{"id":"https://openalex.org/W1603075283","doi":"https://doi.org/10.1109/icassp.2015.7178484","title":"A learning-based approach to direction of arrival estimation in noisy and reverberant environments","display_name":"A learning-based approach to direction of arrival estimation in noisy and reverberant environments","publication_year":2015,"publication_date":"2015-04-01","ids":{"openalex":"https://openalex.org/W1603075283","doi":"https://doi.org/10.1109/icassp.2015.7178484","mag":"1603075283"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2015.7178484","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178484","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5101602536","display_name":"Xiong Xiao","orcid":"https://orcid.org/0009-0001-5128-6518"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Xiong Xiao","raw_affiliation_strings":["Temasek Lab@NTU, Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Temasek Lab@NTU, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103758307","display_name":"Shengkui Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210108443","display_name":"Advanced Digital Sciences Center","ror":"https://ror.org/01xaqx887","country_code":"SG","type":"facility","lineage":["https://openalex.org/I4210108443"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Shengkui Zhao","raw_affiliation_strings":["Advanced Digital Sciences Center, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Digital Sciences Center, Singapore","institution_ids":["https://openalex.org/I4210108443"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100681425","display_name":"Xionghu Zhong","orcid":"https://orcid.org/0000-0002-7533-2347"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Xionghu Zhong","raw_affiliation_strings":["School of Computer Engineering, Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5105462806","display_name":"Douglas L. Jones","orcid":"https://orcid.org/0000-0002-7817-7629"},"institutions":[{"id":"https://openalex.org/I4210108443","display_name":"Advanced Digital Sciences Center","ror":"https://ror.org/01xaqx887","country_code":"SG","type":"facility","lineage":["https://openalex.org/I4210108443"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Douglas L. Jones","raw_affiliation_strings":["Advanced Digital Sciences Center, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Digital Sciences Center, Singapore","institution_ids":["https://openalex.org/I4210108443"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070872826","display_name":"Eng Siong Chng","orcid":"https://orcid.org/0000-0001-6257-7399"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Eng Siong Chng","raw_affiliation_strings":["School of Computer Engineering, Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":"https://orcid.org/0000-0001-9158-9401"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":["Department of Human Language Technology, Institute for Infocomm Research, Singapore","School of Computer Engineering, Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Human Language Technology, Institute for Infocomm Research, Singapore","institution_ids":["https://openalex.org/I3005327000"]},{"raw_affiliation_string":"School of Computer Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":291,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2814","last_page":"2818"},"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/T10931","display_name":"Direction-of-Arrival Estimation Techniques","score":0.9987999796867371,"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/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.9973999857902527,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7505954504013062},{"id":"https://openalex.org/keywords/multilateration","display_name":"Multilateration","score":0.7353967428207397},{"id":"https://openalex.org/keywords/direction-of-arrival","display_name":"Direction of arrival","score":0.7234712839126587},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.6905093193054199},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.614123523235321},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5344411730766296},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5025639533996582},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.4969659149646759},{"id":"https://openalex.org/keywords/multilayer-perceptron","display_name":"Multilayer perceptron","score":0.48641490936279297},{"id":"https://openalex.org/keywords/mean-squared-error","display_name":"Mean squared error","score":0.4855627715587616},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.47362133860588074},{"id":"https://openalex.org/keywords/perceptron","display_name":"Perceptron","score":0.4423426687717438},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.44090554118156433},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41663694381713867},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40931856632232666},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.36703652143478394},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16158053278923035},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.124482661485672},{"id":"https://openalex.org/keywords/azimuth","display_name":"Azimuth","score":0.1169775128364563},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09946408867835999},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07694700360298157}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7505954504013062},{"id":"https://openalex.org/C104037064","wikidata":"https://www.wikidata.org/wiki/Q1640884","display_name":"Multilateration","level":3,"score":0.7353967428207397},{"id":"https://openalex.org/C172051844","wikidata":"https://www.wikidata.org/wiki/Q5280438","display_name":"Direction of arrival","level":3,"score":0.7234712839126587},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.6905093193054199},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.614123523235321},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5344411730766296},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5025639533996582},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.4969659149646759},{"id":"https://openalex.org/C179717631","wikidata":"https://www.wikidata.org/wiki/Q2991667","display_name":"Multilayer perceptron","level":3,"score":0.48641490936279297},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.4855627715587616},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.47362133860588074},{"id":"https://openalex.org/C60908668","wikidata":"https://www.wikidata.org/wiki/Q690207","display_name":"Perceptron","level":3,"score":0.4423426687717438},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.44090554118156433},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41663694381713867},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40931856632232666},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.36703652143478394},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16158053278923035},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.124482661485672},{"id":"https://openalex.org/C159737794","wikidata":"https://www.wikidata.org/wiki/Q124274","display_name":"Azimuth","level":2,"score":0.1169775128364563},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09946408867835999},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07694700360298157},{"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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C21822782","wikidata":"https://www.wikidata.org/wiki/Q131214","display_name":"Antenna (radio)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2015.7178484","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178484","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W126779258","https://openalex.org/W1569512666","https://openalex.org/W1978683583","https://openalex.org/W1989314204","https://openalex.org/W1993678034","https://openalex.org/W2011396567","https://openalex.org/W2046317813","https://openalex.org/W2085156437","https://openalex.org/W2101658087","https://openalex.org/W2103519107","https://openalex.org/W2113638573","https://openalex.org/W2113744809","https://openalex.org/W2117029426","https://openalex.org/W2117678320","https://openalex.org/W2128131274","https://openalex.org/W2128970593","https://openalex.org/W2130722890","https://openalex.org/W2135817141","https://openalex.org/W2139375301","https://openalex.org/W2156642994","https://openalex.org/W2159675447","https://openalex.org/W2168140505","https://openalex.org/W2171000037","https://openalex.org/W2399682411","https://openalex.org/W4206633762","https://openalex.org/W6605165268","https://openalex.org/W6634326339","https://openalex.org/W6677464594","https://openalex.org/W6679230416","https://openalex.org/W6712848690","https://openalex.org/W6941384618"],"related_works":["https://openalex.org/W4319862450","https://openalex.org/W2350404734","https://openalex.org/W3001418501","https://openalex.org/W4389082013","https://openalex.org/W2188292175","https://openalex.org/W2385053527","https://openalex.org/W1983991597","https://openalex.org/W4386900535","https://openalex.org/W2787115139","https://openalex.org/W2898655231"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,68,75,103],"learning-based":[4,69],"approach":[5,70],"to":[6,108,116,182],"the":[7,25,95,110,117,122,136,152,162,183],"task":[8],"of":[9,11,41,44,78,121],"direction":[10],"arrival":[12,45],"estimation":[13,138],"(DOA)":[14],"from":[15,58,74,94,113],"microphone":[16,83],"array":[17,84],"input.":[18],"Traditional":[19],"signal":[20,36],"processing":[21],"methods":[22],"such":[23,114],"as":[24,128],"classic":[26],"least":[27],"square":[28],"(LS)":[29],"method":[30,125,156],"rely":[31],"on":[32,35,147,169],"strong":[33],"assumptions":[34],"models":[37],"and":[38,60,81,101,130,142],"accurate":[39],"estimations":[40],"time":[42],"delay":[43],"(TDOA)":[46],".":[47],"They":[48],"only":[49],"work":[50],"well":[51],"in":[52,173],"relatively":[53],"clean":[54],"conditions,":[55],"but":[56],"suffer":[57],"noise":[59],"reverberation":[61],"distortions.":[62],"In":[63],"this":[64],"paper,":[65],"we":[66,91],"propose":[67],"that":[71,127,151],"can":[72],"learn":[73,109],"large":[76],"amount":[77],"simulated":[79,148],"noisy":[80],"reverberant":[82],"inputs":[85],"for":[86],"robust":[87],"DOA":[88,137],"estimation.":[89],"Specifically,":[90],"extract":[92],"features":[93,115],"generalised":[96],"cross":[97],"correlation":[98],"(GCC)":[99],"vectors":[100],"use":[102],"multilayer":[104],"perceptron":[105],"neural":[106],"network":[107],"nonlinear":[111],"mapping":[112],"DOA.":[118],"One":[119],"advantage":[120],"learning":[123,154],"based":[124,155],"is":[126],"more":[129,131,141,143],"training":[132],"data":[133,149,171],"becomes":[134],"available,":[135],"will":[139],"become":[140],"accurate.":[144],"Experimental":[145],"results":[146,160,168],"show":[150,176],"proposed":[153],"produces":[157],"much":[158],"better":[159],"than":[161],"state-of-the-art":[163],"LS":[164,184],"method.":[165,185],"The":[166],"testing":[167],"real":[170],"recorded":[172],"meeting":[174],"rooms":[175],"improved":[177],"root-mean-square":[178],"error":[179],"(RMSE)":[180],"compared":[181]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":16},{"year":2024,"cited_by_count":25},{"year":2023,"cited_by_count":31},{"year":2022,"cited_by_count":43},{"year":2021,"cited_by_count":44},{"year":2020,"cited_by_count":40},{"year":2019,"cited_by_count":39},{"year":2018,"cited_by_count":26},{"year":2017,"cited_by_count":15},{"year":2016,"cited_by_count":9},{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}