{"id":"https://openalex.org/W3011890046","doi":"https://doi.org/10.1109/icassp40776.2020.9054090","title":"Raw Waveform Based End-to-end Deep Convolutional Network for Spatial Localization of Multiple Acoustic Sources","display_name":"Raw Waveform Based End-to-end Deep Convolutional Network for Spatial Localization of Multiple Acoustic Sources","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3011890046","doi":"https://doi.org/10.1109/icassp40776.2020.9054090","mag":"3011890046"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054090","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054090","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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/A5041146903","display_name":"Harshavardhan Sundar","orcid":"https://orcid.org/0000-0002-8305-7701"},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Harshavardhan Sundar","raw_affiliation_strings":["Amazon.com Inc"],"affiliations":[{"raw_affiliation_string":"Amazon.com Inc","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101432591","display_name":"Weiran Wang","orcid":"https://orcid.org/0009-0000-0843-707X"},"institutions":[{"id":"https://openalex.org/I4210155268","display_name":"Salesforce (United States)","ror":"https://ror.org/057315g56","country_code":"US","type":"company","lineage":["https://openalex.org/I4210155268"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Weiran Wang","raw_affiliation_strings":["Salesforce Research"],"affiliations":[{"raw_affiliation_string":"Salesforce Research","institution_ids":["https://openalex.org/I4210155268"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100755311","display_name":"Ming Sun","orcid":"https://orcid.org/0000-0002-5948-2708"},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ming Sun","raw_affiliation_strings":["Amazon.com Inc"],"affiliations":[{"raw_affiliation_string":"Amazon.com Inc","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100406950","display_name":"Chao Wang","orcid":"https://orcid.org/0000-0002-1560-6182"},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Chao Wang","raw_affiliation_strings":["Amazon.com Inc"],"affiliations":[{"raw_affiliation_string":"Amazon.com Inc","institution_ids":["https://openalex.org/I4210089985"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5041146903"],"corresponding_institution_ids":["https://openalex.org/I4210089985"],"apc_list":null,"apc_paid":null,"fwci":4.3945,"has_fulltext":false,"cited_by_count":42,"citation_normalized_percentile":{"value":0.95279789,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4642","last_page":"4646"},"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":0.9997000098228455,"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":0.9951000213623047,"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/computer-science","display_name":"Computer science","score":0.7800971269607544},{"id":"https://openalex.org/keywords/multilateration","display_name":"Multilateration","score":0.7518703937530518},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.592896580696106},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.5919321775436401},{"id":"https://openalex.org/keywords/permutation","display_name":"Permutation (music)","score":0.5766353607177734},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5529525279998779},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5057792663574219},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5045348405838013},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.49019676446914673},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4880189001560211},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4764723777770996},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.43774041533470154},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.36908257007598877},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3349332809448242},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10168623924255371},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09841972589492798},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.09039682149887085}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7800971269607544},{"id":"https://openalex.org/C104037064","wikidata":"https://www.wikidata.org/wiki/Q1640884","display_name":"Multilateration","level":3,"score":0.7518703937530518},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.592896580696106},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.5919321775436401},{"id":"https://openalex.org/C21308566","wikidata":"https://www.wikidata.org/wiki/Q7169365","display_name":"Permutation (music)","level":2,"score":0.5766353607177734},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5529525279998779},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5057792663574219},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5045348405838013},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.49019676446914673},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4880189001560211},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4764723777770996},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.43774041533470154},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.36908257007598877},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3349332809448242},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10168623924255371},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09841972589492798},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.09039682149887085},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"id":"https://openalex.org/C159737794","wikidata":"https://www.wikidata.org/wiki/Q124274","display_name":"Azimuth","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054090","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054090","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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":44,"referenced_works":["https://openalex.org/W5385147","https://openalex.org/W66588809","https://openalex.org/W79622236","https://openalex.org/W126779258","https://openalex.org/W1493595169","https://openalex.org/W1495086638","https://openalex.org/W1836465849","https://openalex.org/W1964509330","https://openalex.org/W1969299255","https://openalex.org/W1988904709","https://openalex.org/W2046317813","https://openalex.org/W2090020898","https://openalex.org/W2101315693","https://openalex.org/W2117678320","https://openalex.org/W2119642783","https://openalex.org/W2121756139","https://openalex.org/W2128562854","https://openalex.org/W2128970593","https://openalex.org/W2129821199","https://openalex.org/W2130989868","https://openalex.org/W2149900846","https://openalex.org/W2160557558","https://openalex.org/W2166320821","https://openalex.org/W2170393302","https://openalex.org/W2403149086","https://openalex.org/W2771922328","https://openalex.org/W2772736377","https://openalex.org/W2810087991","https://openalex.org/W2884822476","https://openalex.org/W2888793942","https://openalex.org/W2910096450","https://openalex.org/W2935162632","https://openalex.org/W2949117887","https://openalex.org/W2964342924","https://openalex.org/W3125848009","https://openalex.org/W3127686677","https://openalex.org/W6600202591","https://openalex.org/W6605165268","https://openalex.org/W6629645474","https://openalex.org/W6638667902","https://openalex.org/W6679438253","https://openalex.org/W6746576432","https://openalex.org/W6746809379","https://openalex.org/W6917638038"],"related_works":["https://openalex.org/W2380293945","https://openalex.org/W1972023576","https://openalex.org/W1500522817","https://openalex.org/W1974812937","https://openalex.org/W3095239554","https://openalex.org/W3212409750","https://openalex.org/W1541088746","https://openalex.org/W1976761755","https://openalex.org/W2023873321","https://openalex.org/W2043541782"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"present":[4],"an":[5,81],"end-to-end":[6,82],"deep":[7,28],"convolutional":[8],"neural":[9],"network":[10],"operating":[11],"on":[12,94],"multi-channel":[13,41],"raw":[14],"audio":[15],"data":[16,97],"to":[17,48,53,65,113],"localize":[18,49],"multiple":[19,50,71,78,127],"simultaneously":[20],"active":[21],"acoustic":[22],"sources":[23,51,79],"in":[24,34,80,132],"space.":[25],"Previously":[26],"reported":[27,131],"learning":[29],"based":[30,126],"approaches":[31],"work":[32],"well":[33,55,112],"localizing":[35],"a":[36,61,95,119],"single":[37],"source":[38,128],"directly":[39],"from":[40,102],"raw-audio,":[42],"but":[43],"are":[44],"not":[45],"easily":[46],"extendable":[47],"due":[52],"the":[54,67,85,103,108,133],"known":[56],"permutation":[57,86],"problem.":[58],"We":[59],"propose":[60],"novel":[62],"encoding":[63],"scheme":[64],"represent":[66],"spatial":[68,91],"coordinates":[69],"of":[70,77,123],"sources,":[72],"which":[73],"facilitates":[74],"2D":[75],"localization":[76,129],"fashion,":[83],"avoiding":[84],"problem":[87],"and":[88,99,117],"achieving":[89],"arbitrary":[90],"resolution.":[92],"Experiments":[93],"simulated":[96],"set":[98],"real":[100],"recordings":[101],"AV16.3":[104],"Corpus":[105],"demonstrate":[106],"that":[107],"proposed":[109],"method":[110],"generalizes":[111],"unseen":[114],"test":[115],"conditions,":[116],"outperforms":[118],"recent":[120],"time":[121],"difference":[122],"arrival":[124],"(TDOA)":[125],"approach":[130],"literature.":[134]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":13},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}