{"id":"https://openalex.org/W4402351373","doi":"https://doi.org/10.1109/ijcnn60899.2024.10650194","title":"Complex Recurrent Variational Autoencoder for Speech Resynthesis and Enhancement","display_name":"Complex Recurrent Variational Autoencoder for Speech Resynthesis and Enhancement","publication_year":2024,"publication_date":"2024-06-30","ids":{"openalex":"https://openalex.org/W4402351373","doi":"https://doi.org/10.1109/ijcnn60899.2024.10650194"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn60899.2024.10650194","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn60899.2024.10650194","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2204.02195","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069800152","display_name":"Yuying Xie","orcid":"https://orcid.org/0000-0002-4804-2176"},"institutions":[{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Yuying Xie","raw_affiliation_strings":["Aalborg University,Department of Electronic Systems,Aalborg,Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalborg University,Department of Electronic Systems,Aalborg,Denmark","institution_ids":["https://openalex.org/I891191580"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001695391","display_name":"Thomas Arildsen","orcid":"https://orcid.org/0000-0003-3254-3790"},"institutions":[{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Thomas Arildsen","raw_affiliation_strings":["Aalborg University,Department of Electronic Systems,Aalborg,Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalborg University,Department of Electronic Systems,Aalborg,Denmark","institution_ids":["https://openalex.org/I891191580"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090108098","display_name":"Zheng\u2010Hua Tan","orcid":"https://orcid.org/0000-0001-6856-8928"},"institutions":[{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Zheng-Hua Tan","raw_affiliation_strings":["Aalborg University,Department of Electronic Systems,Aalborg,Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalborg University,Department of Electronic Systems,Aalborg,Denmark","institution_ids":["https://openalex.org/I891191580"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I891191580"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998000264167786,"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":0.9987999796867371,"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/autoencoder","display_name":"Autoencoder","score":0.8727109432220459},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5651888251304626},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5645259022712708},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5210058689117432},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36635106801986694},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.095339834690094},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.06793060898780823}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.8727109432220459},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5651888251304626},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5645259022712708},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5210058689117432},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36635106801986694},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.095339834690094},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.06793060898780823}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ijcnn60899.2024.10650194","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn60899.2024.10650194","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:publications/6fc68d90-8095-4b25-baa1-1ca2cc0d9589","is_oa":true,"landing_page_url":"https://vbn.aau.dk/da/publications/6fc68d90-8095-4b25-baa1-1ca2cc0d9589","pdf_url":"https://arxiv.org/pdf/2204.02195","source":{"id":"https://openalex.org/S4306401731","display_name":"VBN Forskningsportal (Aalborg Universitet)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I891191580","host_organization_name":"Aalborg University","host_organization_lineage":["https://openalex.org/I891191580"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Xie, Y, Arildsen, T & Tan, Z H 2024, Complex Recurrent Variational Autoencoder for Speech Resynthesis and Enhancement. in 2024 International Joint Conference on Neural Networks, IJCNN 2024 - Proceedings., 10650194, IEEE (Institute of Electrical and Electronics Engineers), International Joint Conference on Neural Networks (IJCNN), 2024 International Joint Conference on Neural Networks, IJCNN 2024, Yokohama, Japan, 30/06/2024. https://doi.org/10.1109/IJCNN60899.2024.10650194","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:pure.atira.dk:publications/6fc68d90-8095-4b25-baa1-1ca2cc0d9589","is_oa":true,"landing_page_url":"https://vbn.aau.dk/da/publications/6fc68d90-8095-4b25-baa1-1ca2cc0d9589","pdf_url":"https://arxiv.org/pdf/2204.02195","source":{"id":"https://openalex.org/S4306401731","display_name":"VBN Forskningsportal (Aalborg Universitet)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I891191580","host_organization_name":"Aalborg University","host_organization_lineage":["https://openalex.org/I891191580"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Xie, Y, Arildsen, T & Tan, Z H 2024, Complex Recurrent Variational Autoencoder for Speech Resynthesis and Enhancement. in 2024 International Joint Conference on Neural Networks, IJCNN 2024 - Proceedings., 10650194, IEEE (Institute of Electrical and Electronics Engineers), International Joint Conference on Neural Networks (IJCNN), 2024 International Joint Conference on Neural Networks, IJCNN 2024, Yokohama, Japan, 30/06/2024. https://doi.org/10.1109/IJCNN60899.2024.10650194","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4402351373.pdf","grobid_xml":"https://content.openalex.org/works/W4402351373.grobid-xml"},"referenced_works_count":43,"referenced_works":["https://openalex.org/W592244745","https://openalex.org/W1522301498","https://openalex.org/W1552314771","https://openalex.org/W2070126272","https://openalex.org/W2095072097","https://openalex.org/W2120847449","https://openalex.org/W2141998673","https://openalex.org/W2402144811","https://openalex.org/W2514828952","https://openalex.org/W2539406037","https://openalex.org/W2586068394","https://openalex.org/W2758785877","https://openalex.org/W2774389566","https://openalex.org/W2889597349","https://openalex.org/W2898446161","https://openalex.org/W2922391058","https://openalex.org/W2936689732","https://openalex.org/W2938901746","https://openalex.org/W2991361823","https://openalex.org/W2998572311","https://openalex.org/W3005621653","https://openalex.org/W3032514799","https://openalex.org/W3095797429","https://openalex.org/W3096408984","https://openalex.org/W3174264304","https://openalex.org/W3185637724","https://openalex.org/W3191448984","https://openalex.org/W3200754814","https://openalex.org/W3201698955","https://openalex.org/W4206634335","https://openalex.org/W4224931274","https://openalex.org/W4292692317","https://openalex.org/W4385688722","https://openalex.org/W6617744952","https://openalex.org/W6631190155","https://openalex.org/W6631943919","https://openalex.org/W6640963894","https://openalex.org/W6685537299","https://openalex.org/W6738884980","https://openalex.org/W6745117592","https://openalex.org/W6754813530","https://openalex.org/W6756005648","https://openalex.org/W6757632829"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W3013693939","https://openalex.org/W2566616303","https://openalex.org/W2159052453","https://openalex.org/W3131327266","https://openalex.org/W4220775285","https://openalex.org/W3096184950","https://openalex.org/W4231424160"],"abstract_inverted_index":{"Aiming":[0],"at":[1],"learning":[2],"a":[3,20],"probabilistic":[4],"distribution":[5],"over":[6],"data,":[7,31],"generative":[8,89],"models":[9],"have":[10],"been":[11],"actively":[12],"studied":[13],"with":[14],"broad":[15],"applications.":[16],"This":[17],"paper":[18],"proposes":[19],"complex":[21,78,88,125],"recurrent":[22,48],"variational":[23],"autoencoder":[24],"(VAE)":[25],"framework,":[26],"for":[27,38,140],"modeling":[28],"time":[29],"series":[30],"particularly":[32],"speech":[33,43,60,93,135],"signals.":[34],"First,":[35],"to":[36],"account":[37],"the":[39,52,64,68,84,87,100,110,120],"temporal":[40],"structure":[41],"of":[42,86],"signals,":[44],"we":[45,91],"introduce":[46],"complex-valued":[47],"neural":[49],"network":[50],"in":[51,59,67,103,134],"framework.":[53],"Then,":[54],"inspired":[55],"by":[56],"recent":[57],"advancements":[58],"enhancement":[61,98],"and":[62,79,96,113,128,137],"separation,":[63],"reconstruction":[65],"loss":[66],"proposed":[69,121],"model":[70],"is":[71],"L1-based":[72],"loss,":[73],"considering":[74],"penalty":[75],"on":[76,109,131],"both":[77],"magnitude":[80],"spectrograms.":[81],"To":[82],"exemplify":[83],"use":[85],"model,":[90],"choose":[92],"resynthesis":[94],"first":[95],"then":[97],"as":[99],"specific":[101],"application":[102],"this":[104],"paper.":[105],"Experiments":[106],"are":[107],"conducted":[108],"VCTK,":[111],"TIMIT,":[112],"VoiceBank+DEMAND":[114],"datasets.":[115],"The":[116],"results":[117],"show":[118],"that":[119],"method":[122],"can":[123],"resynthesize":[124],"spectrogram":[126],"well,":[127],"offers":[129],"improvements":[130],"objective":[132],"metrics":[133],"intelligibility":[136],"signal":[138],"quality":[139],"enhancement.":[141]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}