{"id":"https://openalex.org/W4388820758","doi":"https://doi.org/10.1109/apsipaasc58517.2023.10317138","title":"Multi-granularity Semantic and Acoustic Stress Prediction for Expressive TTS","display_name":"Multi-granularity Semantic and Acoustic Stress Prediction for Expressive TTS","publication_year":2023,"publication_date":"2023-10-31","ids":{"openalex":"https://openalex.org/W4388820758","doi":"https://doi.org/10.1109/apsipaasc58517.2023.10317138"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc58517.2023.10317138","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/apsipaasc58517.2023.10317138","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5104200277","display_name":"Wenjiang Chi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210132948","display_name":"Shanghai Chengtou (China)","ror":"https://ror.org/041rv6v55","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210132948"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wenjiang Chi","raw_affiliation_strings":["Shanghai Mobvoi Information Technology Co., Ltd,China","Shanghai Mobvoi Information Technology Co., Ltd, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Mobvoi Information Technology Co., Ltd,China","institution_ids":["https://openalex.org/I4210132948"]},{"raw_affiliation_string":"Shanghai Mobvoi Information Technology Co., Ltd, China","institution_ids":["https://openalex.org/I4210132948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100530661","display_name":"Xiaoqin Feng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210132948","display_name":"Shanghai Chengtou (China)","ror":"https://ror.org/041rv6v55","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210132948"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoqin Feng","raw_affiliation_strings":["Shanghai Mobvoi Information Technology Co., Ltd,China","Shanghai Mobvoi Information Technology Co., Ltd, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Mobvoi Information Technology Co., Ltd,China","institution_ids":["https://openalex.org/I4210132948"]},{"raw_affiliation_string":"Shanghai Mobvoi Information Technology Co., Ltd, China","institution_ids":["https://openalex.org/I4210132948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009337933","display_name":"Liumeng Xue","orcid":"https://orcid.org/0000-0003-2815-8494"},"institutions":[{"id":"https://openalex.org/I2800643029","display_name":"Association for Symbolic Logic","ror":"https://ror.org/00baryp08","country_code":"US","type":"other","lineage":["https://openalex.org/I2800643029"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liumeng Xue","raw_affiliation_strings":["Audio, Speech and Language Processing Group (ASLP)"],"affiliations":[{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP)","institution_ids":["https://openalex.org/I2800643029"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104124393","display_name":"Yunlin Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210132948","display_name":"Shanghai Chengtou (China)","ror":"https://ror.org/041rv6v55","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210132948"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunlin Chen","raw_affiliation_strings":["Shanghai Mobvoi Information Technology Co., Ltd,China","Shanghai Mobvoi Information Technology Co., Ltd, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Mobvoi Information Technology Co., Ltd,China","institution_ids":["https://openalex.org/I4210132948"]},{"raw_affiliation_string":"Shanghai Mobvoi Information Technology Co., Ltd, China","institution_ids":["https://openalex.org/I4210132948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100668966","display_name":"Lei Xie","orcid":"https://orcid.org/0000-0001-8234-0823"},"institutions":[{"id":"https://openalex.org/I2800643029","display_name":"Association for Symbolic Logic","ror":"https://ror.org/00baryp08","country_code":"US","type":"other","lineage":["https://openalex.org/I2800643029"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lei Xie","raw_affiliation_strings":["Audio, Speech and Language Processing Group (ASLP)"],"affiliations":[{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP)","institution_ids":["https://openalex.org/I2800643029"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100782898","display_name":"Zhifei Li","orcid":"https://orcid.org/0000-0003-1246-741X"},"institutions":[{"id":"https://openalex.org/I4210132948","display_name":"Shanghai Chengtou (China)","ror":"https://ror.org/041rv6v55","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210132948"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhifei Li","raw_affiliation_strings":["Shanghai Mobvoi Information Technology Co., Ltd,China","Shanghai Mobvoi Information Technology Co., Ltd, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Mobvoi Information Technology Co., Ltd,China","institution_ids":["https://openalex.org/I4210132948"]},{"raw_affiliation_string":"Shanghai Mobvoi Information Technology Co., Ltd, China","institution_ids":["https://openalex.org/I4210132948"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5104200277"],"corresponding_institution_ids":["https://openalex.org/I4210132948"],"apc_list":null,"apc_paid":null,"fwci":0.5882,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.72355581,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"2409","last_page":"2415"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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":0.9994999766349792,"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":0.996999979019165,"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":0.9965999722480774,"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":0.7839920520782471},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.7816709280014038},{"id":"https://openalex.org/keywords/stress","display_name":"Stress (linguistics)","score":0.7738857269287109},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.68443763256073},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6189120411872864},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5600992441177368},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.509243369102478},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.5015065670013428},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.4940939247608185},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41393956542015076},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.14660048484802246},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.08885744214057922}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7839920520782471},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.7816709280014038},{"id":"https://openalex.org/C21036866","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.7738857269287109},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.68443763256073},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6189120411872864},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5600992441177368},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.509243369102478},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.5015065670013428},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.4940939247608185},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41393956542015076},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.14660048484802246},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.08885744214057922},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.0},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc58517.2023.10317138","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/apsipaasc58517.2023.10317138","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5199999809265137,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W78968296","https://openalex.org/W162654330","https://openalex.org/W1494198834","https://openalex.org/W1940872118","https://openalex.org/W2043003570","https://openalex.org/W2168972852","https://openalex.org/W2171121512","https://openalex.org/W2250471514","https://openalex.org/W2259867505","https://openalex.org/W2517194566","https://openalex.org/W2543823510","https://openalex.org/W2550497374","https://openalex.org/W2613126092","https://openalex.org/W2766406951","https://openalex.org/W2888855092","https://openalex.org/W2890116704","https://openalex.org/W2896457183","https://openalex.org/W2904459034","https://openalex.org/W2932022923","https://openalex.org/W2946200149","https://openalex.org/W2952370363","https://openalex.org/W2963351448","https://openalex.org/W2963609956","https://openalex.org/W2964243274","https://openalex.org/W2971753973","https://openalex.org/W2973190645","https://openalex.org/W3033411150","https://openalex.org/W3135644023","https://openalex.org/W3197704090","https://openalex.org/W4205807230","https://openalex.org/W4287761884","https://openalex.org/W4390911531","https://openalex.org/W6640362995","https://openalex.org/W6745232783","https://openalex.org/W6749555683","https://openalex.org/W6750489868","https://openalex.org/W6755207826","https://openalex.org/W6760861152","https://openalex.org/W6763832098","https://openalex.org/W6765540686","https://openalex.org/W6767453231","https://openalex.org/W6778823374","https://openalex.org/W6779337556","https://openalex.org/W6796464841"],"related_works":["https://openalex.org/W1914543332","https://openalex.org/W2946856121","https://openalex.org/W2108985546","https://openalex.org/W2081919107","https://openalex.org/W2433276473","https://openalex.org/W1537411440","https://openalex.org/W1984347656","https://openalex.org/W2535215250","https://openalex.org/W2024201202","https://openalex.org/W2049083033"],"abstract_inverted_index":{"Stress,":[0],"as":[1],"the":[2,19,25,39,45,51,57,89,109,115,134,139],"perceptual":[3],"prominence":[4,27],"within":[5],"sentences,":[6],"plays":[7],"a":[8,64,100],"key":[9],"role":[10],"in":[11,22,28,44,129],"expressive":[12,70],"text-to-speech":[13],"(TTS).":[14],"It":[15],"can":[16],"be":[17],"either":[18],"semantic":[20,42,82,94],"focus":[21],"text":[23],"or":[24],"acoustic":[26,86,97],"speech.":[29,141],"However,":[30],"stress":[31,54,66,83,95,130],"labels":[32],"are":[33],"always":[34],"annotated":[35],"by":[36],"listening":[37],"to":[38,105],"speech,":[40],"lacking":[41],"information":[43],"corresponding":[46],"text,":[47],"which":[48],"may":[49],"degrade":[50],"accuracy":[52,128],"of":[53,59,138],"prediction":[55,67,131],"and":[56,84,96,118,132,136],"expressivity":[58],"TTS.":[60,71],"This":[61],"paper":[62],"proposes":[63],"multi-granularity":[65],"method":[68],"for":[69],"Specifically,":[72],"we":[73],"first":[74],"build":[75],"Chinese":[76],"Mandarin":[77],"datasets":[78],"with":[79,108],"both":[80],"coarse-grained":[81],"fine-grained":[85],"stress.":[87,98,111],"Then,":[88],"proposed":[90,116,124],"model":[91,102,117,125],"progressively":[92],"predicts":[93],"Finally,":[99],"TTS":[101],"is":[103],"adopted":[104],"synthesize":[106],"speech":[107,120],"predicted":[110],"Experimental":[112],"results":[113],"on":[114],"synthesized":[119,140],"show":[121],"that":[122],"our":[123],"achieves":[126],"good":[127],"improves":[133],"expressiveness":[135],"naturalness":[137]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-01-13T01:12:25.745995","created_date":"2025-10-10T00:00:00"}