{"id":"https://openalex.org/W4392909673","doi":"https://doi.org/10.1109/icassp48485.2024.10446112","title":"Fastmandarin: Efficient Local Modeling for Natural Mandarin Speech Synthesis","display_name":"Fastmandarin: Efficient Local Modeling for Natural Mandarin Speech Synthesis","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392909673","doi":"https://doi.org/10.1109/icassp48485.2024.10446112"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446112","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446112","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5102000320","display_name":"Chenglong Jiang","orcid":"https://orcid.org/0009-0007-3935-9482"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chenglong Jiang","raw_affiliation_strings":["South China University of Technology,School of Computer and Engineering,Guangzhou,China","School of Computer and Engineering, South China University of Technology, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"South China University of Technology,School of Computer and Engineering,Guangzhou,China","institution_ids":["https://openalex.org/I90610280"]},{"raw_affiliation_string":"School of Computer and Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101828088","display_name":"Ying Gao","orcid":"https://orcid.org/0000-0002-8925-8192"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Gao","raw_affiliation_strings":["South China University of Technology,School of Computer and Engineering,Guangzhou,China","School of Computer and Engineering, South China University of Technology, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"South China University of Technology,School of Computer and Engineering,Guangzhou,China","institution_ids":["https://openalex.org/I90610280"]},{"raw_affiliation_string":"School of Computer and Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101731285","display_name":"Hao Jin","orcid":"https://orcid.org/0000-0003-2294-3408"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Jin","raw_affiliation_strings":["South China University of Technology,School of Computer and Engineering,Guangzhou,China","School of Computer and Engineering, South China University of Technology, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"South China University of Technology,School of Computer and Engineering,Guangzhou,China","institution_ids":["https://openalex.org/I90610280"]},{"raw_affiliation_string":"School of Computer and Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103345129","display_name":"L. J. Pan","orcid":"https://orcid.org/0009-0005-1914-7306"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linrong Pan","raw_affiliation_strings":["South China University of Technology,School of Computer and Engineering,Guangzhou,China","School of Computer and Engineering, South China University of Technology, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"South China University of Technology,School of Computer and Engineering,Guangzhou,China","institution_ids":["https://openalex.org/I90610280"]},{"raw_affiliation_string":"School of Computer and Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5105759393","display_name":"Wing W. Y. Ng","orcid":"https://orcid.org/0000-0003-0783-3585"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wing W. Y. Ng","raw_affiliation_strings":["South China University of Technology,School of Computer and Engineering,Guangzhou,China","School of Computer and Engineering, South China University of Technology, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"South China University of Technology,School of Computer and Engineering,Guangzhou,China","institution_ids":["https://openalex.org/I90610280"]},{"raw_affiliation_string":"School of Computer and Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5102000320"],"corresponding_institution_ids":["https://openalex.org/I90610280"],"apc_list":null,"apc_paid":null,"fwci":0.3637,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.61750422,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"461","last_page":"465"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9980000257492065,"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":0.9980000257492065,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9779999852180481,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9578999876976013,"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/mandarin-chinese","display_name":"Mandarin Chinese","score":0.8739811778068542},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7216169834136963},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6220378875732422},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.5720353126525879},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5575957298278809},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.41704124212265015},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3572913408279419},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.12306290864944458}],"concepts":[{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.8739811778068542},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7216169834136963},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6220378875732422},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.5720353126525879},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5575957298278809},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.41704124212265015},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3572913408279419},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.12306290864944458},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"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/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446112","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446112","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1576227399","https://openalex.org/W2091425152","https://openalex.org/W2125838338","https://openalex.org/W2134973740","https://openalex.org/W2142384583","https://openalex.org/W2515943672","https://openalex.org/W2766812927","https://openalex.org/W2901997113","https://openalex.org/W2903739847","https://openalex.org/W2914584698","https://openalex.org/W2916009164","https://openalex.org/W2963609956","https://openalex.org/W2964243274","https://openalex.org/W2964302946","https://openalex.org/W2973043900","https://openalex.org/W3005962597","https://openalex.org/W3007580377","https://openalex.org/W3015680182","https://openalex.org/W3033411150","https://openalex.org/W4212774754","https://openalex.org/W4385245566","https://openalex.org/W6679436768","https://openalex.org/W6718763946","https://openalex.org/W6731370813","https://openalex.org/W6778823374","https://openalex.org/W6783867762","https://openalex.org/W6810833361"],"related_works":["https://openalex.org/W2990005675","https://openalex.org/W2374317326","https://openalex.org/W1603321096","https://openalex.org/W2394766824","https://openalex.org/W2078713291","https://openalex.org/W2361574037","https://openalex.org/W2386292991","https://openalex.org/W2364440891","https://openalex.org/W2393726922","https://openalex.org/W127416991"],"abstract_inverted_index":{"Attention-based":[0],"speech":[1,36,126],"synthesis":[2,37,127],"methods":[3,43],"often":[4],"suffer":[5],"from":[6],"dispersed":[7],"attention":[8],"across":[9],"the":[10,70],"entire":[11],"input":[12],"sequence,":[13],"resulting":[14],"in":[15,83,120],"poor":[16],"local":[17,46,81,121],"modeling":[18,47],"and":[19,33,48,64,107],"unnatural":[20],"Mandarin":[21,35,125],"synthesized":[22],"speech.":[23],"To":[24],"address":[25],"these":[26,65],"issues,":[27],"we":[28,53,87,103],"present":[29],"FastMandarin,":[30],"a":[31,62,89],"rapid":[32],"natural":[34],"framework":[38],"that":[39,95,117],"employs":[40,96],"two":[41],"explicit":[42],"to":[44,57,110],"enhance":[45,111],"improve":[49],"pronunciation":[50],"representation.":[51],"Firstly,":[52],"tag":[54],"Chinese":[55],"characters":[56],"delineate":[58],"phrase":[59],"boundaries":[60],"within":[61],"sentence,":[63],"tags":[66],"are":[67],"integrated":[68],"into":[69],"network\u2019s":[71],"hidden":[72],"layer":[73],"features":[74],"at":[75],"each":[76],"time":[77],"step,":[78],"effectively":[79],"bolstering":[80],"contributions":[82],"latent":[84],"representations.":[85],"Secondly,":[86],"introduce":[88],"multi-scale":[90],"context":[91],"feature":[92],"extractor":[93],"network":[94],"parallel":[97],"convolution":[98],"with":[99],"various":[100],"filters.":[101],"Additionally,":[102],"optimize":[104],"duration":[105],"alignment":[106],"Mel-spectrogram":[108],"reconstruction":[109],"overall":[112],"performance.":[113],"Experimental":[114],"results":[115],"demonstrate":[116],"FastMandarin":[118],"excels":[119],"modeling,":[122],"delivering":[123],"robust":[124],"results.":[128]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}