{"id":"https://openalex.org/W4324116678","doi":"https://doi.org/10.1109/lsp.2023.3256319","title":"Mandarin Text-to-Speech Front-End with Lightweight Distilled Convolution Network","display_name":"Mandarin Text-to-Speech Front-End with Lightweight Distilled Convolution Network","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4324116678","doi":"https://doi.org/10.1109/lsp.2023.3256319"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2023.3256319","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/lsp.2023.3256319","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-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/A5040153479","display_name":"Wei Zhao","orcid":"https://orcid.org/0000-0001-8452-9339"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wei Zhao","raw_affiliation_strings":["College of Electrical Engineering, Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"College of Electrical Engineering, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020535366","display_name":"Zuyi Wang","orcid":"https://orcid.org/0000-0001-7652-268X"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zuyi Wang","raw_affiliation_strings":["College of Electrical Engineering, Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"College of Electrical Engineering, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100648031","display_name":"Xu Li","orcid":"https://orcid.org/0000-0001-7874-629X"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Xu","raw_affiliation_strings":["College of Electrical Engineering, Zhejiang University, Hangzhou, China","Institute of Robotics, Zhejiang University, Yuyao, China"],"affiliations":[{"raw_affiliation_string":"College of Electrical Engineering, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"Institute of Robotics, Zhejiang University, Yuyao, China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5040153479"],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02156762,"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":0.9998999834060669,"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":0.9998999834060669,"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/T10028","display_name":"Topic Modeling","score":0.9991000294685364,"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":0.9976999759674072,"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/computer-science","display_name":"Computer science","score":0.7835425138473511},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6371745467185974},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.610529899597168},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5740112066268921},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.5156346559524536},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46656695008277893},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.46306508779525757},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.4360291063785553},{"id":"https://openalex.org/keywords/front-and-back-ends","display_name":"Front and back ends","score":0.4145733714103699},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.12114176154136658},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.0733809769153595}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7835425138473511},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6371745467185974},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.610529899597168},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5740112066268921},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.5156346559524536},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46656695008277893},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.46306508779525757},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.4360291063785553},{"id":"https://openalex.org/C53016008","wikidata":"https://www.wikidata.org/wiki/Q620167","display_name":"Front and back ends","level":2,"score":0.4145733714103699},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.12114176154136658},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0733809769153595},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lsp.2023.3256319","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/lsp.2023.3256319","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.8100000023841858,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1973424788","https://openalex.org/W2042463830","https://openalex.org/W2133834138","https://openalex.org/W2158912874","https://openalex.org/W2162433174","https://openalex.org/W2531409750","https://openalex.org/W2612199078","https://openalex.org/W2883780447","https://openalex.org/W2889523925","https://openalex.org/W2896457183","https://openalex.org/W2946200149","https://openalex.org/W2952370363","https://openalex.org/W2952809536","https://openalex.org/W2963300588","https://openalex.org/W2970454332","https://openalex.org/W2972585802","https://openalex.org/W2972881244","https://openalex.org/W2972956685","https://openalex.org/W2978017171","https://openalex.org/W2996428491","https://openalex.org/W3007419862","https://openalex.org/W3047171714","https://openalex.org/W3095762785","https://openalex.org/W3105966348","https://openalex.org/W3113850747","https://openalex.org/W3196475561","https://openalex.org/W3198533616","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6680092363","https://openalex.org/W6683633098","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6757585730","https://openalex.org/W6763832098","https://openalex.org/W6768021236","https://openalex.org/W6768851824","https://openalex.org/W6781275321","https://openalex.org/W6788095661"],"related_works":["https://openalex.org/W2374317326","https://openalex.org/W2990005675","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/W2366752344"],"abstract_inverted_index":{"Mandarin":[0,141],"text-to-speech":[1],"(TTS)":[2],"systems":[3],"heavily":[4],"depend":[5],"on":[6,57,138],"front-end":[7,143],"processing,":[8],"such":[9,27],"as":[10,28,101],"grapheme-to-phoneme":[11],"conversion":[12],"and":[13,60,85,123,167],"prosodic":[14],"boundary":[15],"prediction,":[16],"to":[17,79,104,133,156],"produce":[18],"expressive,":[19],"human-like":[20],"speech.":[21],"Utilizing":[22],"a":[23,64,71,96,134],"pre-trained":[24],"language":[25],"model,":[26],"the":[29,39,44,80,86,105,116,121,130,164],"bidirectional":[30],"encoder":[31],"representations":[32],"from":[33,129],"Transformers":[34],"(BERT),":[35],"could":[36],"significantly":[37],"improve":[38],"TTS":[40,52,142],"front-end\u2019s":[41],"performance.":[42],"However,":[43],"original":[45],"BERT":[46,66,159],"is":[47],"too":[48],"big":[49],"for":[50,120],"edge":[51],"applications":[53],"with":[54],"tight":[55],"limits":[56],"memory":[58],"costs":[59],"inference":[61,168],"latency.":[62,169],"Although":[63],"distilled":[65,98,106,149,158],"can":[67,152],"alleviate":[68],"this":[69,92],"problem,":[70],"considerable":[72],"efficiency":[73],"barrier":[74],"may":[75],"still":[76],"exist":[77],"due":[78],"self-attention":[81,118,131],"module's":[82,88],"quadratic":[83],"complexity":[84],"feed-forward":[87],"enormous":[89],"computation.":[90],"To":[91],"end,":[93],"we":[94,126],"propose":[95],"lightweight":[97],"convolution":[99,135,150],"network":[100,119,132],"an":[102],"alternative":[103],"BERT.":[107],"Unlike":[108],"previous":[109],"knowledge":[110,128],"distillation":[111],"methods,":[112],"which":[113],"commonly":[114],"used":[115],"same":[117],"teacher":[122],"student":[124],"models,":[125],"transfer":[127],"network.":[136],"Experiments":[137],"two":[139],"major":[140],"tasks":[144],"have":[145],"shown":[146],"that":[147],"our":[148],"model":[151,165],"achieve":[153],"comparable":[154],"results":[155],"various":[157],"variants":[160],"while":[161],"drastically":[162],"reducing":[163],"size":[166]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}