{"id":"https://openalex.org/W2888842465","doi":"https://doi.org/10.21437/interspeech.2018-1269","title":"Joint Localization and Classification of Multiple Sound Sources Using a Multi-task Neural Network","display_name":"Joint Localization and Classification of Multiple Sound Sources Using a Multi-task Neural Network","publication_year":2018,"publication_date":"2018-08-28","ids":{"openalex":"https://openalex.org/W2888842465","doi":"https://doi.org/10.21437/interspeech.2018-1269","mag":"2888842465"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2018-1269","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1269","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://infoscience.epfl.ch/record/256280","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103162780","display_name":"Weipeng He","orcid":"https://orcid.org/0000-0002-3874-3083"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Weipeng He","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076409146","display_name":"Petr Motl\u00ed\u010dek","orcid":"https://orcid.org/0000-0001-6467-1119"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Petr Motlicek","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5053358969","display_name":"Jean\u2010Marc Odobez","orcid":"https://orcid.org/0000-0002-9537-9898"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jean-Marc Odobez","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5103162780"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.4766,"has_fulltext":false,"cited_by_count":34,"citation_normalized_percentile":{"value":0.95545005,"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":"312","last_page":"316"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9951000213623047,"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":0.9951000213623047,"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":0.9801999926567078,"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":0.91839998960495,"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":0.7487062811851501},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.7410138249397278},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7137719392776489},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5983862280845642},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.525897204875946},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5179919004440308},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4649084508419037},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3229205906391144},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.15602639317512512},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10683408379554749}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7487062811851501},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.7410138249397278},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7137719392776489},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5983862280845642},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.525897204875946},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5179919004440308},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4649084508419037},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3229205906391144},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.15602639317512512},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10683408379554749},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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":3,"locations":[{"id":"doi:10.21437/interspeech.2018-1269","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1269","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"},{"id":"pmh:oai:infoscience.epfl.ch:256280","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/256280","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://infoscience.epfl.ch/record/256280","raw_type":"Text"},{"id":"pmh:oai:infoscience.epfl.ch:263126","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/263126","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://infoscience.epfl.ch/record/263126","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:infoscience.epfl.ch:256280","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/256280","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://infoscience.epfl.ch/record/256280","raw_type":"Text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2909726438","https://openalex.org/W2067046791","https://openalex.org/W2909888262","https://openalex.org/W2025747832","https://openalex.org/W3020957235","https://openalex.org/W2056769785","https://openalex.org/W1996130883","https://openalex.org/W611303608","https://openalex.org/W2748574964","https://openalex.org/W4313595395"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2],"novel":[3],"multi-task":[4],"neural":[5],"network-based":[6],"approach":[7],"for":[8,34,41],"joint":[9],"sound":[10,54],"source":[11],"localization":[12,45,73,82],"and":[13,29,46,72,83],"speech/non-speech":[14,70],"classification":[15,47,71,84],"in":[16,67],"noisy":[17],"environments.":[18],"The":[19],"network":[20],"takes":[21],"raw":[22],"short":[23],"time":[24],"Fourier":[25],"transform":[26],"as":[27],"input":[28],"outputs":[30],"the":[31,35,42,92,98],"likelihood":[32],"values":[33],"two":[36],"tasks,":[37],"which":[38],"are":[39],"used":[40],"simultaneous":[43],"detection,":[44],"of":[48,52,69,74],"an":[49],"unknown":[50],"number":[51],"overlapping":[53],"sources,":[55,76],"Tested":[56],"with":[57],"real":[58],"recorded":[59],"data,":[60],"our":[61],"method":[62,79],"achieves":[63],"significantly":[64],"better":[65],"performance":[66],"terms":[68],"speech":[75],"compared":[77],"to":[78],"that":[80,90],"performs":[81],"separately.":[85],"In":[86],"addition,":[87],"we":[88],"demonstrate":[89],"incorporating":[91],"temporal":[93],"context":[94],"can":[95],"further":[96],"improve":[97],"performance.":[99]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":10}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
