{"id":"https://openalex.org/W2771725120","doi":"https://doi.org/10.1109/waspaa.2017.8169997","title":"Low latency sound source separation using convolutional recurrent neural networks","display_name":"Low latency sound source separation using convolutional recurrent neural networks","publication_year":2017,"publication_date":"2017-10-01","ids":{"openalex":"https://openalex.org/W2771725120","doi":"https://doi.org/10.1109/waspaa.2017.8169997","mag":"2771725120"},"language":"en","primary_location":{"id":"doi:10.1109/waspaa.2017.8169997","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa.2017.8169997","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","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":[],"countries":[],"is_corresponding":true,"raw_author_name":"Gaurav Naithani","raw_affiliation_strings":["Department of Signal Processing, Max Planck Institute for Intelligent Systems, Tampere, Finland"],"affiliations":[{"raw_affiliation_string":"Department of Signal Processing, Max Planck Institute for Intelligent Systems, Tampere, Finland","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104103091","display_name":"Tom Barker","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tom Barker","raw_affiliation_strings":["Department of Signal Processing, Max Planck Institute for Intelligent Systems, Tampere, Finland"],"affiliations":[{"raw_affiliation_string":"Department of Signal Processing, Max Planck Institute for Intelligent Systems, Tampere, Finland","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014848044","display_name":"Giambattista Parascandolo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Giambattista Parascandolo","raw_affiliation_strings":["Department of Signal Processing, Max Planck Institute for Intelligent Systems, Tampere, Finland"],"affiliations":[{"raw_affiliation_string":"Department of Signal Processing, Max Planck Institute for Intelligent Systems, Tampere, Finland","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017911969","display_name":"Lars Bramsl\u00f8w","orcid":"https://orcid.org/0000-0002-4963-2629"},"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":"Lars Bramslow","raw_affiliation_strings":["Eriksholm Research Centre, Oticon A/S, Snekkersten, Denmark"],"affiliations":[{"raw_affiliation_string":"Eriksholm Research Centre, Oticon A/S, Snekkersten, Denmark","institution_ids":["https://openalex.org/I4210130492"]}]},{"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, Oticon A/S, Snekkersten, Denmark"],"affiliations":[{"raw_affiliation_string":"Eriksholm Research Centre, Oticon A/S, 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":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tuomas Virtanen","raw_affiliation_strings":["Department of Signal Processing, Max Planck Institute for Intelligent Systems, Tampere, Finland"],"affiliations":[{"raw_affiliation_string":"Department of Signal Processing, Max Planck Institute for Intelligent Systems, Tampere, Finland","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5001429662"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.5419,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":{"value":0.94089207,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"71","last_page":"75"},"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":0.9991999864578247,"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":0.9988999962806702,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/monaural","display_name":"Monaural","score":0.7935225367546082},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7929293513298035},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.6495462656021118},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.646048367023468},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5909484028816223},{"id":"https://openalex.org/keywords/feed-forward","display_name":"Feed forward","score":0.5805174112319946},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5446779131889343},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.5333831906318665},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4581645131111145},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.4354020953178406},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4340006709098816},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42301082611083984},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36527734994888306},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1025596559047699},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09173315763473511}],"concepts":[{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.7935225367546082},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7929293513298035},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.6495462656021118},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.646048367023468},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5909484028816223},{"id":"https://openalex.org/C38858127","wikidata":"https://www.wikidata.org/wiki/Q5441228","display_name":"Feed forward","level":2,"score":0.5805174112319946},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5446779131889343},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.5333831906318665},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4581645131111145},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.4354020953178406},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4340006709098816},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42301082611083984},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36527734994888306},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1025596559047699},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09173315763473511},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/waspaa.2017.8169997","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa.2017.8169997","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"},{"id":"pmh:oai:escidoc.org:escidoc:2581516","is_oa":false,"landing_page_url":"http://hdl.handle.net/21.11116/0000-0001-313C-5","pdf_url":null,"source":{"id":"https://openalex.org/S7407052962","display_name":"Max Planck Digital Library","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W88987024","https://openalex.org/W1507216254","https://openalex.org/W1522301498","https://openalex.org/W1546771929","https://openalex.org/W1557436995","https://openalex.org/W1836465849","https://openalex.org/W2020307986","https://openalex.org/W2031647436","https://openalex.org/W2046869671","https://openalex.org/W2053165762","https://openalex.org/W2064675550","https://openalex.org/W2067295501","https://openalex.org/W2095705004","https://openalex.org/W2108089013","https://openalex.org/W2112482982","https://openalex.org/W2127851351","https://openalex.org/W2135823751","https://openalex.org/W2136848157","https://openalex.org/W2141520175","https://openalex.org/W2143317947","https://openalex.org/W2157963512","https://openalex.org/W2516001803","https://openalex.org/W2563215737","https://openalex.org/W2587994092","https://openalex.org/W2591013610","https://openalex.org/W2701869962","https://openalex.org/W2963451564","https://openalex.org/W2963453742","https://openalex.org/W2964121744","https://openalex.org/W3210141620","https://openalex.org/W4293248946","https://openalex.org/W6631190155","https://openalex.org/W6632360823","https://openalex.org/W6638667902","https://openalex.org/W6662385463","https://openalex.org/W6674330103","https://openalex.org/W6727174287","https://openalex.org/W6728226663"],"related_works":["https://openalex.org/W2036157531","https://openalex.org/W2056406069","https://openalex.org/W1974981856","https://openalex.org/W1518859147","https://openalex.org/W2045506488","https://openalex.org/W1983045063","https://openalex.org/W2103031592","https://openalex.org/W1967226023","https://openalex.org/W178436704","https://openalex.org/W3150394233"],"abstract_inverted_index":{"Deep":[0],"neural":[1,27],"networks":[2],"(DNN)":[3],"have":[4],"been":[5],"successfully":[6],"employed":[7],"for":[8,31],"the":[9,59],"problem":[10],"of":[11,107],"monaural":[12],"sound":[13],"source":[14,86],"separation":[15,82],"achieving":[16],"state-of-the-art":[17],"results.":[18],"In":[19,78],"this":[20,33],"paper,":[21],"we":[22,90],"propose":[23],"using":[24],"convolutional":[25],"recurrent":[26],"network":[28],"(CRNN)":[29],"architecture":[30,61],"tackling":[32],"problem.":[34],"We":[35,56],"focus":[36],"on":[37],"a":[38],"scenario":[39],"where":[40],"low":[41],"algorithmic":[42],"delay":[43],"(<;":[44],"10":[45],"ms)":[46],"is":[47,54],"paramount,":[48],"and":[49,72],"relatively":[50],"little":[51],"training":[52],"data":[53],"available.":[55],"show":[57],"that":[58],"proposed":[60],"can":[62],"achieve":[63],"slightly":[64],"better":[65,101],"performance":[66,83,104],"as":[67],"compared":[68],"to":[69,80,87],"feedforward":[70],"DNNs":[71],"long":[73],"short-term":[74],"memory":[75],"(LSTM)":[76],"networks.":[77],"addition":[79],"reporting":[81],"metrics":[84],"(i.e.,":[85],"distortion":[88],"ratios),":[89],"also":[91],"report":[92],"extended":[93],"short":[94],"term":[95],"objective":[96],"intelligibility":[97,103],"(ESTOI)":[98],"scores":[99],"which":[100],"predict":[102],"in":[105],"presence":[106],"non-stationary":[108],"interferers.":[109]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":10},{"year":2018,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}