{"id":"https://openalex.org/W4408352831","doi":"https://doi.org/10.1109/icassp49660.2025.10889039","title":"Universal Low-Resource Speech Synthesis Via Phoneme Fusion Coordinating Low-Rank Decomposition","display_name":"Universal Low-Resource Speech Synthesis Via Phoneme Fusion Coordinating Low-Rank Decomposition","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352831","doi":"https://doi.org/10.1109/icassp49660.2025.10889039"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889039","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889039","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":"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/A5047606331","display_name":"Yanliang Li","orcid":"https://orcid.org/0009-0008-0962-545X"},"institutions":[{"id":"https://openalex.org/I146071755","display_name":"Kunming University","ror":"https://ror.org/035rhx828","country_code":"CN","type":"education","lineage":["https://openalex.org/I146071755"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanliang Li","raw_affiliation_strings":["Kunming University of Tech. and Sci.,Info. Engineering and Automation Yunnan Key Lab. of AI,Kunming,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kunming University of Tech. and Sci.,Info. Engineering and Automation Yunnan Key Lab. of AI,Kunming,China","institution_ids":["https://openalex.org/I146071755"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100619287","display_name":"Zhengtao Yu","orcid":"https://orcid.org/0000-0002-4012-461X"},"institutions":[{"id":"https://openalex.org/I146071755","display_name":"Kunming University","ror":"https://ror.org/035rhx828","country_code":"CN","type":"education","lineage":["https://openalex.org/I146071755"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengtao Yu","raw_affiliation_strings":["Kunming University of Tech. and Sci.,Info. Engineering and Automation Yunnan Key Lab. of AI,Kunming,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kunming University of Tech. and Sci.,Info. Engineering and Automation Yunnan Key Lab. of AI,Kunming,China","institution_ids":["https://openalex.org/I146071755"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076315968","display_name":"Linqin Wang","orcid":"https://orcid.org/0000-0001-6293-6742"},"institutions":[{"id":"https://openalex.org/I146071755","display_name":"Kunming University","ror":"https://ror.org/035rhx828","country_code":"CN","type":"education","lineage":["https://openalex.org/I146071755"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linqin Wang","raw_affiliation_strings":["Kunming University of Tech. and Sci.,Info. Engineering and Automation Yunnan Key Lab. of AI,Kunming,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kunming University of Tech. and Sci.,Info. Engineering and Automation Yunnan Key Lab. of AI,Kunming,China","institution_ids":["https://openalex.org/I146071755"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017471172","display_name":"Shengxiang Gao","orcid":"https://orcid.org/0000-0002-2980-8420"},"institutions":[{"id":"https://openalex.org/I146071755","display_name":"Kunming University","ror":"https://ror.org/035rhx828","country_code":"CN","type":"education","lineage":["https://openalex.org/I146071755"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengxiang Gao","raw_affiliation_strings":["Kunming University of Tech. and Sci.,Info. Engineering and Automation Yunnan Key Lab. of AI,Kunming,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kunming University of Tech. and Sci.,Info. Engineering and Automation Yunnan Key Lab. of AI,Kunming,China","institution_ids":["https://openalex.org/I146071755"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068973438","display_name":"Ling Dong","orcid":"https://orcid.org/0000-0003-1612-6671"},"institutions":[{"id":"https://openalex.org/I146071755","display_name":"Kunming University","ror":"https://ror.org/035rhx828","country_code":"CN","type":"education","lineage":["https://openalex.org/I146071755"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ling Dong","raw_affiliation_strings":["Kunming University of Tech. and Sci.,Info. Engineering and Automation Yunnan Key Lab. of AI,Kunming,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kunming University of Tech. and Sci.,Info. Engineering and Automation Yunnan Key Lab. of AI,Kunming,China","institution_ids":["https://openalex.org/I146071755"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100393038","display_name":"Wenjun Wang","orcid":"https://orcid.org/0000-0002-9886-694X"},"institutions":[{"id":"https://openalex.org/I146071755","display_name":"Kunming University","ror":"https://ror.org/035rhx828","country_code":"CN","type":"education","lineage":["https://openalex.org/I146071755"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenjun Wang","raw_affiliation_strings":["Kunming University of Tech. and Sci.,Info. Engineering and Automation Yunnan Key Lab. of AI,Kunming,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kunming University of Tech. and Sci.,Info. Engineering and Automation Yunnan Key Lab. of AI,Kunming,China","institution_ids":["https://openalex.org/I146071755"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I146071755"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02575831,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9976000189781189,"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":0.9976000189781189,"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":0.9833999872207642,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9681000113487244,"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/computer-science","display_name":"Computer science","score":0.6583248376846313},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6211325526237488},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6179578304290771},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.6006752252578735},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.5442594885826111},{"id":"https://openalex.org/keywords/decomposition","display_name":"Decomposition","score":0.5282708406448364},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14949488639831543},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.11507782340049744},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.05938836932182312}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6583248376846313},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6211325526237488},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6179578304290771},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.6006752252578735},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.5442594885826111},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.5282708406448364},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14949488639831543},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11507782340049744},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.05938836932182312},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889039","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889039","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":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W51373460","https://openalex.org/W2963242190","https://openalex.org/W2964243274","https://openalex.org/W2969658393","https://openalex.org/W2972359262","https://openalex.org/W2973034126","https://openalex.org/W3022876224","https://openalex.org/W3081416955","https://openalex.org/W3096303254","https://openalex.org/W3096656663","https://openalex.org/W3161492781","https://openalex.org/W3195171908","https://openalex.org/W3197287223","https://openalex.org/W4210690177","https://openalex.org/W4221166168","https://openalex.org/W4225943493","https://openalex.org/W4285182272","https://openalex.org/W4285189120","https://openalex.org/W4307323391","https://openalex.org/W4390480998","https://openalex.org/W6752124048","https://openalex.org/W6755207826","https://openalex.org/W6778823374","https://openalex.org/W6850334629"],"related_works":["https://openalex.org/W2112835755","https://openalex.org/W4291951920","https://openalex.org/W2349674371","https://openalex.org/W2097495471","https://openalex.org/W1696545756","https://openalex.org/W2952827811","https://openalex.org/W2056202066","https://openalex.org/W2963262648","https://openalex.org/W4301867002","https://openalex.org/W2380059383"],"abstract_inverted_index":{"Recent":[0],"advancements":[1],"in":[2,75],"end-to-end":[3],"text-to-speech":[4],"models":[5],"have":[6],"made":[7],"significant":[8],"progress.":[9],"However,":[10],"these":[11],"approaches":[12],"based":[13],"on":[14],"high-resource":[15],"languages,":[16,21,109],"are":[17,28,151],"inapplicable":[18],"for":[19,41,64,98,133],"low-resource":[20,24,42,66,134],"and":[22,61,90,94],"existing":[23],"speech":[25,43,116,128,135],"synthesis":[26,44],"methods":[27,132],"typically":[29],"specific":[30],"to":[31,140],"single":[32],"languages.":[33],"Consequently,":[34],"the":[35,100,123,126],"pursuit":[36],"of":[37,115,125,145,147],"a":[38,47,59,76,83],"universal":[39,62],"methodology":[40],"emerges":[45],"as":[46],"critical":[48],"problem":[49],"that":[50,122],"requires":[51],"immediate":[52],"attention.":[53],"Unlike":[54],"previous":[55],"works,":[56],"we":[57],"propose":[58],"novel":[60],"approach":[63],"multiple":[65],"languages":[67],"by":[68,81],"leveraging":[69],"phoneme":[70,85,88],"fusion":[71,89],"coordinating":[72],"low-rank":[73],"decomposition":[74,96],"pre-trained":[77],"multilingual":[78,84],"model.":[79],"Specifically,":[80],"establishing":[82],"dictionary":[86],"through":[87],"applying":[91],"parameter":[92],"freezing":[93],"matrix":[95],"techniques":[97],"fine-tuning,":[99],"proposed":[101],"method":[102],"was":[103],"extensively":[104],"evaluated":[105],"across":[106],"four":[107],"different":[108],"each":[110],"utilizing":[111],"approximately":[112],"3":[113],"hours":[114,146],"data.":[117,148],"The":[118],"experimental":[119],"results":[120],"demonstrate":[121],"quality":[124],"synthesized":[127],"surpasses":[129],"current":[130],"mainstream":[131],"synthesis,":[136],"achieving":[137],"outcomes":[138],"comparable":[139],"those":[141],"trained":[142],"with":[143],"tens":[144],"Audio":[149],"samples":[150],"available":[152],"at":[153],"https://priankaan.github.io/Demo.github.io.":[154]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}