{"id":"https://openalex.org/W4415540591","doi":"https://doi.org/10.1145/3746027.3758312","title":"SMIIP-NV: A Multi-Annotation Non-Verbal Expressive Speech Corpus in Mandarin for LLM-Based Speech Synthesis","display_name":"SMIIP-NV: A Multi-Annotation Non-Verbal Expressive Speech Corpus in Mandarin for LLM-Based Speech Synthesis","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415540591","doi":"https://doi.org/10.1145/3746027.3758312"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3758312","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3758312","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","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/A5042586877","display_name":"Zhuojun Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210159968","display_name":"Duke Kunshan University","ror":"https://ror.org/04sr5ys16","country_code":"CN","type":"education","lineage":["https://openalex.org/I170897317","https://openalex.org/I37461747","https://openalex.org/I4210159968"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhuojun Wu","raw_affiliation_strings":["School of Computer Science, Wuhan University, Wuhan, China and Duke Kunshan University, Kunshan, China"],"raw_orcid":"https://orcid.org/0009-0008-1238-4829","affiliations":[{"raw_affiliation_string":"School of Computer Science, Wuhan University, Wuhan, China and Duke Kunshan University, Kunshan, China","institution_ids":["https://openalex.org/I4210159968"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Dong Liu","orcid":"https://orcid.org/0009-0003-9419-1580"},"institutions":[{"id":"https://openalex.org/I4210159968","display_name":"Duke Kunshan University","ror":"https://ror.org/04sr5ys16","country_code":"CN","type":"education","lineage":["https://openalex.org/I170897317","https://openalex.org/I37461747","https://openalex.org/I4210159968"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dong Liu","raw_affiliation_strings":["School of Computer Science, Wuhan University, Wuhan, China and Duke Kunshan University, Kunshan, China"],"raw_orcid":"https://orcid.org/0009-0003-9419-1580","affiliations":[{"raw_affiliation_string":"School of Computer Science, Wuhan University, Wuhan, China and Duke Kunshan University, Kunshan, China","institution_ids":["https://openalex.org/I4210159968"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100446290","display_name":"Juan Liu","orcid":"https://orcid.org/0000-0001-9344-7415"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Juan Liu","raw_affiliation_strings":["School of Artificial Intelligence, Wuhan University, Wuhan, China and School of Computer Science, Wuhan University, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0001-9344-7415","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Wuhan University, Wuhan, China and School of Computer Science, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111348795","display_name":"Yechen Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210156159","display_name":"JSpectrum (China)","ror":"https://ror.org/04sdv1b42","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210156159"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yechen Wang","raw_affiliation_strings":["OfSpectrum, Inc., Wuhan, China"],"raw_orcid":"https://orcid.org/0009-0004-7957-9058","affiliations":[{"raw_affiliation_string":"OfSpectrum, Inc., Wuhan, China","institution_ids":["https://openalex.org/I4210156159"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120132420","display_name":"Linxi Li","orcid":null},"institutions":[{"id":"https://openalex.org/I4210156159","display_name":"JSpectrum (China)","ror":"https://ror.org/04sdv1b42","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210156159"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linxi Li","raw_affiliation_strings":["OfSpectrum, Inc., Wuhan, China"],"raw_orcid":"https://orcid.org/0009-0003-9315-0576","affiliations":[{"raw_affiliation_string":"OfSpectrum, Inc., Wuhan, China","institution_ids":["https://openalex.org/I4210156159"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026623761","display_name":"Liwei Jin","orcid":null},"institutions":[{"id":"https://openalex.org/I4210156159","display_name":"JSpectrum (China)","ror":"https://ror.org/04sdv1b42","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210156159"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liwei Jin","raw_affiliation_strings":["OfSpectrum, Inc., Wuhan, China"],"raw_orcid":"https://orcid.org/0009-0004-7825-1229","affiliations":[{"raw_affiliation_string":"OfSpectrum, Inc., Wuhan, China","institution_ids":["https://openalex.org/I4210156159"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hui Bu","orcid":"https://orcid.org/0000-0002-5883-1195"},"institutions":[{"id":"https://openalex.org/I4210155967","display_name":"OriginWater (China)","ror":"https://ror.org/04h7gmn81","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210155967"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Bu","raw_affiliation_strings":["Beijing AIShell Technology Co. Ltd, China, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-5883-1195","affiliations":[{"raw_affiliation_string":"Beijing AIShell Technology Co. Ltd, China, Beijing, China","institution_ids":["https://openalex.org/I4210155967"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036446253","display_name":"Pengyuan Zhang","orcid":"https://orcid.org/0000-0001-6838-5160"},"institutions":[{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengyuan Zhang","raw_affiliation_strings":["Speech and Intelligent Information Processing Laboratory, Institute of Acoustics, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-6838-5160","affiliations":[{"raw_affiliation_string":"Speech and Intelligent Information Processing Laboratory, Institute of Acoustics, Beijing, China","institution_ids":["https://openalex.org/I4210099069"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100351449","display_name":"Ming Li","orcid":"https://orcid.org/0000-0002-6406-1983"},"institutions":[{"id":"https://openalex.org/I4210159968","display_name":"Duke Kunshan University","ror":"https://ror.org/04sr5ys16","country_code":"CN","type":"education","lineage":["https://openalex.org/I170897317","https://openalex.org/I37461747","https://openalex.org/I4210159968"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming Li","raw_affiliation_strings":["School of Computer Science, Wuhan University, Wuhan, China and Duke Kunshan University, Kunshan, China"],"raw_orcid":"https://orcid.org/0000-0002-6406-1983","affiliations":[{"raw_affiliation_string":"School of Computer Science, Wuhan University, Wuhan, China and Duke Kunshan University, Kunshan, China","institution_ids":["https://openalex.org/I4210159968"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"12564","last_page":"12570"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998000264167786,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9998000264167786,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9955999851226807,"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":0.9944000244140625,"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/speech-corpus","display_name":"Speech corpus","score":0.5748999714851379},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.5489000082015991},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5266000032424927},{"id":"https://openalex.org/keywords/bigram","display_name":"Bigram","score":0.397599995136261},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.38760000467300415},{"id":"https://openalex.org/keywords/speech-production","display_name":"Speech production","score":0.3544999957084656},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3301999866962433},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.3224000036716461}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8039000034332275},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5800999999046326},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.5748999714851379},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5730000138282776},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.5489000082015991},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5266000032424927},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4415999948978424},{"id":"https://openalex.org/C108757681","wikidata":"https://www.wikidata.org/wiki/Q2773912","display_name":"Bigram","level":3,"score":0.397599995136261},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.38760000467300415},{"id":"https://openalex.org/C43617652","wikidata":"https://www.wikidata.org/wiki/Q7575399","display_name":"Speech production","level":2,"score":0.3544999957084656},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3301999866962433},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.3224000036716461},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.29420000314712524},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.29420000314712524},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.2854999899864197},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.2831000089645386},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.28029999136924744},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.2793999910354614},{"id":"https://openalex.org/C113954288","wikidata":"https://www.wikidata.org/wiki/Q186885","display_name":"Timestamp","level":2,"score":0.27559998631477356},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.27250000834465027},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.2687999904155731},{"id":"https://openalex.org/C541956065","wikidata":"https://www.wikidata.org/wiki/Q2250680","display_name":"Speech error","level":3,"score":0.26739999651908875},{"id":"https://openalex.org/C51764019","wikidata":"https://www.wikidata.org/wiki/Q283987","display_name":"Direct speech","level":2,"score":0.2515999972820282}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3758312","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3758312","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","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":4,"referenced_works":["https://openalex.org/W2790322224","https://openalex.org/W2959143276","https://openalex.org/W4390075359","https://openalex.org/W4391454536"],"related_works":[],"abstract_inverted_index":{"In":[0],"natural":[1],"language":[2,151],"communication,":[3],"emotions":[4,57,99],"are":[5,161],"often":[6],"conveyed":[7],"through":[8],"non-verbal":[9,30,50,59,84,104,116,143],"sounds":[10],"(NVs),":[11],"such":[12],"as":[13],"laughter,":[14,62],"crying,":[15,63],"cough":[16],"and":[17,58,64,86,100,109,157],"so":[18],"on.":[19],"However,":[20],"most":[21],"existing":[22],"text-to-speech":[23],"(TTS)":[24],"corpora":[25],"lack":[26],"annotations":[27,122],"for":[28,112,123,142],"these":[29],"sounds,":[31,60,105],"leading":[32],"to":[33],"a":[34,49,140,148],"scarcity":[35],"of":[36,39,69,93,103,115,135],"systems":[37],"capable":[38],"generating":[40],"them.":[41],"To":[42,66,131],"address":[43],"this":[44,136],"gap,":[45],"we":[46,138],"introduce":[47],"SMIIP-NV,":[48],"speech":[51,80,85,94,124,144],"synthesis":[52,145],"corpus":[53,81,120],"annotated":[54],"with":[55,106],"both":[56],"including":[61],"cough.":[65],"the":[67,74,119,133],"best":[68],"our":[70],"knowledge,":[71],"SMIIP-NV":[72,155],"is":[73],"largest":[75],"publicly":[76,162],"available":[77,163],"open-source":[78],"expressive":[79],"that":[82,126],"includes":[83],"rich":[87],"annotations.":[88],"It":[89],"comprises":[90],"33":[91],"hours":[92],"data,":[95],"covering":[96],"five":[97],"distinct":[98],"three":[101],"types":[102],"detailed":[107],"transcriptions":[108],"precise":[110],"timestamps":[111],"each":[113],"occurrence":[114],"sounds.":[117],"Additionally,":[118],"provides":[121],"segments":[125],"contain":[127],"laughter":[128],"or":[129],"crying.":[130],"demonstrate":[132],"utility":[134],"dataset,":[137],"establish":[139],"baseline":[141],"by":[146],"employing":[147],"lightweight":[149],"large":[150],"model":[152],"(LLM).":[153],"The":[154,166],"dataset":[156],"static":[158],"audio":[159],"demonstrations":[160,170],"at":[164,174],"https://axunyii.github.io/SMIIP-NV.":[165],"interactive":[167],"real-time":[168],"\u00ad":[169],"can":[171],"be":[172],"accessed":[173],"https://huggingface.co/spaces/xunyi/SMIIP-NV_Finetuned_CosyVoice2.":[175]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-25T00:00:00"}
