{"id":"https://openalex.org/W4416798562","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249193","title":"Noro: Noise-Robust One-Shot Voice Conversion with Hidden Speaker Representation Learning","display_name":"Noro: Noise-Robust One-Shot Voice Conversion with Hidden Speaker Representation Learning","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416798562","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249193"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249193","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249193","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5075603893","display_name":"Haorui He","orcid":"https://orcid.org/0000-0002-3429-863X"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haorui He","raw_affiliation_strings":["School of Data Science, Chinese University of Hong Kong,Shenzhen,China,518172"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Data Science, Chinese University of Hong Kong,Shenzhen,China,518172","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039865900","display_name":"Yuchen Song","orcid":"https://orcid.org/0000-0002-0940-3178"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuchen Song","raw_affiliation_strings":["School of Data Science, Chinese University of Hong Kong,Shenzhen,China,518172"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Data Science, Chinese University of Hong Kong,Shenzhen,China,518172","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090055283","display_name":"Yuancheng Wang","orcid":"https://orcid.org/0000-0002-6253-8311"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuancheng Wang","raw_affiliation_strings":["School of Data Science, Chinese University of Hong Kong,Shenzhen,China,518172"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Data Science, Chinese University of Hong Kong,Shenzhen,China,518172","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037624853","display_name":"Haoyang Li","orcid":"https://orcid.org/0000-0003-3024-1350"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Haoyang Li","raw_affiliation_strings":["School of Computer Science and Engineering, Nanyang Technological University,Singapore,639798"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University,Singapore,639798","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115589596","display_name":"X. Zhang","orcid":"https://orcid.org/0000-0003-4341-1603"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xueyao Zhang","raw_affiliation_strings":["School of Data Science, Chinese University of Hong Kong,Shenzhen,China,518172"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Data Science, Chinese University of Hong Kong,Shenzhen,China,518172","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116319512","display_name":"Li Wang","orcid":"https://orcid.org/0000-0002-4658-2558"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Wang","raw_affiliation_strings":["School of Data Science, Chinese University of Hong Kong,Shenzhen,China,518172"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Data Science, Chinese University of Hong Kong,Shenzhen,China,518172","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034257180","display_name":"Gongping Huang","orcid":"https://orcid.org/0000-0002-6825-7473"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gongping Huang","raw_affiliation_strings":["School of Electronic Information, Wuhan University,Wuhan,China,430072"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic Information, Wuhan University,Wuhan,China,430072","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070872826","display_name":"Eng Siong Chng","orcid":"https://orcid.org/0000-0001-6257-7399"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Eng Siong Chng","raw_affiliation_strings":["School of Computer Science and Engineering, Nanyang Technological University,Singapore,639798"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University,Singapore,639798","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102765381","display_name":"Zhizheng Wu","orcid":"https://orcid.org/0009-0001-1192-9857"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhizheng Wu","raw_affiliation_strings":["School of Data Science, Chinese University of Hong Kong,Shenzhen,China,518172"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Data Science, Chinese University of Hong Kong,Shenzhen,China,518172","institution_ids":["https://openalex.org/I4210116924"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2247","last_page":"2251"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9706000089645386,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9706000089645386,"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/T10860","display_name":"Speech and Audio Processing","score":0.009100000374019146,"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/T11448","display_name":"Face recognition and analysis","score":0.002199999988079071,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/representation","display_name":"Representation (politics)","score":0.5925999879837036},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5745000243186951},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.44209998846054077},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.41119998693466187},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.40070000290870667},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.3871000111103058}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7662000060081482},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6603000164031982},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5925999879837036},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5745000243186951},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47350001335144043},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.44209998846054077},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.41119998693466187},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.40070000290870667},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3871000111103058},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.37299999594688416},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3147999942302704},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.2851000130176544},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2831999957561493},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2800999879837036},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.27379998564720154},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.262800008058548}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249193","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249193","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2603567530","https://openalex.org/W2973049979","https://openalex.org/W2981087920","https://openalex.org/W2995181338","https://openalex.org/W3016181583","https://openalex.org/W3097448764","https://openalex.org/W3143523927","https://openalex.org/W3162184950","https://openalex.org/W3197580070","https://openalex.org/W3206503703","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4205582447","https://openalex.org/W4283836776","https://openalex.org/W4287854499","https://openalex.org/W4372260053","https://openalex.org/W4386902717","https://openalex.org/W4392902857","https://openalex.org/W4402112204","https://openalex.org/W4406461271","https://openalex.org/W4406461681","https://openalex.org/W4414404922"],"related_works":[],"abstract_inverted_index":{"The":[0,104],"effectiveness":[1],"of":[2,91],"one-shot":[3,36,133],"voice":[4],"conversion":[5],"(VC)":[6],"decreases":[7],"in":[8,71],"real-world":[9,81],"scenarios":[10],"where":[11],"reference":[12,48,53,98],"speeches,":[13,49],"which":[14],"are":[15],"often":[16],"sourced":[17],"from":[18],"the":[19,86,121,125],"internet,":[20],"contain":[21],"various":[22],"disturbances":[23],"like":[24],"background":[25],"noise.":[26],"To":[27],"address":[28],"this":[29],"issue,":[30],"we":[31,84],"introduce":[32],"Noro,":[33],"a":[34,51,57,101],"noise-robust":[35],"VC":[37,45,134],"system.":[38],"Noro":[39,66],"features":[40],"innovative":[41],"components":[42],"tailored":[43],"for":[44,80,117,127],"using":[46],"noisy":[47,75],"including":[50],"dual-branch":[52],"encoding":[54],"module":[55],"and":[56,74],"noise-agnostic":[58],"contrastive":[59],"speaker":[60,88,102,118,129],"loss.":[61],"Experimental":[62],"results":[63,105],"demonstrate":[64],"that":[65,107],"outperforms":[67],"our":[68,92],"baseline":[69,93],"system":[70,94],"both":[72],"clean":[73],"scenarios,":[76],"highlighting":[77,124],"its":[78,97],"efficacy":[79],"applications.":[82],"Additionally,":[83],"investigate":[85],"hidden":[87],"representation":[89,119,130],"capabilities":[90],"by":[95],"repurposing":[96],"encoder":[99],"as":[100],"encoder.":[103],"show":[106],"it":[108],"is":[109],"competitive":[110],"with":[111],"several":[112],"advanced":[113],"self-supervised":[114],"learning":[115,131],"models":[116],"under":[120],"SUPERB":[122],"settings,":[123],"potential":[126],"advancing":[128],"through":[132],"tasks.":[135]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-28T00:00:00"}