{"id":"https://openalex.org/W3163031268","doi":"https://doi.org/10.1109/icassp39728.2021.9414043","title":"Litesing: Towards Fast, Lightweight and Expressive Singing Voice Synthesis","display_name":"Litesing: Towards Fast, Lightweight and Expressive Singing Voice Synthesis","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3163031268","doi":"https://doi.org/10.1109/icassp39728.2021.9414043","mag":"3163031268"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414043","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414043","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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/A5001776951","display_name":"Xiaobin Zhuang","orcid":"https://orcid.org/0000-0002-0285-6705"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaobin Zhuang","raw_affiliation_strings":["Tencent Music Entertainment, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent Music Entertainment, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101911266","display_name":"Tao Jiang","orcid":"https://orcid.org/0000-0003-3833-4498"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Jiang","raw_affiliation_strings":["Tencent Music Entertainment, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent Music Entertainment, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066751519","display_name":"Szu-Yu Chou","orcid":"https://orcid.org/0000-0001-5738-8470"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Szu-Yu Chou","raw_affiliation_strings":["Tencent Music Entertainment, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent Music Entertainment, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005167596","display_name":"Bin Wu","orcid":"https://orcid.org/0000-0002-4722-4226"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Wu","raw_affiliation_strings":["Tencent Music Entertainment, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent Music Entertainment, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110055668","display_name":"Peng Hu","orcid":"https://orcid.org/0000-0003-0186-2190"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Hu","raw_affiliation_strings":["Tencent Music Entertainment, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent Music Entertainment, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103134236","display_name":"Simon Lui","orcid":"https://orcid.org/0000-0002-0829-2867"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Simon Lui","raw_affiliation_strings":["Tencent Music Entertainment, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent Music Entertainment, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.853,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.85786972,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"7078","last_page":"7082"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9994999766349792,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7596837282180786},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.7424077987670898},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6655177474021912},{"id":"https://openalex.org/keywords/timbre","display_name":"Timbre","score":0.5840726494789124},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4787932336330414},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2474057972431183}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7596837282180786},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.7424077987670898},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6655177474021912},{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.5840726494789124},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4787932336330414},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2474057972431183},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414043","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414043","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.8799999952316284}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2102870814","https://openalex.org/W2471520273","https://openalex.org/W2516406502","https://openalex.org/W2519091744","https://openalex.org/W2606052883","https://openalex.org/W2794490148","https://openalex.org/W2937242376","https://openalex.org/W2946200149","https://openalex.org/W2949382160","https://openalex.org/W2962883485","https://openalex.org/W2963609956","https://openalex.org/W2963691546","https://openalex.org/W2963975282","https://openalex.org/W2964121744","https://openalex.org/W2964307104","https://openalex.org/W2970006822","https://openalex.org/W2971753973","https://openalex.org/W2981934523","https://openalex.org/W2984106626","https://openalex.org/W3015645837","https://openalex.org/W3033411150","https://openalex.org/W3035430139","https://openalex.org/W3037567775","https://openalex.org/W3097514409","https://openalex.org/W4298580827","https://openalex.org/W6631190155","https://openalex.org/W6748409065","https://openalex.org/W6749489859","https://openalex.org/W6750489868","https://openalex.org/W6753855596","https://openalex.org/W6761725420","https://openalex.org/W6763832098","https://openalex.org/W6767111847","https://openalex.org/W6767453231","https://openalex.org/W6769050887","https://openalex.org/W6778823374","https://openalex.org/W6779669310"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W2088854863","https://openalex.org/W4402568167","https://openalex.org/W3179495260","https://openalex.org/W2897924318","https://openalex.org/W2138997758"],"abstract_inverted_index":{"LiteSing":[0,112,146,166],"proposed":[1],"in":[2,27,54,153],"this":[3,55],"paper":[4,56],"is":[5,14,101],"a":[6,33,97,136],"high-quality":[7],"singing":[8],"voice":[9],"synthesis":[10],"(SVS)":[11],"system,":[12],"which":[13,69,161],"fast,":[15],"lightweight":[16],"and":[17,30,44,65,80,134,156],"expressive.":[18],"This":[19],"model":[20,116],"mainly":[21],"stacks":[22],"several":[23],"non-autoregressive":[24],"WaveNet":[25],"blocks":[26],"the":[28,41,74,78,81,86,104,114,163,168],"encoder":[29],"decoder":[31],"under":[32],"generative":[34],"adversarial":[35],"architecture,":[36],"predicts":[37],"full":[38,52],"conditions":[39,53],"from":[40,48],"musical":[42],"score,":[43],"generates":[45],"acoustic":[46],"features":[47,83],"these":[49,89],"conditions.":[50],"The":[51],"consist":[57],"of":[58,93,165],"dynamic":[59,66,157],"spectrogram":[60,158],"energy,":[61],"voiced/unvoiced":[62],"(V/UV)":[63],"decision":[64],"pitch":[67,79,105,154],"curve,":[68],"are":[70],"proven":[71],"related":[72],"to":[73],"expressiveness.":[75],"We":[76],"predict":[77],"timbre":[82],"separately,":[84],"avoiding":[85],"interdependence":[87],"between":[88],"two":[90],"features.":[91],"Instead":[92],"neural":[94],"network":[95],"vocoders,":[96],"parametric":[98],"WORLD":[99],"vocoder":[100],"employed":[102],"for":[103],"curve":[106,155],"consistency.":[107],"Experiment":[108],"results":[109],"show":[110],"that":[111],"outperforms":[113],"baseline":[115,152],"using":[117],"feed-forward":[118],"Transformer":[119],"by":[120],"1.386":[121],"times":[122,128],"faster":[123],"on":[124,130,139],"inference":[125],"speed,":[126],"15":[127],"smaller":[129],"training":[131],"parameters":[132],"number,":[133],"achieves":[135,147],"similar":[137],"MOS":[138],"sound":[140],"quality.":[141],"Through":[142],"an":[143],"A/B":[144],"test,":[145],"67.3%":[148],"preference":[149],"rate":[150],"over":[151,167],"energy":[159],"prediction.":[160],"demonstrates":[162],"advantage":[164],"other":[169],"compared":[170],"models.":[171]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}