{"id":"https://openalex.org/W2996766320","doi":"https://doi.org/10.1109/aivr46125.2019.00039","title":"Extracting Specific Voice from Mixed Audio Source","display_name":"Extracting Specific Voice from Mixed Audio Source","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W2996766320","doi":"https://doi.org/10.1109/aivr46125.2019.00039","mag":"2996766320"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/aivr46125.2019.00039","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-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/A5109545869","display_name":"Kunihiko Sato","orcid":null},"institutions":[{"id":"https://openalex.org/I4210096607","display_name":"Line Corporation (Japan)","ror":"https://ror.org/00qg8pm87","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210096607","https://openalex.org/I60922564"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Kunihiko Sato","raw_affiliation_strings":["LINE Corporation, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"LINE Corporation, Tokyo, Japan","institution_ids":["https://openalex.org/I4210096607"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5109545869"],"corresponding_institution_ids":["https://openalex.org/I4210096607"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":0,"max":62},"biblio":{"volume":"36","issue":null,"first_page":"187","last_page":"1873"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech Enhancement Techniques","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 Enhancement Techniques","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":"Audio Signal Classification and Analysis","score":0.9991,"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/T10283","display_name":"Impact of Hearing Loss on Cognitive Function","score":0.9958,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/source-separation","display_name":"Source Separation","score":0.583394},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker Verification","score":0.569314},{"id":"https://openalex.org/keywords/audio-event-detection","display_name":"Audio Event Detection","score":0.566494},{"id":"https://openalex.org/keywords/environmental-sound-recognition","display_name":"Environmental Sound Recognition","score":0.554989},{"id":"https://openalex.org/keywords/speaker-diarization","display_name":"Speaker Diarization","score":0.554739},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.48108885},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.41605482},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.41022944}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7869329},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7752949},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.6875267},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.61995},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5563219},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.51061064},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.48108885},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.45691735},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4218365},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.41656},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.41605482},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.41022944},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36626494},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.18368798},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.15668228},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"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}],"mesh":[],"locations_count":1,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/aivr46125.2019.00039","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.63,"display_name":"Quality education","id":"https://metadata.un.org/sdg/4"}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":29,"referenced_works":["https://openalex.org/W1983108229","https://openalex.org/W2221409856","https://openalex.org/W2460742184","https://openalex.org/W2465050681","https://openalex.org/W2499182527","https://openalex.org/W2552071709","https://openalex.org/W2594251744","https://openalex.org/W2661910912","https://openalex.org/W2687223163","https://openalex.org/W2698117193","https://openalex.org/W2724657720","https://openalex.org/W2738588019","https://openalex.org/W2745634895","https://openalex.org/W2747161606","https://openalex.org/W2749679082","https://openalex.org/W2805553723","https://openalex.org/W2942368658","https://openalex.org/W2950862326","https://openalex.org/W2951295643","https://openalex.org/W2962715207","https://openalex.org/W2963103134","https://openalex.org/W2963341071","https://openalex.org/W2963828919","https://openalex.org/W2970011264","https://openalex.org/W3123318516","https://openalex.org/W3127686677","https://openalex.org/W4232282348","https://openalex.org/W4289665794","https://openalex.org/W95152782"],"related_works":["https://openalex.org/W4375869276","https://openalex.org/W3030102128","https://openalex.org/W2568425241","https://openalex.org/W2376606440","https://openalex.org/W2373767407","https://openalex.org/W2251439150","https://openalex.org/W2187949121","https://openalex.org/W2135485548","https://openalex.org/W2077498359","https://openalex.org/W1127445803"],"abstract_inverted_index":{"We":[0,43],"propose":[1],"auditory":[2],"diminished":[3],"reality":[4],"by":[5],"a":[6,12,17,34,71],"deep":[7],"neural":[8],"network":[9],"(DNN)":[10],"extracting":[11],"single":[13],"speech":[14,93],"signal":[15],"from":[16],"mixture":[18],"of":[19,38,52,61,67,89],"sounds":[20],"containing":[21],"other":[22],"speakers":[23],"and":[24,40,86],"background":[25],"noise.":[26],"To":[27],"realize":[28],"the":[29,48,53,58,81,90],"proposed":[30],"DNN,":[31],"we":[32,56,73],"introduce":[33],"new":[35],"dataset":[36],"comprised":[37],"multi-speakers":[39],"environment":[41],"noises.":[42],"conduct":[44],"evaluations":[45],"for":[46,95],"measuring":[47],"source":[49],"separation":[50,59,82],"quality":[51,60,83],"DNN.":[54],"Additionally,":[55],"compare":[57],"models":[62],"learned":[63],"with":[64],"different":[65],"amounts":[66],"training":[68,96],"data.":[69,97],"As":[70],"result,":[72],"found":[74],"there":[75],"is":[76],"no":[77],"significant":[78],"difference":[79],"in":[80],"between":[84],"10":[85],"30":[87],"minutes":[88],"target":[91],"speaker's":[92],"length":[94]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2996766320","counts_by_year":[],"updated_date":"2024-10-18T10:24:31.878872","created_date":"2020-01-10"}