{"id":"https://openalex.org/W2986634321","doi":"https://doi.org/10.23919/eusipco.2019.8902655","title":"Monaural Speech Separation with Deep Learning Using Phase Modelling and Capsule Networks","display_name":"Monaural Speech Separation with Deep Learning Using Phase Modelling and Capsule Networks","publication_year":2019,"publication_date":"2019-09-01","ids":{"openalex":"https://openalex.org/W2986634321","doi":"https://doi.org/10.23919/eusipco.2019.8902655","mag":"2986634321"},"language":"en","primary_location":{"id":"doi:10.23919/eusipco.2019.8902655","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco.2019.8902655","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 27th European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5041451512","display_name":"Toby Staines","orcid":null},"institutions":[{"id":"https://openalex.org/I180825142","display_name":"City, University of London","ror":"https://ror.org/04489at23","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I180825142"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Toby Staines","raw_affiliation_strings":["Department of Computer Science City, University of London, London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science City, University of London, London, UK","institution_ids":["https://openalex.org/I180825142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018493892","display_name":"Tillman Weyde","orcid":"https://orcid.org/0000-0001-8028-9905"},"institutions":[{"id":"https://openalex.org/I180825142","display_name":"City, University of London","ror":"https://ror.org/04489at23","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I180825142"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Tillman Weyde","raw_affiliation_strings":["Department of Computer Science City, University of London, London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science City, University of London, London, UK","institution_ids":["https://openalex.org/I180825142"]}]},{"author_position":"last","author":{"id":null,"display_name":"Oleksandr Galkin","orcid":null},"institutions":[{"id":"https://openalex.org/I180825142","display_name":"City, University of London","ror":"https://ror.org/04489at23","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I180825142"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Oleksandr Galkin","raw_affiliation_strings":["Department of Computer Science City, University of London, London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science City, University of London, London, UK","institution_ids":["https://openalex.org/I180825142"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I180825142"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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":0.9995999932289124,"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":0.9991000294685364,"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/spectrogram","display_name":"Spectrogram","score":0.8107973337173462},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7891404032707214},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6384807229042053},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5861638784408569},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5689601302146912},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5308906435966492},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.5028635859489441},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.484567791223526},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.47991928458213806},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.46380236744880676},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.43394094705581665},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.4242883026599884},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.41877397894859314},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3617671728134155},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.3235146999359131},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.25136423110961914}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8107973337173462},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7891404032707214},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6384807229042053},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5861638784408569},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5689601302146912},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5308906435966492},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.5028635859489441},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.484567791223526},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.47991928458213806},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.46380236744880676},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.43394094705581665},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.4242883026599884},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.41877397894859314},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3617671728134155},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.3235146999359131},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25136423110961914},{"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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.23919/eusipco.2019.8902655","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco.2019.8902655","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 27th European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"},{"id":"pmh:oai:openaccess.city.ac.uk:23668","is_oa":false,"landing_page_url":"https://openaccess.city.ac.uk/view/creators_id/t=2Ee=2Eweyde.html>","pdf_url":null,"source":{"id":"https://openalex.org/S4306401940","display_name":"City Research Online (City University London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I180825142","host_organization_name":"City, University of London","host_organization_lineage":["https://openalex.org/I180825142"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.6100000143051147}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1901129140","https://openalex.org/W2070126272","https://openalex.org/W2092147578","https://openalex.org/W2127851351","https://openalex.org/W2289394825","https://openalex.org/W2291877678","https://openalex.org/W2618946976","https://openalex.org/W2774707525","https://openalex.org/W2775143585","https://openalex.org/W2797472209","https://openalex.org/W2881244050","https://openalex.org/W2889134433","https://openalex.org/W2889597349","https://openalex.org/W2963703618","https://openalex.org/W2964121744","https://openalex.org/W4293450051","https://openalex.org/W6631190155","https://openalex.org/W6639824700","https://openalex.org/W6738884980","https://openalex.org/W6743446608","https://openalex.org/W6745413045","https://openalex.org/W6747050675","https://openalex.org/W6750207810","https://openalex.org/W6753067400"],"related_works":["https://openalex.org/W3094316140","https://openalex.org/W3133205200","https://openalex.org/W4289363934","https://openalex.org/W2898145319","https://openalex.org/W2898606530","https://openalex.org/W2098101267","https://openalex.org/W2059119686","https://openalex.org/W4289362680","https://openalex.org/W2403380333","https://openalex.org/W2761596192"],"abstract_inverted_index":{"The":[0],"removal":[1],"of":[2,17,30,38,100,108,118],"background":[3],"noise":[4],"from":[5],"speech":[6,119,135],"audio":[7],"is":[8,57],"a":[9,34,39,62,89],"problem":[10],"with":[11],"high":[12],"practical":[13],"relevance.":[14],"A":[15],"variety":[16],"deep":[18],"learning":[19],"approaches":[20],"have":[21,81],"been":[22,82],"applied":[23],"to":[24,42,52,74,112],"it":[25],"in":[26,84,115,125],"recent":[27],"years,":[28],"most":[29],"which":[31,56,93],"operate":[32],"on":[33],"magnitude":[35],"spectrogram":[36],"representation":[37],"noisy":[40],"recording":[41],"estimate":[43],"the":[44,77,97,106,116],"isolated":[45],"speaking":[46],"voice.":[47],"This":[48],"work":[49],"investigates":[50],"ways":[51],"include":[53],"phase":[54,109],"information,":[55],"commonly":[58],"discarded,":[59],"firstly":[60],"within":[61],"convolutional":[63,128],"neural":[64,129],"network":[65],"(CNN)":[66],"architecture,":[67],"and":[68],"secondly":[69],"by":[70],"applying":[71],"capsule":[72,132],"networks,":[73],"our":[75,126],"knowledge":[76],"first":[78],"time":[79],"capsules":[80],"used":[83],"source":[85],"separation.":[86,120,136],"We":[87,121],"present":[88],"Circular":[90],"Loss":[91],"function,":[92],"takes":[94],"into":[95],"account":[96],"periodic":[98],"nature":[99],"phase.":[101],"Our":[102],"results":[103],"show":[104],"that":[105,124],"inclusion":[107],"information":[110],"leads":[111],"an":[113],"improvement":[114],"quality":[117],"also":[122],"find":[123],"experiments":[127],"networks":[130,133],"outperform":[131],"at":[134]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}