{"id":"https://openalex.org/W2983519761","doi":"https://doi.org/10.1109/lsp.2019.2951894","title":"A Speech Synthesis Approach for High Quality Speech Separation and Generation","display_name":"A Speech Synthesis Approach for High Quality Speech Separation and Generation","publication_year":2019,"publication_date":"2019-11-06","ids":{"openalex":"https://openalex.org/W2983519761","doi":"https://doi.org/10.1109/lsp.2019.2951894","mag":"2983519761"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2019.2951894","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2019.2951894","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-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/A5004547566","display_name":"Qingju Liu","orcid":"https://orcid.org/0000-0003-0778-2992"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Qingju Liu","raw_affiliation_strings":["Centre for Vision, Speech and Signal Processing, University of Surrey, UK"],"raw_orcid":"https://orcid.org/0000-0003-0778-2992","affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing, University of Surrey, UK","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022165330","display_name":"Philip J. B. Jackson","orcid":"https://orcid.org/0000-0001-7933-5935"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Philip J.B. Jackson","raw_affiliation_strings":["Centre for Vision, Speech and Signal Processing, University of Surrey, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing, University of Surrey, UK","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100676721","display_name":"Wenwu Wang","orcid":"https://orcid.org/0000-0002-8393-5703"},"institutions":[{"id":"https://openalex.org/I143413998","display_name":"Qingdao University of Science and Technology","ror":"https://ror.org/041j8js14","country_code":"CN","type":"education","lineage":["https://openalex.org/I143413998"]},{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["CN","GB"],"is_corresponding":false,"raw_author_name":"Wenwu Wang","raw_affiliation_strings":["Centre for Vision, Speech and Signal Processing, University of Surrey, UK","Qingdao University of Science and Technology, China"],"raw_orcid":"https://orcid.org/0000-0002-8393-5703","affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing, University of Surrey, UK","institution_ids":["https://openalex.org/I28290843"]},{"raw_affiliation_string":"Qingdao University of Science and Technology, China","institution_ids":["https://openalex.org/I143413998"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5004547566"],"corresponding_institution_ids":["https://openalex.org/I28290843"],"apc_list":null,"apc_paid":null,"fwci":0.6677,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.69765601,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"26","issue":"12","first_page":"1872","last_page":"1876"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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":0.7743061780929565},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.6592007875442505},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6164170503616333},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.531399130821228},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5005156993865967},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4739656150341034},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.35200968384742737},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34152740240097046}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7743061780929565},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.6592007875442505},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6164170503616333},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.531399130821228},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5005156993865967},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4739656150341034},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.35200968384742737},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34152740240097046},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/lsp.2019.2951894","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2019.2951894","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"},{"id":"pmh:oai:alma.44SUR_INST:11138446100002346","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4210197018","display_name":"View","issn_l":"2688-268X","issn":["2688-268X","2688-3988"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"","raw_type":""},{"id":"pmh:oai:epubs.surrey.ac.uk:853179","is_oa":false,"landing_page_url":"http://epubs.surrey.ac.uk/853179/1/SynthesisForSeparation.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400680","display_name":"Surrey Research Insight Open Access (The University of Surrey)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I28290843","host_organization_name":"University of Surrey","host_organization_lineage":["https://openalex.org/I28290843"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3186182679","display_name":null,"funder_award_id":"EP/L000539/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G88623513","display_name":"S3A: Future Spatial Audio for an Immersive Listener Experience at Home","funder_award_id":"EP/L000539/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1552314771","https://openalex.org/W1790748249","https://openalex.org/W2052666245","https://openalex.org/W2067295501","https://openalex.org/W2120847449","https://openalex.org/W2127851351","https://openalex.org/W2194775991","https://openalex.org/W2221409856","https://openalex.org/W2307770531","https://openalex.org/W2519091744","https://openalex.org/W2587994092","https://openalex.org/W2591927543","https://openalex.org/W2620812332","https://openalex.org/W2747161606","https://openalex.org/W2797579321","https://openalex.org/W2890983311","https://openalex.org/W2930648092","https://openalex.org/W2963103134","https://openalex.org/W2963341071","https://openalex.org/W2964243274","https://openalex.org/W3124794156","https://openalex.org/W3193588461","https://openalex.org/W6631190155","https://openalex.org/W6697925102","https://openalex.org/W6734815144","https://openalex.org/W6917585676"],"related_works":["https://openalex.org/W4390516098","https://openalex.org/W2181948922","https://openalex.org/W2384362569","https://openalex.org/W4205302943","https://openalex.org/W2561132942","https://openalex.org/W2142795561","https://openalex.org/W3155418658","https://openalex.org/W4243199227","https://openalex.org/W2379948177","https://openalex.org/W127416991"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,13,34,50,57,93,103],"new":[3,58],"method":[4,48,139],"for":[5,140],"source":[6,11,23,29,39,143],"separation":[7,24,144],"by":[8,17,41],"synthesizing":[9],"the":[10,28,31,37,67,78,84,89,100,111,119,129],"from":[12,30,83],"speech":[14,106,142],"mixture":[15,32],"corrupted":[16],"various":[18],"environmental":[19],"noise.":[20],"Unlike":[21],"traditional":[22],"methods":[25],"which":[26,53,113],"estimate":[27],"as":[33],"replica":[35],"of":[36,88,118,136],"original":[38,68],"(e.g.":[40],"solving":[42],"an":[43,74],"inverse":[44],"problem),":[45],"our":[46,137],"proposed":[47,71,138],"is":[49,102],"synthesis-based":[51],"approach":[52],"aims":[54],"to":[55,66],"generate":[56],"signal":[59],"(i.e.":[60],"\u201cfake\u201d":[61],"source)":[62],"that":[63],"sounds":[64],"similar":[65],"source.":[69],"The":[70],"system":[72],"has":[73],"encoder-decoder":[75],"topology,":[76],"where":[77],"encoder":[79],"predicts":[80],"intermediate-level":[81],"features":[82],"mixture,":[85],"i.e.":[86],"Mel-spectrum":[87],"target":[90],"source,":[91],"using":[92],"hybrid":[94],"recurrent":[95],"and":[96,123,132,145],"hourglass":[97],"network,":[98],"while":[99],"decoder":[101],"state-of-the-art":[104],"WaveNet":[105],"synthesis":[107],"network":[108],"conditioned":[109],"on":[110,128],"Mel-spectrum,":[112],"directly":[114],"generates":[115],"time-domain":[116],"samples":[117],"sources.":[120],"Both":[121],"objective":[122],"subjective":[124],"evaluations":[125],"were":[126],"performed":[127],"synthesized":[130],"sources,":[131],"show":[133],"great":[134],"advantages":[135],"high-quality":[141],"generation.":[146]},"counts_by_year":[{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}