{"id":"https://openalex.org/W7148299292","doi":"https://doi.org/10.1109/asru65441.2025.11434634","title":"CASPER: A Large Scale Spontaneous Speech Dataset","display_name":"CASPER: A Large Scale Spontaneous Speech Dataset","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148299292","doi":"https://doi.org/10.1109/asru65441.2025.11434634"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434634","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434634","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5101215727","display_name":"Cihan Xiao","orcid":"https://orcid.org/0009-0006-6262-3213"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Cihan Xiao","raw_affiliation_strings":["Johns Hopkins University,Baltimore,USA"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Baltimore,USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004455436","display_name":"Ruixing Liang","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ruixing Liang","raw_affiliation_strings":["Johns Hopkins University,Baltimore,USA"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Baltimore,USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100362470","display_name":"Xiangyu Zhang","orcid":"https://orcid.org/0000-0003-3186-8067"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiangyu Zhang","raw_affiliation_strings":["Johns Hopkins University,Baltimore,USA"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Baltimore,USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120796776","display_name":"Mehmet Emre Tiryaki","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mehmet Emre Tiryaki","raw_affiliation_strings":["Johns Hopkins University,Baltimore,USA"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Baltimore,USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120796777","display_name":"Veronica Bae","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Veronica Bae","raw_affiliation_strings":["Johns Hopkins University,Baltimore,USA"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Baltimore,USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5117862455","display_name":"Lavanya Shankar","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lavanya Shankar","raw_affiliation_strings":["Johns Hopkins University,Baltimore,USA"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Baltimore,USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132814208","display_name":"Rong Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rong Yang","raw_affiliation_strings":["Johns Hopkins University,Baltimore,USA"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Baltimore,USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024703011","display_name":"E Poon","orcid":"https://orcid.org/0000-0001-9204-6126"},"institutions":[{"id":"https://openalex.org/I4210157460","display_name":"Manufacturing Advocacy & Growth Network (United States)","ror":"https://ror.org/05p9yxg92","country_code":"US","type":"company","lineage":["https://openalex.org/I4210157460"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ethan Poon","raw_affiliation_strings":["Edison Academy Magnet School,USA"],"affiliations":[{"raw_affiliation_string":"Edison Academy Magnet School,USA","institution_ids":["https://openalex.org/I4210157460"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132807434","display_name":"Emmanuel Dupoux","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Emmanuel Dupoux","raw_affiliation_strings":["Meta,USA"],"affiliations":[{"raw_affiliation_string":"Meta,USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014580424","display_name":"Sanjeev Khudanpur","orcid":"https://orcid.org/0000-0001-5976-0897"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sanjeev Khudanpur","raw_affiliation_strings":["Johns Hopkins University,Baltimore,USA"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Baltimore,USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129752498","display_name":"Leibny Paola Garcia Perera","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Leibny Paola Garcia Perera","raw_affiliation_strings":["Johns Hopkins University,Baltimore,USA"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Baltimore,USA","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":11,"corresponding_author_ids":["https://openalex.org/A5101215727"],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.87550625,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.36320000886917114,"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/T12031","display_name":"Speech and dialogue systems","score":0.36320000886917114,"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/T12128","display_name":"AI in Service Interactions","score":0.08389999717473984,"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":0.07660000026226044,"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/pipeline","display_name":"Pipeline (software)","score":0.7702999711036682},{"id":"https://openalex.org/keywords/economic-shortage","display_name":"Economic shortage","score":0.5543000102043152},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5415999889373779},{"id":"https://openalex.org/keywords/scarcity","display_name":"Scarcity","score":0.5271999835968018},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.522599995136261},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5166000127792358},{"id":"https://openalex.org/keywords/plan","display_name":"Plan (archaeology)","score":0.4749000072479248},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.46880000829696655}],"concepts":[{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7702999711036682},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.743399977684021},{"id":"https://openalex.org/C194051981","wikidata":"https://www.wikidata.org/wiki/Q1337691","display_name":"Economic shortage","level":3,"score":0.5543000102043152},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5415999889373779},{"id":"https://openalex.org/C109747225","wikidata":"https://www.wikidata.org/wiki/Q815758","display_name":"Scarcity","level":2,"score":0.5271999835968018},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.522599995136261},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5166000127792358},{"id":"https://openalex.org/C2776505523","wikidata":"https://www.wikidata.org/wiki/Q4785468","display_name":"Plan (archaeology)","level":2,"score":0.4749000072479248},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.46880000829696655},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44609999656677246},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.4277999997138977},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.4250999987125397},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.42179998755455017},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4169999957084656},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.3720000088214874},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.34380000829696655},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3158000111579895},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.29840001463890076},{"id":"https://openalex.org/C22467394","wikidata":"https://www.wikidata.org/wiki/Q849359","display_name":"Multidisciplinary approach","level":2,"score":0.29409998655319214},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2809999883174896},{"id":"https://openalex.org/C54953205","wikidata":"https://www.wikidata.org/wiki/Q4142201","display_name":"Speech analytics","level":4,"score":0.26930001378059387},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.26330000162124634},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.251800000667572}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434634","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434634","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2118142207","https://openalex.org/W2166637769","https://openalex.org/W2972949456","https://openalex.org/W3160747466","https://openalex.org/W3198694222","https://openalex.org/W3205878676","https://openalex.org/W3210177631","https://openalex.org/W4307680525","https://openalex.org/W4381786045","https://openalex.org/W4385800699","https://openalex.org/W4385822293","https://openalex.org/W4385822353","https://openalex.org/W4385822356","https://openalex.org/W4389519275","https://openalex.org/W4389524500","https://openalex.org/W4406688858","https://openalex.org/W4415432991"],"related_works":[],"abstract_inverted_index":{"The":[0],"success":[1],"of":[2,22,55,69,103],"large":[3],"language":[4],"models":[5],"has":[6],"driven":[7],"interest":[8],"in":[9,113],"developing":[10],"similar":[11],"speech":[12,25,105],"processing":[13],"capabilities.":[14],"However,":[15],"a":[16,39,66,82,117],"key":[17],"challenge":[18],"is":[19],"the":[20,97,101,121],"scarcity":[21],"high-quality":[23],"spontaneous":[24,56,104],"data,":[26],"as":[27],"most":[28],"existing":[29],"datasets":[30],"contain":[31],"scripted":[32],"dialogues.":[33],"To":[34],"address":[35],"this,":[36],"we":[37],"present":[38],"novel":[40],"pipeline":[41],"for":[42,85,99,120],"eliciting":[43],"and":[44,48,71,94],"recording":[45],"natural":[46,62],"dialogues":[47],"release":[49],"our":[50,92],"dataset":[51,93,112],"with":[52],"100+":[53],"hours":[54],"speech.":[57],"Our":[58],"approach":[59],"fosters":[60],"fluid,":[61],"conversations":[63],"while":[64],"encouraging":[65],"diverse":[67],"range":[68],"topics":[70],"interactive":[72],"exchanges.":[73],"Unlike":[74],"traditional":[75],"methods,":[76],"it":[77],"facilitates":[78],"genuine":[79],"interactions,":[80],"providing":[81],"reproducible":[83],"framework":[84],"future":[86,114],"data":[87],"collection.":[88],"This":[89],"paper":[90],"introduces":[91],"methodology,":[95],"laying":[96],"groundwork":[98],"addressing":[100],"shortage":[102],"data.":[106],"We":[107],"plan":[108],"to":[109],"expand":[110],"this":[111],"stages,":[115],"offering":[116],"growing":[118],"resource":[119],"research":[122],"community.":[123]},"counts_by_year":[],"updated_date":"2026-04-03T16:44:17.987007","created_date":"2026-04-03T00:00:00"}
