{"id":"https://openalex.org/W7203756445","doi":"https://doi.org/10.48550/arxiv.2608.17931","title":"SpeechSense: A Paralinguistic-Focused Dataset for Fine-Grained Speech Sentiment Analysis","display_name":"SpeechSense: A Paralinguistic-Focused Dataset for Fine-Grained Speech Sentiment Analysis","publication_year":2026,"publication_date":"2026-08-18","ids":{"openalex":"https://openalex.org/W7203756445","doi":"https://doi.org/10.48550/arxiv.2608.17931"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.17931","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.17931","pdf_url":"https://arxiv.org/pdf/2608.17931","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.17931","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5147580370","display_name":"Shicheng Ma","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Ma, Shicheng","raw_affiliation_strings":["Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong , Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong , Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014251650","display_name":"Wenqian Cui","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Cui, Wenqian","raw_affiliation_strings":["Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong , Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong , Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5123516107","display_name":"Irwin King","orcid":"https://orcid.org/0000-0001-8106-6447","observed_orcids":["https://orcid.org/0000-0001-8106-6447"]},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"King, Irwin","raw_affiliation_strings":["Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong , Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong , Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I177725633"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.6118000149726868,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.6118000149726868,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.2833999991416931,"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":0.08780000358819962,"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/paralinguistic-cues","display_name":"paralinguistic cues","score":0.8880000114440918},{"id":"https://openalex.org/keywords/interpersonal-stance","display_name":"interpersonal stance","score":0.8889999985694885},{"id":"https://openalex.org/keywords/prosody","display_name":"prosody","score":0.7570000290870667},{"id":"https://openalex.org/keywords/fine-grained-sentiment","display_name":"fine-grained sentiment","score":0.6430000066757202},{"id":"https://openalex.org/keywords/speech-emotion-recognition","display_name":"speech emotion recognition","score":0.3630000054836273},{"id":"https://openalex.org/keywords/acoustic-characteristics","display_name":"acoustic features","score":0.5659999847412109},{"id":"https://openalex.org/keywords/speaker-attitude","display_name":"speaker attitude","score":0.48899999260902405},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"speech synthesis","score":0.5130000114440918},{"id":"https://openalex.org/keywords/dataset-construction","display_name":"dataset construction","score":0.4259999990463257}],"concepts":[{"id":"https://openalex.org/C133378560","wikidata":"https://www.wikidata.org/wiki/Q1753225","display_name":"Paralanguage","level":2,"score":0.8220999836921692},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.7063999772071838},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6869000196456909},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4875999987125397},{"id":"https://openalex.org/C66402592","wikidata":"https://www.wikidata.org/wiki/Q2271421","display_name":"Sentiment analysis","level":2,"score":0.438400000333786},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4293000102043152},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4090999960899353},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.3952000141143799},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.33480000495910645},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33160001039505005},{"id":"https://openalex.org/C164850336","wikidata":"https://www.wikidata.org/wiki/Q3685487","display_name":"Interpersonal communication","level":2,"score":0.29809999465942383},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.2854999899864197},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.2727999985218048},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.2669999897480011},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.2549999952316284},{"id":"https://openalex.org/C30539005","wikidata":"https://www.wikidata.org/wiki/Q1066689","display_name":"Human communication","level":2,"score":0.25360000133514404}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.17931","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.17931","pdf_url":"https://arxiv.org/pdf/2608.17931","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.17931","doi":"https://doi.org/10.48550/arxiv.2608.17931","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.17931","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.17931","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.17931","pdf_url":"https://arxiv.org/pdf/2608.17931","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.4000000059604645}],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322942","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7203756445.pdf","grobid_xml":"https://content.openalex.org/works/W7203756445.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7161000911","https://openalex.org/W7214031333","https://openalex.org/W7151400534","https://openalex.org/W3015489952","https://openalex.org/W7139095727","https://openalex.org/W4408353462","https://openalex.org/W4415251890","https://openalex.org/W7206161146","https://openalex.org/W7138314334","https://openalex.org/W2149097201"],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,31,87,98,201],"AI":[3],"have":[4],"revolutionized":[5],"speech":[6,10,131,166,180],"processing,":[7],"yet":[8],"effective":[9],"understanding":[11],"requires":[12],"discerning":[13],"not":[14],"just":[15],"what":[16],"is":[17,22],"said,":[18],"but":[19],"how":[20],"it":[21],"said.":[23],"Speech":[24,48,66],"Sentiment":[25,49],"Analysis":[26,50],"plays":[27],"a":[28,96,125,137,156],"critical":[29],"role":[30],"decoding":[32],"these":[33,121],"paralinguistic":[34],"cues":[35,148,200],"for":[36,116,129],"diverse":[37],"real-world":[38],"applications":[39],"such":[40],"as":[41],"recruitment":[42],"and":[43,80,168,179,212],"customer":[44],"service.":[45],"However,":[46],"existing":[47],"research":[51],"faces":[52],"two":[53],"primary":[54],"limitations.":[55],"First,":[56],"dominant":[57],"approaches":[58],"rely":[59],"on":[60,160],"text-centric":[61],"pipelines":[62],"that":[63,183],"cascade":[64],"Automatic":[65],"Recognition":[67],"with":[68,185],"text":[69],"analysis.":[70,133],"This":[71],"process":[72],"inevitably":[73],"discards":[74],"essential":[75],"acoustic":[76,186,199],"features":[77],"like":[78],"prosody":[79],"tone,":[81],"failing":[82],"to":[83],"capture":[84],"attitudinal":[85],"meanings":[86],"acoustically":[88],"ambiguous":[89],"utterances.":[90],"Second,":[91],"current":[92],"benchmarks":[93],"suffer":[94],"from":[95,164],"mismatch":[97],"label":[99],"granularity,":[100],"prioritizing":[101],"basic":[102],"emotions":[103],"(e.g.,":[104,112],"happy,":[105],"sad)":[106],"over":[107],"the":[108,196,207],"nuanced":[109],"interpersonal":[110,142],"stances":[111,143],"confident,":[113],"impatient)":[114],"necessary":[115],"social":[117],"sensitivity.":[118],"To":[119],"address":[120],"limitations,":[122],"we":[123,135],"propose":[124],"novel":[126],"dataset,":[127],"SpeechSense,":[128],"fine-grained":[130],"sentiment":[132],"Specifically,":[134],"define":[136],"specialized":[138],"8-class":[139],"taxonomy":[140],"of":[141,198,209],"detectable":[144],"primarily":[145],"through":[146],"prosodic":[147],"beyond":[149],"lexical":[150],"content":[151],"alone.":[152],"We":[153],"then":[154],"construct":[155],"curated":[157],"dataset":[158],"based":[159],"this":[161],"taxonomy,":[162],"built":[163],"high-fidelity":[165],"synthesis":[167],"rigorous":[169],"human":[170],"validation.":[171],"Comprehensive":[172],"experiments":[173],"across":[174],"multi-modal":[175],"LLMs,":[176,178],"text-only":[177,190],"encoders":[181],"demonstrate":[182],"models":[184],"access":[187],"consistently":[188],"outperform":[189],"baselines.":[191],"These":[192],"results":[193],"empirically":[194],"validate":[195],"primacy":[197],"detecting":[202],"subtle":[203],"speaker":[204],"attitudes,":[205],"highlighting":[206],"necessity":[208],"SpeechSense.":[210],"Dataset":[211],"supplementary":[213],"materials":[214],"are":[215],"available":[216],"at":[217],"https://github.com/Sher13cked/SpeechSense.":[218]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-08-20T00:00:00"}