{"id":"https://openalex.org/W7130339207","doi":"https://doi.org/10.1109/o-cocosda68185.2025.11384822","title":"HifiDiff: Two Stream Diffusion Models for High Fidelity Speech Generation of Unseen Languages","display_name":"HifiDiff: Two Stream Diffusion Models for High Fidelity Speech Generation of Unseen Languages","publication_year":2025,"publication_date":"2025-11-12","ids":{"openalex":"https://openalex.org/W7130339207","doi":"https://doi.org/10.1109/o-cocosda68185.2025.11384822"},"language":null,"primary_location":{"id":"doi:10.1109/o-cocosda68185.2025.11384822","is_oa":false,"landing_page_url":"https://doi.org/10.1109/o-cocosda68185.2025.11384822","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 28th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","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/A5069397372","display_name":"Lhuqita Fazry","orcid":"https://orcid.org/0009-0004-8494-9375"},"institutions":[{"id":"https://openalex.org/I29617571","display_name":"University of Indonesia","ror":"https://ror.org/0116zj450","country_code":"ID","type":"education","lineage":["https://openalex.org/I29617571"]}],"countries":["ID"],"is_corresponding":false,"raw_author_name":"Lhuqita Fazry","raw_affiliation_strings":["University of Indonesia,Indonesia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Indonesia,Indonesia","institution_ids":["https://openalex.org/I29617571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066073372","display_name":"Kurniawati Azizah","orcid":"https://orcid.org/0000-0002-3217-7025"},"institutions":[{"id":"https://openalex.org/I29617571","display_name":"University of Indonesia","ror":"https://ror.org/0116zj450","country_code":"ID","type":"education","lineage":["https://openalex.org/I29617571"]}],"countries":["ID"],"is_corresponding":false,"raw_author_name":"Kurniawati Azizah","raw_affiliation_strings":["University of Indonesia,Indonesia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Indonesia,Indonesia","institution_ids":["https://openalex.org/I29617571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066930701","display_name":"Dipta Tanaya","orcid":"https://orcid.org/0009-0000-1480-8041"},"institutions":[{"id":"https://openalex.org/I29617571","display_name":"University of Indonesia","ror":"https://ror.org/0116zj450","country_code":"ID","type":"education","lineage":["https://openalex.org/I29617571"]}],"countries":["ID"],"is_corresponding":false,"raw_author_name":"Dipta Tanaya","raw_affiliation_strings":["University of Indonesia,Indonesia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Indonesia,Indonesia","institution_ids":["https://openalex.org/I29617571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078939269","display_name":"Ayu Purwarianti","orcid":null},"institutions":[{"id":"https://openalex.org/I134635517","display_name":"Bandung Institute of Technology","ror":"https://ror.org/00apj8t60","country_code":"ID","type":"education","lineage":["https://openalex.org/I134635517"]}],"countries":["ID"],"is_corresponding":false,"raw_author_name":"Ayu Purwarianti","raw_affiliation_strings":["Bandung Institute of Technology,Indonesia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bandung Institute of Technology,Indonesia","institution_ids":["https://openalex.org/I134635517"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109343497","display_name":"Dessi Fuji Lestari","orcid":null},"institutions":[{"id":"https://openalex.org/I134635517","display_name":"Bandung Institute of Technology","ror":"https://ror.org/00apj8t60","country_code":"ID","type":"education","lineage":["https://openalex.org/I134635517"]}],"countries":["ID"],"is_corresponding":false,"raw_author_name":"Dessi Lestari","raw_affiliation_strings":["Bandung Institute of Technology,Indonesia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bandung Institute of Technology,Indonesia","institution_ids":["https://openalex.org/I134635517"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040108974","display_name":"Sakriani Sakti","orcid":"https://orcid.org/0000-0001-5509-8963"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sakriani Sakti","raw_affiliation_strings":["Nara Institute of Science and Technology,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology,Japan","institution_ids":["https://openalex.org/I75917431"]}]}],"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":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.5306000113487244,"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":0.5306000113487244,"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/T11448","display_name":"Face recognition and analysis","score":0.06539999693632126,"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"}},{"id":"https://openalex.org/T10403","display_name":"Phonetics and Phonology Research","score":0.040800001472234726,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/high-fidelity","display_name":"High fidelity","score":0.6353999972343445},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.45649999380111694},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4496999979019165},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.4348999857902527},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.40529999136924744},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.40389999747276306},{"id":"https://openalex.org/keywords/mean-opinion-score","display_name":"Mean opinion score","score":0.3968000113964081},{"id":"https://openalex.org/keywords/natural-language-generation","display_name":"Natural language generation","score":0.39259999990463257}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.727400004863739},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6938999891281128},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.6353999972343445},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5145999789237976},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.45649999380111694},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4496999979019165},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.4348999857902527},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.40529999136924744},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.40389999747276306},{"id":"https://openalex.org/C62897895","wikidata":"https://www.wikidata.org/wiki/Q1915482","display_name":"Mean opinion score","level":3,"score":0.3968000113964081},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.39259999990463257},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3880000114440918},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.37119999527931213},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.34200000762939453},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.31949999928474426},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3028999865055084},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.30000001192092896},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.26409998536109924},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.2531000077724457},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2517000138759613},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.25060001015663147}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/o-cocosda68185.2025.11384822","is_oa":false,"landing_page_url":"https://doi.org/10.1109/o-cocosda68185.2025.11384822","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 28th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","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":18,"referenced_works":["https://openalex.org/W1677182931","https://openalex.org/W1915786104","https://openalex.org/W2519091744","https://openalex.org/W2750167318","https://openalex.org/W2951310434","https://openalex.org/W2954386831","https://openalex.org/W2962834855","https://openalex.org/W2963103134","https://openalex.org/W2972504514","https://openalex.org/W3015338123","https://openalex.org/W3015935472","https://openalex.org/W3045000780","https://openalex.org/W3049605724","https://openalex.org/W3162536450","https://openalex.org/W3198769980","https://openalex.org/W4205267278","https://openalex.org/W4224931676","https://openalex.org/W4319585868"],"related_works":[],"abstract_inverted_index":{"Speech":[0],"generation":[1,77],"aims":[2],"to":[3,71],"produce":[4],"synthetic":[5],"speech":[6,76],"that":[7],"mimics":[8],"natural":[9],"speech's":[10],"properties.":[11],"However,":[12],"pitch":[13],"inaccuracies":[14],"exist":[15],"in":[16,51,78],"voiced":[17,41],"and":[18,42],"unvoiced":[19,43],"sounds":[20],"when":[21],"the":[22,48,57,66,73],"trained":[23],"model":[24,37],"is":[25],"conditioned":[26],"on":[27],"unseen":[28,53,79],"languages.":[29,80],"This":[30,63],"paper":[31],"proposes":[32],"HifiDiff,":[33],"a":[34],"two-stream":[35],"diffusion":[36],"for":[38,56],"separately":[39],"generating":[40],"sounds.":[44],"Our":[45],"approach":[46,70],"outperforms":[47],"baseline":[49],"method":[50],"most":[52],"language":[54],"datasets":[55],"mean":[58],"opinion":[59],"score":[60],"(MOS)":[61],"metric.":[62],"result":[64],"concludes":[65],"effectiveness":[67],"of":[68,75],"our":[69],"resolving":[72],"problem":[74]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-02-19T00:00:00"}
