{"id":"https://openalex.org/W6884627473","doi":"https://doi.org/10.1109/tencon61640.2024.10902687","title":"DisfluencySpeech \u2013 Single-Speaker Conversational Speech Dataset with Paralanguage","display_name":"DisfluencySpeech \u2013 Single-Speaker Conversational Speech Dataset with Paralanguage","publication_year":2024,"publication_date":"2024-12-01","ids":{"openalex":"https://openalex.org/W6884627473","doi":"https://doi.org/10.1109/tencon61640.2024.10902687"},"language":"en","primary_location":{"id":"doi:10.1109/tencon61640.2024.10902687","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tencon61640.2024.10902687","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"TENCON 2024 - 2024 IEEE Region 10 Conference (TENCON)","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":null,"display_name":"Kyra Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I152815399","display_name":"Singapore University of Technology and Design","ror":"https://ror.org/05j6fvn87","country_code":"SG","type":"education","lineage":["https://openalex.org/I152815399"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Kyra Wang","raw_affiliation_strings":["Information Systems Technology and Design, Singapore University of Technology and Design,Singapore,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Systems Technology and Design, Singapore University of Technology and Design,Singapore,Singapore","institution_ids":["https://openalex.org/I152815399"]}]},{"author_position":"last","author":{"id":null,"display_name":"Dorien Herremans","orcid":null},"institutions":[{"id":"https://openalex.org/I152815399","display_name":"Singapore University of Technology and Design","ror":"https://ror.org/05j6fvn87","country_code":"SG","type":"education","lineage":["https://openalex.org/I152815399"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Dorien Herremans","raw_affiliation_strings":["Information Systems Technology and Design, Singapore University of Technology and Design,Singapore,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Systems Technology and Design, Singapore University of Technology and Design,Singapore,Singapore","institution_ids":["https://openalex.org/I152815399"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I152815399"],"apc_list":null,"apc_paid":null,"fwci":0.5459,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.74440898,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"469","last_page":"472"},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T12684","display_name":"Stuttering Research and Treatment","score":0.1143999993801117,"subfield":{"id":"https://openalex.org/subfields/3203","display_name":"Clinical 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/T12684","display_name":"Stuttering Research and Treatment","score":0.1143999993801117,"subfield":{"id":"https://openalex.org/subfields/3203","display_name":"Clinical 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/T10465","display_name":"Neurobiology of Language and Bilingualism","score":0.11169999837875366,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.09629999846220016,"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/paralanguage","display_name":"Paralanguage","score":0.9843000173568726},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5163999795913696},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4478999972343445},{"id":"https://openalex.org/keywords/meaning","display_name":"Meaning (existential)","score":0.39969998598098755},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.3393999934196472},{"id":"https://openalex.org/keywords/speech-communication","display_name":"Speech communication","score":0.31130000948905945}],"concepts":[{"id":"https://openalex.org/C133378560","wikidata":"https://www.wikidata.org/wiki/Q1753225","display_name":"Paralanguage","level":2,"score":0.9843000173568726},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7106000185012817},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5861999988555908},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5295000076293945},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5163999795913696},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4478999972343445},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4318999946117401},{"id":"https://openalex.org/C2780876879","wikidata":"https://www.wikidata.org/wiki/Q3054749","display_name":"Meaning (existential)","level":2,"score":0.39969998598098755},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.3393999934196472},{"id":"https://openalex.org/C2989496772","wikidata":"https://www.wikidata.org/wiki/Q52946","display_name":"Speech communication","level":2,"score":0.31130000948905945},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.29269999265670776},{"id":"https://openalex.org/C53893814","wikidata":"https://www.wikidata.org/wiki/Q7378909","display_name":"Rule-based machine translation","level":2,"score":0.28790000081062317},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.28760001063346863},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.2874000072479248},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.27709999680519104},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.2703000009059906},{"id":"https://openalex.org/C43617652","wikidata":"https://www.wikidata.org/wiki/Q7575399","display_name":"Speech production","level":2,"score":0.2535000145435333}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tencon61640.2024.10902687","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tencon61640.2024.10902687","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"TENCON 2024 - 2024 IEEE Region 10 Conference (TENCON)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.44996559619903564}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W2071473964","https://openalex.org/W2120847449","https://openalex.org/W2131709139","https://openalex.org/W2137091751","https://openalex.org/W2336364342","https://openalex.org/W2747874407","https://openalex.org/W2903739847","https://openalex.org/W3094912909","https://openalex.org/W3196001064","https://openalex.org/W4206711328","https://openalex.org/W4254718357","https://openalex.org/W4372260474","https://openalex.org/W6745297980","https://openalex.org/W6777694618","https://openalex.org/W6783867762"],"related_works":[],"abstract_inverted_index":{"Laughing,":[0],"sighing,":[1],"stuttering,":[2],"and":[3,26,43,62,167],"other":[4],"forms":[5],"of":[6,114,132,156,160,164,169,181],"paralanguage":[7,142],"do":[8,55,67],"not":[9,56],"contribute":[10],"any":[11],"direct":[12],"lexical":[13],"meaning":[14],"to":[15,40,46,83,139],"speech,":[16],"but":[17],"they":[18],"provide":[19,149],"crucial":[20],"propositional":[21],"context":[22],"that":[23,66,90,136],"aids":[24],"semantic":[25],"pragmatic":[27],"processes":[28],"such":[29,92,146],"as":[30,172,174],"irony.":[31],"It":[32],"is":[33,137],"thus":[34,96],"important":[35],"for":[36],"artificial":[37],"social":[38],"agents":[39],"both":[41],"understand":[42],"be":[44],"able":[45,138],"generate":[47],"speech":[48,53,60,103],"with":[49,105],"semantically-important":[50],"paralanguage.":[51,106],"Most":[52],"datasets":[54,71],"include":[57,91],"transcribed":[58],"non-lexical":[59],"sounds":[61],"disfluencies,":[63],"while":[64],"those":[65],"are":[68],"typically":[69],"multispeaker":[70],"where":[72],"each":[73,180],"speaker":[74,109],"provides":[75],"relatively":[76],"little":[77],"audio.":[78],"This":[79],"makes":[80],"it":[81],"challenging":[82],"train":[84],"conversational":[85],"Text-to-Speech":[86],"(TTS)":[87],"synthesis":[88],"models":[89,177],"paralinguistic":[93],"components.":[94],"We":[95],"present":[97],"DisfluencySpeech,":[98],"a":[99,133],"studio-quality":[100],"labeled":[101],"English":[102],"dataset":[104],"A":[107],"single":[108],"recreates":[110],"nearly":[111],"10":[112],"hours":[113],"expressive":[115],"utterances":[116],"from":[117,143],"the":[118,130],"Switchboard-1":[119],"Telephone":[120],"Speech":[121],"Corpus":[122],"(Switchboard),":[123],"simulating":[124],"realistic":[125],"informal":[126],"conversations.":[127],"To":[128],"aid":[129],"development":[131],"TTS":[134,176],"model":[135],"predictively":[140],"synthesise":[141],"text":[144],"without":[145],"components,":[147],"we":[148],"three":[150],"different":[151,154],"transcripts":[152],"at":[153],"levels":[155],"information":[157],"removal":[158,163,168],"(removal":[159],"non-speech":[161],"events,":[162],"non-sentence":[165],"elements,":[166],"false":[170],"starts),":[171],"well":[173],"benchmark":[175],"trained":[178],"on":[179],"these":[182],"levels.":[183]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}