{"id":"https://openalex.org/W2563215737","doi":"https://doi.org/10.1109/globalsip.2016.7905846","title":"Low-latency sound source separation using deep neural networks","display_name":"Low-latency sound source separation using deep neural networks","publication_year":2016,"publication_date":"2016-12-01","ids":{"openalex":"https://openalex.org/W2563215737","doi":"https://doi.org/10.1109/globalsip.2016.7905846","mag":"2563215737"},"language":"en","primary_location":{"id":"doi:10.1109/globalsip.2016.7905846","is_oa":false,"landing_page_url":"https://doi.org/10.1109/globalsip.2016.7905846","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE Global Conference on Signal and Information Processing (GlobalSIP)","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/A5001429662","display_name":"Gaurav Naithani","orcid":"https://orcid.org/0000-0001-6622-6457"},"institutions":[{"id":"https://openalex.org/I4210133110","display_name":"Tampere University","ror":null,"country_code":"FI","type":null,"lineage":["https://openalex.org/I4210133110"]},{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Gaurav Naithani","raw_affiliation_strings":["Department of Signal Processing, Tampere University of Technology, Tampere, Finland"],"affiliations":[{"raw_affiliation_string":"Department of Signal Processing, Tampere University of Technology, Tampere, Finland","institution_ids":["https://openalex.org/I166825849","https://openalex.org/I4210133110"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014848044","display_name":"Giambattista Parascandolo","orcid":null},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]},{"id":"https://openalex.org/I4210133110","display_name":"Tampere University","ror":null,"country_code":"FI","type":null,"lineage":["https://openalex.org/I4210133110"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Giambattista Parascandolo","raw_affiliation_strings":["Department of Signal Processing, Tampere University of Technology, Tampere, Finland"],"affiliations":[{"raw_affiliation_string":"Department of Signal Processing, Tampere University of Technology, Tampere, Finland","institution_ids":["https://openalex.org/I166825849","https://openalex.org/I4210133110"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104103091","display_name":"Tom Barker","orcid":null},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]},{"id":"https://openalex.org/I4210133110","display_name":"Tampere University","ror":null,"country_code":"FI","type":null,"lineage":["https://openalex.org/I4210133110"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Tom Barker","raw_affiliation_strings":["Department of Signal Processing, Tampere University of Technology, Tampere, Finland"],"affiliations":[{"raw_affiliation_string":"Department of Signal Processing, Tampere University of Technology, Tampere, Finland","institution_ids":["https://openalex.org/I166825849","https://openalex.org/I4210133110"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053590493","display_name":"Niels Henrik Pontoppidan","orcid":"https://orcid.org/0000-0002-8172-4232"},"institutions":[{"id":"https://openalex.org/I4210130492","display_name":"Oticon Medical (Denmark)","ror":"https://ror.org/03c5ds320","country_code":"DK","type":"company","lineage":["https://openalex.org/I4210130492"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Niels Henrik Pontoppidan","raw_affiliation_strings":["Eriksholm Research Centre, Snekkersten, Denmark"],"affiliations":[{"raw_affiliation_string":"Eriksholm Research Centre, Snekkersten, Denmark","institution_ids":["https://openalex.org/I4210130492"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049691461","display_name":"Tuomas Virtanen","orcid":"https://orcid.org/0000-0002-4604-9729"},"institutions":[{"id":"https://openalex.org/I4210133110","display_name":"Tampere University","ror":null,"country_code":"FI","type":null,"lineage":["https://openalex.org/I4210133110"]},{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Tuomas Virtanen","raw_affiliation_strings":["Department of Signal Processing, Tampere University of Technology, Tampere, Finland"],"affiliations":[{"raw_affiliation_string":"Department of Signal Processing, Tampere University of Technology, Tampere, Finland","institution_ids":["https://openalex.org/I166825849","https://openalex.org/I4210133110"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5001429662"],"corresponding_institution_ids":["https://openalex.org/I166825849","https://openalex.org/I4210133110"],"apc_list":null,"apc_paid":null,"fwci":2.2696,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.89430749,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"272","last_page":"276"},"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9988999962806702,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7758549451828003},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.7018818855285645},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.6106065511703491},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5961838364601135},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5256575345993042},{"id":"https://openalex.org/keywords/low-latency","display_name":"Low latency (capital markets)","score":0.5106449723243713},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.4748777747154236},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4667316675186157},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.45867663621902466},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4300903081893921},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.3364087641239166},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33235442638397217},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.19807645678520203},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09862065315246582}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7758549451828003},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.7018818855285645},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.6106065511703491},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5961838364601135},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5256575345993042},{"id":"https://openalex.org/C46637626","wikidata":"https://www.wikidata.org/wiki/Q6693015","display_name":"Low latency (capital markets)","level":2,"score":0.5106449723243713},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.4748777747154236},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4667316675186157},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.45867663621902466},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4300903081893921},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.3364087641239166},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33235442638397217},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.19807645678520203},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09862065315246582},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/globalsip.2016.7905846","is_oa":false,"landing_page_url":"https://doi.org/10.1109/globalsip.2016.7905846","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE Global Conference on Signal and Information Processing (GlobalSIP)","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":26,"referenced_works":["https://openalex.org/W88987024","https://openalex.org/W95152782","https://openalex.org/W160800111","https://openalex.org/W1507216254","https://openalex.org/W1522301498","https://openalex.org/W1836465849","https://openalex.org/W2016891207","https://openalex.org/W2031647436","https://openalex.org/W2048854038","https://openalex.org/W2053165762","https://openalex.org/W2068144845","https://openalex.org/W2095705004","https://openalex.org/W2127851351","https://openalex.org/W2135823751","https://openalex.org/W2141520175","https://openalex.org/W2156876426","https://openalex.org/W2158291955","https://openalex.org/W2293634267","https://openalex.org/W2964121744","https://openalex.org/W6603838645","https://openalex.org/W6631190155","https://openalex.org/W6638667902","https://openalex.org/W6674330103","https://openalex.org/W6683161558","https://openalex.org/W6683202405","https://openalex.org/W6696934422"],"related_works":["https://openalex.org/W2289868279","https://openalex.org/W3132176577","https://openalex.org/W2970176078","https://openalex.org/W4231351862","https://openalex.org/W4212794605","https://openalex.org/W2114974607","https://openalex.org/W3112881379","https://openalex.org/W2002298560","https://openalex.org/W2019256813","https://openalex.org/W2158216966"],"abstract_inverted_index":{"Sound":[0],"source":[1,63,123],"separation":[2,64,92],"at":[3,15],"low-latency":[4,52,136],"requires":[5],"that":[6],"each":[7],"incoming":[8,86],"frame":[9,144,164],"of":[10,71,104,148],"audio":[11,87],"data":[12],"be":[13],"processed":[14],"very":[16],"low":[17],"delay,":[18],"and":[19,142],"outputted":[20],"as":[21,23,94],"soon":[22],"possible.":[24],"For":[25],"practical":[26],"purposes":[27],"involving":[28],"human":[29],"listeners,":[30],"a":[31,51,135],"20":[32,56],"ms":[33],"algorithmic":[34],"delay":[35,54],"is":[36,41],"the":[37,44,114],"uppermost":[38],"limit":[39],"which":[40,81],"comfortable":[42],"to":[43,85,89,96,124],"listener.":[45],"In":[46],"this":[47],"paper,":[48],"we":[49],"propose":[50],"(algorithmic":[53],"<;":[55],"ms)":[57],"deep":[58],"neural":[59],"network":[60],"(DNN)":[61],"based":[62],"method.":[65],"The":[66,146],"proposed":[67],"method":[68],"takes":[69],"advantage":[70],"an":[72],"extended":[73],"past":[74],"context,":[75],"outputting":[76],"soft":[77],"time-frequency":[78],"masking":[79],"filters":[80],"are":[82],"then":[83],"applied":[84],"frames":[88],"give":[90],"better":[91],"performance":[93],"compared":[95],"NMF":[97,137],"baseline.":[98],"Acoustic":[99],"mixtures":[100],"from":[101,106],"five":[102],"pairs":[103],"speakers":[105],"CMU":[107],"Arctic":[108],"database":[109],"[1]":[110],"were":[111],"used":[112],"for":[113,139,161],"experiments.":[115],"At":[116],"least":[117],"1":[118],"dB":[119],"average":[120],"improvement":[121],"in":[122,130,159],"distortion":[125],"ratios":[126],"(SDR)":[127],"was":[128],"observed":[129],"our":[131],"DNN-based":[132],"system":[133],"over":[134],"baseline":[138],"different":[140],"processing":[141,163],"analysis":[143],"lengths.":[145,165],"effect":[147],"incorporating":[149],"previous":[150],"temporal":[151],"context":[152],"into":[153],"DNN":[154],"inputs":[155],"yielded":[156],"significant":[157],"improvements":[158],"SDR":[160],"short":[162]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}