{"id":"https://openalex.org/W4392904245","doi":"https://doi.org/10.1109/icassp48485.2024.10445879","title":"TextrolSpeech: A Text Style Control Speech Corpus with Codec Language Text-to-Speech Models","display_name":"TextrolSpeech: A Text Style Control Speech Corpus with Codec Language Text-to-Speech Models","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904245","doi":"https://doi.org/10.1109/icassp48485.2024.10445879"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10445879","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10445879","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/A5102904447","display_name":"Shengpeng Ji","orcid":null},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]},{"id":"https://openalex.org/I4210146936","display_name":"Huawei Technologies (United States)","ror":"https://ror.org/03jyqk712","country_code":"US","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210146936"]},{"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","US"],"is_corresponding":false,"raw_author_name":"Shengpeng Ji","raw_affiliation_strings":["Zhejiang University,Huawei Cloud","Huawei Cloud, Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,Huawei Cloud","institution_ids":["https://openalex.org/I4210146936","https://openalex.org/I2250955327"]},{"raw_affiliation_string":"Huawei Cloud, Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101230918","display_name":"Jialong Zuo","orcid":null},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]},{"id":"https://openalex.org/I4210146936","display_name":"Huawei Technologies (United States)","ror":"https://ror.org/03jyqk712","country_code":"US","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210146936"]},{"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","US"],"is_corresponding":false,"raw_author_name":"Jialong Zuo","raw_affiliation_strings":["Zhejiang University,Huawei Cloud","Huawei Cloud, Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,Huawei Cloud","institution_ids":["https://openalex.org/I4210146936","https://openalex.org/I2250955327"]},{"raw_affiliation_string":"Huawei Cloud, Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113394692","display_name":"Minghui Fang","orcid":null},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]},{"id":"https://openalex.org/I4210146936","display_name":"Huawei Technologies (United States)","ror":"https://ror.org/03jyqk712","country_code":"US","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210146936"]},{"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","US"],"is_corresponding":false,"raw_author_name":"Minghui Fang","raw_affiliation_strings":["Zhejiang University,Huawei Cloud","Huawei Cloud, Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,Huawei Cloud","institution_ids":["https://openalex.org/I4210146936","https://openalex.org/I2250955327"]},{"raw_affiliation_string":"Huawei Cloud, Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083611896","display_name":"Ziyue Karen Jiang","orcid":"https://orcid.org/0009-0007-4158-4689"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]},{"id":"https://openalex.org/I4210146936","display_name":"Huawei Technologies (United States)","ror":"https://ror.org/03jyqk712","country_code":"US","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210146936"]},{"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","US"],"is_corresponding":false,"raw_author_name":"Ziyue Jiang","raw_affiliation_strings":["Zhejiang University,Huawei Cloud","Huawei Cloud, Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,Huawei Cloud","institution_ids":["https://openalex.org/I4210146936","https://openalex.org/I2250955327"]},{"raw_affiliation_string":"Huawei Cloud, Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060844215","display_name":"Feiyang Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]},{"id":"https://openalex.org/I4210146936","display_name":"Huawei Technologies (United States)","ror":"https://ror.org/03jyqk712","country_code":"US","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210146936"]},{"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","US"],"is_corresponding":false,"raw_author_name":"Feiyang Chen","raw_affiliation_strings":["Zhejiang University,Huawei Cloud","Huawei Cloud, Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,Huawei Cloud","institution_ids":["https://openalex.org/I4210146936","https://openalex.org/I2250955327"]},{"raw_affiliation_string":"Huawei Cloud, Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047258925","display_name":"Xinyu Duan","orcid":"https://orcid.org/0000-0002-6803-7964"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]},{"id":"https://openalex.org/I4210146936","display_name":"Huawei Technologies (United States)","ror":"https://ror.org/03jyqk712","country_code":"US","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210146936"]},{"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","US"],"is_corresponding":false,"raw_author_name":"Xinyu Duan","raw_affiliation_strings":["Zhejiang University,Huawei Cloud","Huawei Cloud, Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,Huawei Cloud","institution_ids":["https://openalex.org/I4210146936","https://openalex.org/I2250955327"]},{"raw_affiliation_string":"Huawei Cloud, Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025894594","display_name":"Baoxing Huai","orcid":null},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]},{"id":"https://openalex.org/I4210146936","display_name":"Huawei Technologies (United States)","ror":"https://ror.org/03jyqk712","country_code":"US","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210146936"]},{"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","US"],"is_corresponding":false,"raw_author_name":"Baoxing Huai","raw_affiliation_strings":["Zhejiang University,Huawei Cloud","Huawei Cloud, Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,Huawei Cloud","institution_ids":["https://openalex.org/I4210146936","https://openalex.org/I2250955327"]},{"raw_affiliation_string":"Huawei Cloud, Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079260216","display_name":"Zhou Zhao","orcid":"https://orcid.org/0000-0001-6121-0384"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]},{"id":"https://openalex.org/I4210146936","display_name":"Huawei Technologies (United States)","ror":"https://ror.org/03jyqk712","country_code":"US","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210146936"]},{"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","US"],"is_corresponding":false,"raw_author_name":"Zhou Zhao","raw_affiliation_strings":["Zhejiang University,Huawei Cloud","Huawei Cloud, Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,Huawei Cloud","institution_ids":["https://openalex.org/I4210146936","https://openalex.org/I2250955327"]},{"raw_affiliation_string":"Huawei Cloud, Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.5858,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.9543166,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"10301","last_page":"10305"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9997000098228455,"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":0.9980999827384949,"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":0.8468908667564392},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.7229883074760437},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5739787817001343},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5430303812026978},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5361784100532532},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5324752330780029},{"id":"https://openalex.org/keywords/codec","display_name":"Codec","score":0.5181218981742859},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4910571575164795},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.4672923684120178},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.45438823103904724},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43245774507522583}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8468908667564392},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.7229883074760437},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5739787817001343},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5430303812026978},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5361784100532532},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5324752330780029},{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.5181218981742859},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4910571575164795},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.4672923684120178},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.45438823103904724},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43245774507522583},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10445879","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10445879","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":[{"id":"https://openalex.org/G6050241676","display_name":"\u57fa\u4e8e\u5f31\u6807\u6ce8\u7684\u8de8\u6a21\u6001\u89c6\u9891\u5b9a\u4f4d\u65b9\u6cd5\u7814\u7a76","funder_award_id":"62072397","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2471520273","https://openalex.org/W2972359262","https://openalex.org/W2981437154","https://openalex.org/W2998572311","https://openalex.org/W3033411150","https://openalex.org/W3094650042","https://openalex.org/W3099284785","https://openalex.org/W3160638507","https://openalex.org/W3163573274","https://openalex.org/W3197541421","https://openalex.org/W4307106676","https://openalex.org/W4307323391","https://openalex.org/W4313679638","https://openalex.org/W4375869257","https://openalex.org/W4379924545","https://openalex.org/W4385822534","https://openalex.org/W4385822787","https://openalex.org/W4398152753","https://openalex.org/W6749555683","https://openalex.org/W6778823374","https://openalex.org/W6803567076","https://openalex.org/W6848735303","https://openalex.org/W6852870047"],"related_works":["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/W1976719989","https://openalex.org/W3127543252","https://openalex.org/W2065606036","https://openalex.org/W2016904525"],"abstract_inverted_index":{"Recently,":[0],"there":[1],"has":[2,45],"been":[3],"a":[4,48,123,169,198],"growing":[5],"interest":[6],"in":[7,106,139,201],"the":[8,58,70,87,131,146,183,190,193,202,211],"field":[9],"of":[10,60,72,79,103,192],"controllable":[11,166,203],"Text-to-Speech":[12],"(TTS).":[13],"While":[14],"previous":[15],"studies":[16],"have":[17],"relied":[18],"on":[19,27,210],"users":[20],"providing":[21],"specific":[22],"style":[23,67,104,112,137,153],"factor":[24],"values":[25],"based":[26],"acoustic":[28],"knowledge":[29],"or":[30],"selecting":[31],"reference":[32],"speeches":[33],"that":[34,128],"meet":[35],"certain":[36],"requirements,":[37],"generating":[38,135,149],"speech":[39,62,90,116],"solely":[40],"from":[41],"natural":[42,65,107,136],"text":[43,66,96,108,165],"prompts":[44],"emerged":[46],"as":[47,168,177],"new":[49],"challenge":[50,54],"for":[51,134,148],"researchers.":[52],"This":[53,162],"arises":[55],"due":[56],"to":[57,144,181],"scarcity":[59],"high-quality":[61],"datasets":[63],"with":[64,94,110,151],"prompt":[68,105,125],"and":[69,114],"absence":[71],"advanced":[73],"text-controllable":[74],"TTS":[75,167,204],"models.":[76],"In":[77],"light":[78],"this,":[80],"1)":[81],"we":[82,121,155,187],"propose":[83,156],"TextrolSpeech,":[84],"which":[85],"is":[86],"first":[88],"large-scale":[89],"emotion":[91],"dataset":[92,99],"annotated":[93],"rich":[95],"attributes.":[97],"The":[98],"comprises":[100],"236,203":[101],"pairs":[102],"descriptions":[109,138],"five":[111],"factors":[113],"corresponding":[115],"samples.":[117],"Through":[118],"iterative":[119],"experimentation,":[120],"introduce":[122],"multi-stage":[124],"programming":[126],"approach":[127],"effectively":[129],"utilizes":[130],"GPT":[132],"model":[133,171,195],"large":[140],"volumes.":[141],"2)":[142],"Furthermore,":[143],"address":[145],"need":[147],"audio":[150,174],"greater":[152],"diversity,":[154],"an":[157,178],"efficient":[158],"architecture":[159,163],"called":[160],"Salle.":[161],"treats":[164],"language":[170],"task,":[172],"utilizing":[173],"codec":[175],"codes":[176],"intermediate":[179],"representation":[180],"replace":[182],"conventional":[184],"mel-spectrogram.":[185],"Finally,":[186],"successfully":[188],"demonstrate":[189],"ability":[191],"proposed":[194],"by":[196],"showing":[197],"comparable":[199],"performance":[200],"task.":[205],"Audio":[206],"samples":[207],"are":[208],"available":[209],"demo":[212],"page":[213],"https://sall-e.github.io/.":[214]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
