{"id":"https://openalex.org/W4408345715","doi":"https://doi.org/10.1109/icassp49660.2025.10888332","title":"AccentBox: Towards High-Fidelity Zero-Shot Accent Generation","display_name":"AccentBox: Towards High-Fidelity Zero-Shot Accent Generation","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408345715","doi":"https://doi.org/10.1109/icassp49660.2025.10888332"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888332","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888332","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5004778288","display_name":"Jinzuomu Zhong","orcid":null},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Jinzuomu Zhong","raw_affiliation_strings":["University of Edinburgh,Centre for Speech Technology Research,UK"],"affiliations":[{"raw_affiliation_string":"University of Edinburgh,Centre for Speech Technology Research,UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055415493","display_name":"Korin Richmond","orcid":"https://orcid.org/0000-0003-1450-8270"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Korin Richmond","raw_affiliation_strings":["University of Edinburgh,Centre for Speech Technology Research,UK"],"affiliations":[{"raw_affiliation_string":"University of Edinburgh,Centre for Speech Technology Research,UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070507407","display_name":"Zhiba Su","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhiba Su","raw_affiliation_strings":["Transsion,Department of AI Technology,China"],"affiliations":[{"raw_affiliation_string":"Transsion,Department of AI Technology,China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012731056","display_name":"Siqi Sun","orcid":"https://orcid.org/0000-0002-8947-4207"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Siqi Sun","raw_affiliation_strings":["University of Edinburgh,Centre for Speech Technology Research,UK"],"affiliations":[{"raw_affiliation_string":"University of Edinburgh,Centre for Speech Technology Research,UK","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5004778288"],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":1.4296,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.8078479,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"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/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.9599999785423279,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.9599999785423279,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12153","display_name":"Advanced Optical Sensing Technologies","score":0.9451000094413757,"subfield":{"id":"https://openalex.org/subfields/3105","display_name":"Instrumentation"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.9412999749183655,"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/stress","display_name":"Stress (linguistics)","score":0.7094897031784058},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.6010503172874451},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.5785609483718872},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5577641129493713},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.5336034893989563},{"id":"https://openalex.org/keywords/high-fidelity","display_name":"High fidelity","score":0.5183061957359314},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.26975730061531067},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.14151817560195923},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.13717153668403625},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.1330808401107788},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.11838850378990173},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10661318898200989}],"concepts":[{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.7094897031784058},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.6010503172874451},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.5785609483718872},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5577641129493713},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.5336034893989563},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.5183061957359314},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.26975730061531067},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.14151817560195923},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.13717153668403625},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.1330808401107788},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.11838850378990173},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10661318898200989},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C191897082","wikidata":"https://www.wikidata.org/wiki/Q11467","display_name":"Metallurgy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888332","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888332","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1987971958","https://openalex.org/W2017742648","https://openalex.org/W2113041501","https://openalex.org/W2407080277","https://openalex.org/W2696967604","https://openalex.org/W2954234533","https://openalex.org/W2962788625","https://openalex.org/W2964243274","https://openalex.org/W2973142754","https://openalex.org/W2996769030","https://openalex.org/W3094843121","https://openalex.org/W3160475509","https://openalex.org/W3209862731","https://openalex.org/W3213029956","https://openalex.org/W4252812408","https://openalex.org/W4319862272","https://openalex.org/W4372341945","https://openalex.org/W4383220533","https://openalex.org/W4385822302","https://openalex.org/W4385823180","https://openalex.org/W4385823191","https://openalex.org/W4385823477","https://openalex.org/W4388820352","https://openalex.org/W4390075359","https://openalex.org/W4391827315","https://openalex.org/W4391892546","https://openalex.org/W4393372125","https://openalex.org/W4406417959","https://openalex.org/W6605806949","https://openalex.org/W6752888775","https://openalex.org/W6771467084","https://openalex.org/W6772349387","https://openalex.org/W6805710207","https://openalex.org/W6848735303","https://openalex.org/W6861507043","https://openalex.org/W6862144568","https://openalex.org/W6869106464"],"related_works":["https://openalex.org/W4313443006","https://openalex.org/W2945374968","https://openalex.org/W4293777179","https://openalex.org/W4385452045","https://openalex.org/W2164070813","https://openalex.org/W2135608140","https://openalex.org/W2895525995","https://openalex.org/W2332512904","https://openalex.org/W4224231624","https://openalex.org/W2319626700"],"abstract_inverted_index":{"While":[0],"recent":[1],"Zero-Shot":[2],"Text-to-Speech":[3],"(ZS-TTS)":[4],"models":[5],"have":[6],"achieved":[7],"high":[8],"naturalness":[9],"and":[10,19,38,95],"speaker":[11],"similarity,":[12],"they":[13],"fall":[14],"short":[15],"in":[16],"accent":[17,28,77,89,93,98],"fidelity":[18,90],"control.":[20],"To":[21],"address":[22],"this":[23],"issue,":[24],"we":[25,49,68],"propose":[26],"zero-shot":[27],"generation":[29],"that":[30],"unifies":[31],"Foreign":[32],"Accent":[33,54],"Conversion":[34],"(FAC),":[35],"accented":[36],"TTS,":[37],"ZS-TTS,":[39],"with":[40,57],"a":[41,70],"novel":[42],"two-stage":[43],"pipeline.":[44],"In":[45,64],"the":[46,65,74,81],"first":[47],"stage,":[48,67],"achieve":[50],"state-of-the-art":[51],"(SOTA)":[52],"on":[53,61,73,91],"Identification":[55],"(AID)":[56],"0.56":[58],"f1":[59],"score":[60],"unseen":[62,97],"speakers.":[63],"second":[66],"condition":[69],"ZS-TTS":[71],"system":[72,86],"pretrained":[75],"speaker-agnostic":[76],"embeddings":[78],"extracted":[79],"by":[80],"AID":[82],"model.":[83],"The":[84],"proposed":[85],"achieves":[87],"higher":[88],"inherent/cross":[92],"generation,":[94],"enables":[96],"generation.":[99]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}