{"id":"https://openalex.org/W3161253965","doi":"https://doi.org/10.1109/icassp39728.2021.9415109","title":"SSLIDE: Sound Source Localization for Indoors Based on Deep Learning","display_name":"SSLIDE: Sound Source Localization for Indoors Based on Deep Learning","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3161253965","doi":"https://doi.org/10.1109/icassp39728.2021.9415109","mag":"3161253965"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9415109","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9415109","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5077198276","display_name":"Yifan Wu","orcid":"https://orcid.org/0000-0001-9316-2479"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California, San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yifan Wu","raw_affiliation_strings":["University of California, San Diego, La Jolla, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California, San Diego, La Jolla, CA, USA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055679699","display_name":"Roshan Ayyalasomayajula","orcid":"https://orcid.org/0000-0002-4069-8429"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California, San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Roshan Ayyalasomayajula","raw_affiliation_strings":["University of California, San Diego, La Jolla, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California, San Diego, La Jolla, CA, USA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018064114","display_name":"Michael J. Bianco","orcid":"https://orcid.org/0000-0001-8710-6980"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California, San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael J. Bianco","raw_affiliation_strings":["University of California, San Diego, La Jolla, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California, San Diego, La Jolla, CA, USA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040875765","display_name":"Dinesh Bharadia","orcid":"https://orcid.org/0000-0002-3518-4722"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California, San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dinesh Bharadia","raw_affiliation_strings":["University of California, San Diego, La Jolla, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California, San Diego, La Jolla, CA, USA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004718675","display_name":"Peter Gerstoft","orcid":"https://orcid.org/0000-0002-0471-062X"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California, San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peter Gerstoft","raw_affiliation_strings":["University of California, San Diego, La Jolla, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California, San Diego, La Jolla, CA, USA","institution_ids":["https://openalex.org/I36258959"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5077198276"],"corresponding_institution_ids":["https://openalex.org/I36258959"],"apc_list":null,"apc_paid":null,"fwci":2.4378,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.89655172,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4680","last_page":"4684"},"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":0.9983000159263611,"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":0.9976999759674072,"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":0.7917113304138184},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.7307308912277222},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5638693571090698},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.539036750793457},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5318552851676941},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5117197036743164},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4939897656440735},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.45743873715400696},{"id":"https://openalex.org/keywords/acoustic-source-localization","display_name":"Acoustic source localization","score":0.4538324177265167},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.2575688362121582},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.24054768681526184}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7917113304138184},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.7307308912277222},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5638693571090698},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.539036750793457},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5318552851676941},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5117197036743164},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4939897656440735},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45743873715400696},{"id":"https://openalex.org/C93240960","wikidata":"https://www.wikidata.org/wiki/Q217270","display_name":"Acoustic source localization","level":3,"score":0.4538324177265167},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.2575688362121582},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.24054768681526184},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9415109","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9415109","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1476210933","https://openalex.org/W1494198834","https://openalex.org/W1555217905","https://openalex.org/W1603075283","https://openalex.org/W1772191655","https://openalex.org/W1971920230","https://openalex.org/W1996304098","https://openalex.org/W2011396567","https://openalex.org/W2020107464","https://openalex.org/W2113638573","https://openalex.org/W2114219351","https://openalex.org/W2117678320","https://openalex.org/W2121065047","https://openalex.org/W2146053319","https://openalex.org/W2403149086","https://openalex.org/W2593116425","https://openalex.org/W2663904211","https://openalex.org/W2763188033","https://openalex.org/W2808484484","https://openalex.org/W2810934215","https://openalex.org/W2885219692","https://openalex.org/W2897977894","https://openalex.org/W2902468342","https://openalex.org/W2917065813","https://openalex.org/W2970971581","https://openalex.org/W2989691494","https://openalex.org/W3021789920","https://openalex.org/W3031005739","https://openalex.org/W3094079453","https://openalex.org/W3105475478","https://openalex.org/W4295312788","https://openalex.org/W6678139903","https://openalex.org/W6734260513","https://openalex.org/W6766978945","https://openalex.org/W6941384618"],"related_works":["https://openalex.org/W1656519308","https://openalex.org/W2042717753","https://openalex.org/W2022849831","https://openalex.org/W4226493464","https://openalex.org/W4312417841","https://openalex.org/W3193565141","https://openalex.org/W3133861977","https://openalex.org/W3167935049","https://openalex.org/W3103566983","https://openalex.org/W3029198973"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"SSLIDE,":[3],"Sound":[4],"Source":[5],"Localization":[6],"for":[7,49],"Indoors":[8],"using":[9],"DEep":[10],"learning,":[11],"which":[12],"applies":[13],"deep":[14],"neural":[15,130],"networks":[16],"(DNNs)":[17],"with":[18,25,118],"encoder-decoder":[19],"structure":[20],"to":[21],"localize":[22],"sound":[23,36,51],"sources":[24],"random":[26],"positions":[27],"in":[28,54,134],"a":[29,71,127,141],"continuous":[30],"space.":[31],"The":[32,68],"spatial":[33],"features":[34],"of":[35,60,74],"signals":[37],"received":[38],"by":[39,65,84],"each":[40,55],"microphone":[41],"are":[42],"extracted":[43],"and":[44,86,100,126],"represented":[45],"as":[46],"likelihood":[47],"surfaces":[48],"the":[50,75,81,87,91,98,135],"source":[52,92],"locations":[53],"point.":[56],"Our":[57],"DNN":[58],"consists":[59],"an":[61],"encoder":[62,69],"network":[63,131],"followed":[64],"two":[66],"decoders.":[67],"obtains":[70],"compressed":[72],"representation":[73],"input":[76],"likelihoods.":[77],"One":[78],"decoder":[79,89],"resolves":[80],"multipath":[82],"caused":[83],"reverberation,":[85],"other":[88],"estimates":[90],"location.":[93],"Experiments":[94],"based":[95],"on":[96],"both":[97],"simulated":[99],"experimental":[101],"data":[102],"show":[103],"that":[104],"our":[105],"method":[106],"can":[107],"not":[108],"only":[109],"outperform":[110],"multiple":[111],"signal":[112],"classification":[113],"(MUSIC),":[114],"steered":[115],"response":[116],"power":[117],"phase":[119],"transform":[120],"(SRP-PHAT),":[121],"sparse":[122],"Bayesian":[123],"learning":[124],"(SBL),":[125],"competing":[128],"convolutional":[129],"(CNN)":[132],"approach":[133],"reverberant":[136],"environment":[137],"but":[138],"also":[139],"achieve":[140],"good":[142],"generalization":[143],"performance.":[144]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
