{"id":"https://openalex.org/W4405709453","doi":"https://doi.org/10.1109/iscslp63861.2024.10800745","title":"EmoSpeech: A Corpus of Emotionally Rich and Contextually Detailed Speech Annotations","display_name":"EmoSpeech: A Corpus of Emotionally Rich and Contextually Detailed Speech Annotations","publication_year":2024,"publication_date":"2024-11-07","ids":{"openalex":"https://openalex.org/W4405709453","doi":"https://doi.org/10.1109/iscslp63861.2024.10800745"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp63861.2024.10800745","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp63861.2024.10800745","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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/A5113307475","display_name":"Weizhen Bian","orcid":null},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Weizhen Bian","raw_affiliation_strings":["Independent Researcher","The Hong Kong University of Science and Technology"],"affiliations":[{"raw_affiliation_string":"Independent Researcher","institution_ids":[]},{"raw_affiliation_string":"The Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024891369","display_name":"Yubo Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I141568987","display_name":"Hong Kong Baptist University","ror":"https://ror.org/0145fw131","country_code":"HK","type":"education","lineage":["https://openalex.org/I141568987"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yubo Zhou","raw_affiliation_strings":["Hong Kong Baptist University"],"affiliations":[{"raw_affiliation_string":"Hong Kong Baptist University","institution_ids":["https://openalex.org/I141568987"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089872687","display_name":"Kaitai Zhang","orcid":"https://orcid.org/0000-0001-9560-9641"},"institutions":[{"id":"https://openalex.org/I141568987","display_name":"Hong Kong Baptist University","ror":"https://ror.org/0145fw131","country_code":"HK","type":"education","lineage":["https://openalex.org/I141568987"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Kaitai Zhang","raw_affiliation_strings":["Hong Kong Baptist University"],"affiliations":[{"raw_affiliation_string":"Hong Kong Baptist University","institution_ids":["https://openalex.org/I141568987"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111134593","display_name":"Xiaohan Gu","orcid":null},"institutions":[{"id":"https://openalex.org/I141568987","display_name":"Hong Kong Baptist University","ror":"https://ror.org/0145fw131","country_code":"HK","type":"education","lineage":["https://openalex.org/I141568987"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xiaohan Gu","raw_affiliation_strings":["Hong Kong Baptist University"],"affiliations":[{"raw_affiliation_string":"Hong Kong Baptist University","institution_ids":["https://openalex.org/I141568987"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5113307475"],"corresponding_institution_ids":["https://openalex.org/I200769079"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.21928968,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"417","last_page":"420"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.770799994468689,"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":0.770799994468689,"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":0.7534000277519226,"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/T12031","display_name":"Speech and dialogue systems","score":0.6887000203132629,"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":0.6374890804290771},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5727141499519348},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.46729591488838196},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4097346067428589},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.38799601793289185},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3571860194206238}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6374890804290771},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5727141499519348},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.46729591488838196},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4097346067428589},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.38799601793289185},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3571860194206238},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp63861.2024.10800745","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp63861.2024.10800745","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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":21,"referenced_works":["https://openalex.org/W127455173","https://openalex.org/W2146334809","https://openalex.org/W3015841875","https://openalex.org/W3163573274","https://openalex.org/W3205015613","https://openalex.org/W3209059054","https://openalex.org/W4283771593","https://openalex.org/W4375869257","https://openalex.org/W4375869364","https://openalex.org/W4376456926","https://openalex.org/W4385570752","https://openalex.org/W4385822407","https://openalex.org/W4387968164","https://openalex.org/W4391745456","https://openalex.org/W4393147046","https://openalex.org/W4398152753","https://openalex.org/W4401039720","https://openalex.org/W4402111974","https://openalex.org/W4403791830","https://openalex.org/W6847363464","https://openalex.org/W6853191338"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2931662336","https://openalex.org/W2077865380","https://openalex.org/W3006817050","https://openalex.org/W4401768695","https://openalex.org/W2765597752","https://openalex.org/W2134894512","https://openalex.org/W2083375246","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Advances":[0],"in":[1,76],"text-to-speech":[2],"(TTS)":[3],"technology":[4],"have":[5,84],"significantly":[6,152],"improved":[7],"the":[8,15,20,26,33,71,145,149,154,163],"quality":[9],"of":[10,19,29,35,39,66,73,148],"generated":[11],"speech,":[12],"closely":[13],"matching":[14],"timbre":[16],"and":[17,103,130,151,176,185],"intonation":[18],"target":[21],"speaker.":[22],"However,":[23,98],"due":[24],"to":[25,61,94,108],"inherent":[27],"complexity":[28],"human":[30],"emotional":[31,42,49,67,106,146],"expression,":[32],"development":[34],"TTS":[36,77,192],"systems":[37],"capable":[38],"controlling":[40],"subtle":[41],"differences":[43],"remains":[44],"a":[45,63,117,139,174,182],"formidable":[46],"challenge.":[47],"Existing":[48],"speech":[50,96,128],"databases":[51,88,123],"often":[52],"suffer":[53],"from":[54],"overly":[55],"simplistic":[56],"labelling":[57],"schemes":[58],"that":[59,89],"fail":[60],"capture":[62],"wide":[64],"range":[65],"states,":[68],"thus":[69],"limiting":[70],"effectiveness":[72],"emotion":[74],"synthesis":[75],"applications.":[78],"To":[79],"this":[80,113],"end,":[81],"recent":[82],"efforts":[83],"focussed":[85],"on":[86,156],"building":[87,122],"use":[90],"natural":[91,135],"language":[92,136,167],"annotations":[93,159],"describe":[95],"emotions.":[97],"these":[99],"approaches":[100],"are":[101],"costly":[102,157],"require":[104],"more":[105,183],"depth":[107],"train":[109],"robust":[110],"systems.":[111,193],"In":[112],"paper,":[114],"we":[115],"propose":[116],"novel":[118],"process":[119],"aimed":[120],"at":[121],"by":[124,160],"systematically":[125],"extracting":[126],"emotion-rich":[127],"segments":[129],"annotating":[131],"them":[132],"with":[133,165],"detailed":[134],"descriptions":[137],"through":[138],"generative":[140],"model.":[141],"This":[142],"approach":[143],"enhances":[144],"granularity":[147],"database":[150,172],"reduces":[153],"reliance":[155],"manual":[158],"automatically":[161],"augmenting":[162],"data":[164],"high-level":[166],"models.":[168],"The":[169],"resulting":[170],"rich":[171],"provides":[173],"scalable":[175],"economically":[177],"viable":[178],"solution":[179],"for":[180,188],"developing":[181,189],"nuanced":[184],"dynamic":[186],"basis":[187],"emotionally":[190],"controlled":[191]},"counts_by_year":[],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}