimedia Signal Processing (MMSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:trepo.tuni.fi:10024/217543","is_oa":false,"landing_page_url":"https://trepo.tuni.fi/handle/10024/217543","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":[{"score":0.5,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1536644969","https://openalex.org/W1565327149","https://openalex.org/W1749787523","https://openalex.org/W1836465849","https://openalex.org/W1882958252","https://openalex.org/W2046317813","https://openalex.org/W2060108923","https://openalex.org/W2104094955","https://openalex.org/W2113638573","https://openalex.org/W2117678320","https://openalex.org/W2128970593","https://openalex.org/W2141411743","https://openalex.org/W2218753925","https://openalex.org/W2526050071","https://openalex.org/W2605102758","https://openalex.org/W2619697695","https://openalex.org/W2701869962","https://openalex.org/W2770501762","https://openalex.org/W2887883376","https://openalex.org/W2889426390","https://openalex.org/W2914484425","https://openalex.org/W2938670253","https://openalex.org/W2939574508","https://openalex.org/W2949117887","https://openalex.org/W2963826681","https://openalex.org/W2995310170","https://openalex.org/W3001121568","https://openalex.org/W3015605759","https://openalex.org/W3106250896","https://openalex.org/W3209141406","https://openalex.org/W4255949318","https://openalex.org/W4300787247","https://openalex.org/W6632049505","https://openalex.org/W6633949838","https://openalex.org/W6638667902","https://openalex.org/W6639480849","https://openalex.org/W6773455346","https://openalex.org/W6785652829","https://openalex.org/W6802983977"],"related_works":["https://openalex.org/W4319862450","https://openalex.org/W1562475690","https://openalex.org/W1488529827","https://openalex.org/W4389082013","https://openalex.org/W1879255185","https://openalex.org/W2188292175","https://openalex.org/W2385053527","https://openalex.org/W1983991597","https://openalex.org/W4386900535","https://openalex.org/W2120442551"],"abstract_inverted_index":{"The":[0,110],"spatial":[1],"information":[2],"about":[3],"a":[4,13,49,120,135],"sound":[5],"source":[6],"is":[7,124,129,193],"carried":[8],"by":[9],"acoustic":[10],"waves":[11],"to":[12,47,52],"microphone":[14],"array":[15],"and":[16,24,43,58,166,171,202],"can":[17,44,60,72,117,207],"be":[18,45],"observed":[19],"through":[20,69],"estimation":[21,151],"of":[22,31,38,90,103,112,147,158,164,198],"phase":[23],"amplitude":[25],"differences":[26],"between":[27,41],"microphones.":[28],"Time":[29],"difference":[30],"arrival":[32],"(TDoA)":[33],"captures":[34],"the":[35,39,54,62,101,145,156,180,189,196,209],"propagation":[36],"delay":[37],"wavefront":[40],"microphones":[42],"used":[46],"steer":[48],"beamformer":[50],"or":[51,100],"localize":[53],"source.":[55],"However,":[56],"reverberation":[57],"interference":[59],"deteriorate":[61],"TDoA":[63,150,183,210],"estimate.":[64],"Deep":[65],"neural":[66],"networks":[67],"(DNNs)":[68],"supervised":[70],"learning":[71],"extract":[73],"speech":[74],"related":[75],"TDoAs":[76],"in":[77,182],"more":[78],"adverse":[79],"conditions":[80],"than":[81],"traditional":[82],"correlation":[83],"-based":[84,149],"methods.Acoustic":[85],"simulations":[86],"provide":[87],"large":[88],"amounts":[89],"data":[91,115,128,133,168,187,204],"with":[92,106,131],"annotations,":[93],"while":[94],"real":[95,132,167,186,203],"recordings":[96],"require":[97],"manual":[98],"annotations":[99],"use":[102,197],"reference":[104],"sensors":[105],"proper":[107],"calibration":[108],"procedures.":[109],"distributions":[111],"these":[113],"two":[114],"sources":[116],"differ.":[118],"When":[119],"DNN":[121,148],"model":[122],"that":[123,195],"trained":[125],"using":[126,188],"simulated":[127,165],"presented":[130],"from":[134],"different":[136,159,190],"distribution,":[137],"its":[138],"performance":[139],"decreases":[140],"if":[141],"not":[142],"properly":[143],"addressed.For":[144],"reduction":[146,181],"error,":[152],"this":[153],"work":[154],"investigates":[155],"role":[157],"input":[160],"normalization":[161,199],"techniques,":[162],"mixing":[163],"for":[169,185],"training,":[170],"applying":[172],"an":[173],"adversarial":[174],"domain":[175],"adaptation":[176],"technique.":[177],"Results":[178],"quantify":[179],"error":[184],"approaches.":[191],"It":[192],"evident":[194],"methods,":[200],"domain-adaptation,":[201],"during":[205],"training":[206],"reduce":[208],"error.":[211]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-03-08T08:50:53.379069","created_date":"2025-10-10T00:00:00"}