{"id":"https://openalex.org/W7133306233","doi":"https://doi.org/10.48550/arxiv.2603.01894","title":"VietSuperSpeech: A Large-Scale Vietnamese Conversational Speech Dataset for ASR Fine-Tuning in Chatbot, Customer Support, and Call Center Applications","display_name":"VietSuperSpeech: A Large-Scale Vietnamese Conversational Speech Dataset for ASR Fine-Tuning in Chatbot, Customer Support, and Call Center Applications","publication_year":2026,"publication_date":"2026-03-02","ids":{"openalex":"https://openalex.org/W7133306233","doi":"https://doi.org/10.48550/arxiv.2603.01894"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2603.01894","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2603.01894","pdf_url":"https://arxiv.org/pdf/2603.01894","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2603.01894","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5128019502","display_name":"Loan Do","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I109689652","display_name":"FPT University","ror":"https://ror.org/03esj4g97","country_code":"VN","type":"education","lineage":["https://openalex.org/I109689652"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Do, Loan","raw_affiliation_strings":["FPT University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"FPT University","institution_ids":["https://openalex.org/I109689652"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127936868","display_name":"Thanh Ngoc Nguyen","orcid":"https://orcid.org/0009-0005-7406-0297","observed_orcids":["https://orcid.org/0009-0005-7406-0297"]},"institutions":[{"id":"https://openalex.org/I4210094839","display_name":"Instituto de Ciencia de Materiales de Sevilla","ror":"https://ror.org/00rafd796","country_code":"ES","type":"facility","lineage":["https://openalex.org/I134820265","https://openalex.org/I4210094839","https://openalex.org/I79238269"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Nguyen, Thanh Ngoc","raw_affiliation_strings":["ICMS"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ICMS","institution_ids":["https://openalex.org/I4210094839"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127914194","display_name":"Thanh Pham","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I157358134","display_name":"RMIT Vietnam","ror":"https://ror.org/004axh929","country_code":"VN","type":"education","lineage":["https://openalex.org/I157358134","https://openalex.org/I82951845"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Pham, Thanh","raw_affiliation_strings":["RMIT University Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RMIT University Vietnam","institution_ids":["https://openalex.org/I157358134"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127971268","display_name":"Vinh Do","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210094839","display_name":"Instituto de Ciencia de Materiales de Sevilla","ror":"https://ror.org/00rafd796","country_code":"ES","type":"facility","lineage":["https://openalex.org/I134820265","https://openalex.org/I4210094839","https://openalex.org/I79238269"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Do, Vinh","raw_affiliation_strings":["ICMS"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ICMS","institution_ids":["https://openalex.org/I4210094839"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128029878","display_name":"Hien Nguyen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I157358134","display_name":"RMIT Vietnam","ror":"https://ror.org/004axh929","country_code":"VN","type":"education","lineage":["https://openalex.org/I157358134","https://openalex.org/I82951845"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Nguyen, Hien","raw_affiliation_strings":["RMIT University Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RMIT University Vietnam","institution_ids":["https://openalex.org/I157358134"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5153421092","display_name":"Charlotte Nguyen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210094839","display_name":"Instituto de Ciencia de Materiales de Sevilla","ror":"https://ror.org/00rafd796","country_code":"ES","type":"facility","lineage":["https://openalex.org/I134820265","https://openalex.org/I4210094839","https://openalex.org/I79238269"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Nguyen, Charlotte","raw_affiliation_strings":["ICMS"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ICMS","institution_ids":["https://openalex.org/I4210094839"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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/T10860","display_name":"Speech and Audio Processing","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.0,"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/vietnamese-speech-recognition","display_name":"Vietnamese speech recognition","score":0.5590000152587891},{"id":"https://openalex.org/keywords/conversational-speech","display_name":"conversational speech","score":0.8339999914169312},{"id":"https://openalex.org/keywords/casual-speech","display_name":"casual speech","score":0.5529999732971191},{"id":"https://openalex.org/keywords/chatbots","display_name":"chatbots","score":0.4690000116825104},{"id":"https://openalex.org/keywords/customer-service","display_name":"customer service","score":0.9440000057220459},{"id":"https://openalex.org/keywords/call-centers","display_name":"call centers","score":0.8880000114440918},{"id":"https://openalex.org/keywords/pseudo-labeling","display_name":"pseudo-labeling","score":0.7379999756813049},{"id":"https://openalex.org/keywords/transcription","display_name":"transcription","score":0.45399999618530273},{"id":"https://openalex.org/keywords/vietnamese-language","display_name":"Vietnamese language","score":0.4350000023841858},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"speech corpus","score":0.4180000126361847}],"concepts":[{"id":"https://openalex.org/C103621254","wikidata":"https://www.wikidata.org/wiki/Q9199","display_name":"Vietnamese","level":2,"score":0.9800999760627747},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6847000122070312},{"id":"https://openalex.org/C2781426162","wikidata":"https://www.wikidata.org/wiki/Q2275793","display_name":"Casual","level":2,"score":0.6355999708175659},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5475000143051147},{"id":"https://openalex.org/C141668000","wikidata":"https://www.wikidata.org/wiki/Q10991973","display_name":"Hotline","level":2,"score":0.5449000000953674},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5128999948501587},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4747999906539917},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4494999945163727},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3634999990463257},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3562999963760376},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.3370000123977661},{"id":"https://openalex.org/C2778304055","wikidata":"https://www.wikidata.org/wiki/Q657474","display_name":"Beijing","level":3,"score":0.3321000039577484},{"id":"https://openalex.org/C2779463800","wikidata":"https://www.wikidata.org/wiki/Q5062222","display_name":"Center (category theory)","level":2,"score":0.3082999885082245},{"id":"https://openalex.org/C2779235478","wikidata":"https://www.wikidata.org/wiki/Q286576","display_name":"Register (sociolinguistics)","level":2,"score":0.2962000072002411},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2815000116825104},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.26489999890327454}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2603.01894","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2603.01894","pdf_url":"https://arxiv.org/pdf/2603.01894","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2603.01894","doi":"https://doi.org/10.48550/arxiv.2603.01894","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.01894","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2603.01894","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2603.01894","pdf_url":"https://arxiv.org/pdf/2603.01894","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7133306233.pdf","grobid_xml":"https://content.openalex.org/works/W7133306233.grobid-xml"},"referenced_works_count":8,"referenced_works":["https://openalex.org/W1828163288","https://openalex.org/W4319862635","https://openalex.org/W4387799863","https://openalex.org/W4388275972","https://openalex.org/W4404782614","https://openalex.org/W4412886767","https://openalex.org/W4412889507","https://openalex.org/W7131837130"],"related_works":["https://openalex.org/W4399424860","https://openalex.org/W4392368946","https://openalex.org/W7140116537","https://openalex.org/W2405083174","https://openalex.org/W7165758914","https://openalex.org/W4415433760","https://openalex.org/W4385823030","https://openalex.org/W7123350710","https://openalex.org/W7131837130","https://openalex.org/W7214394009"],"abstract_inverted_index":{"We":[0,154],"introduce":[1],"VietSuperSpeech,":[2],"a":[3,19,135,159],"large-scale":[4],"Vietnamese":[5,28,56,113,152,164],"automatic":[6],"speech":[7,65],"recognition":[8],"(ASR)":[9],"dataset":[10,119],"of":[11,112,183],"52,023":[12],"audio-text":[13],"pairs":[14],"totaling":[15,146],"267.39":[16],"hours,":[17],"with":[18,134],"distinctive":[20],"focus":[21],"on":[22,109],"casual":[23],"conversational":[24,197],"speech.":[25,114],"Unlike":[26],"existing":[27],"ASR":[29,165],"corpora":[30,168],"that":[31,156],"predominantly":[32],"feature":[33],"read":[34,186],"speech,":[35,187],"news":[36],"narration,":[37],"or":[38],"audiobook":[39],"content,":[40],"VietSuperSpeech":[41,157,200],"is":[42,80,120,201],"sourced":[43],"from":[44],"four":[45],"publicly":[46,202],"accessible":[47],"YouTube":[48],"channels":[49],"spanning":[50],"everyday":[51],"conversation,":[52],"personal":[53],"vlogging,":[54],"overseas":[55],"community":[57],"dialogue,":[58],"and":[59,75,88,128,178,185],"informal":[60],"commentary":[61],"-":[62],"the":[63,100,118,163,191],"very":[64],"styles":[66],"encountered":[67],"in":[68,162],"real-world":[69],"chatbot,":[70],"customer":[71],"support,":[72],"call":[73],"center,":[74],"hotline":[76],"deployments.":[77],"All":[78],"audio":[79],"standardized":[81],"to":[82],"16":[83],"kHz":[84],"mono":[85],"PCM":[86],"WAV":[87],"segmented":[89],"into":[90,122],"3-30":[91],"second":[92],"utterances.":[93],"Transcriptions":[94],"are":[95],"generated":[96],"via":[97],"pseudo-labeling":[98],"using":[99],"Zipformer-30M-RNNT-6000h":[101],"model":[102],"(Nguyen,":[103],"2025)":[104],"deployed":[105],"through":[106],"Sherpa-ONNX,":[107],"pre-trained":[108],"6,000":[110],"hours":[111],"After":[115],"quality":[116],"filtering,":[117],"split":[121],"46,822":[123],"training":[124],"samples":[125,131],"(240.67":[126],"hours)":[127,133],"5,201":[129],"development/test":[130],"(26.72":[132],"fixed":[136],"random":[137],"seed.":[138],"The":[139],"text":[140],"averages":[141],"266":[142],"characters":[143],"per":[144],"utterance,":[145],"13.8":[147],"million":[148],"fully":[149],"diacritically":[150],"marked":[151],"characters.":[153],"demonstrate":[155],"fills":[158],"critical":[160],"gap":[161],"ecosystem:":[166],"while":[167],"such":[169],"as":[170],"VLSP2020,":[171],"VIET_BUD500,":[172],"VietSpeech,":[173],"FLEURS,":[174],"VietMed,":[175],"Sub-GigaSpeech2-Vi,":[176],"viVoice,":[177],"Sub-PhoAudioBook":[179],"provide":[180],"broad":[181],"coverage":[182],"formal":[184],"none":[188],"specifically":[189],"targets":[190],"casual,":[192],"spontaneous":[193],"register":[194],"indispensable":[195],"for":[196],"AI":[198],"applications.":[199],"released":[203],"at":[204],"https://huggingface.co/datasets/thanhnew2001/VietSuperSpeech.":[205]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-03-04T00:00:00"}
