{"id":"https://openalex.org/W4402111964","doi":"https://doi.org/10.21437/interspeech.2024-918","title":"AS-70: A Mandarin stuttered speech dataset for automatic speech recognition and stuttering event detection","display_name":"AS-70: A Mandarin stuttered speech dataset for automatic speech recognition and stuttering event detection","publication_year":2024,"publication_date":"2024-09-01","ids":{"openalex":"https://openalex.org/W4402111964","doi":"https://doi.org/10.21437/interspeech.2024-918"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2024-918","doi":"https://doi.org/10.21437/interspeech.2024-918","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-918","pdf_url":null,"source":{"id":"https://openalex.org/S4393918409","display_name":"Interspeech (USB)","issn_l":"2308-457X","issn":["2308-457X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"},"volume":null,"type":"conference-abstract","is_traditional":false,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2406.07256","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Rong Gong","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rong Gong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014632942","display_name":"Hongfei Xue","orcid":"https://orcid.org/0000-0001-9691-9668","observed_orcids":["https://orcid.org/0000-0001-9691-9668"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hongfei Xue","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Lezhi Wang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lezhi Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053112608","display_name":"Xin Xu","orcid":"https://orcid.org/0000-0003-3238-745X","observed_orcids":["https://orcid.org/0000-0003-3238-745X","https://orcid.org/0009-0002-1718-3555","https://orcid.org/0000-0002-9506-0887","https://orcid.org/0009-0009-8295-9381","https://orcid.org/0000-0002-0780-156X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xin Xu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103149967","display_name":"Qisheng Li","orcid":"https://orcid.org/0000-0001-7609-8102","observed_orcids":["https://orcid.org/0000-0001-7609-8102"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qisheng Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100668966","display_name":"Lei Xie","orcid":"https://orcid.org/0000-0001-8234-0823","observed_orcids":["https://orcid.org/0000-0001-8234-0823"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lei Xie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101791717","display_name":"Hui Bu","orcid":"https://orcid.org/0000-0003-1883-8496","observed_orcids":["https://orcid.org/0000-0003-1883-8496"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hui Bu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023143763","display_name":"Shaomei Wu","orcid":"https://orcid.org/0000-0003-1104-4116","observed_orcids":["https://orcid.org/0000-0003-1104-4116"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shaomei Wu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114859604","display_name":"Jiaming Zhou","orcid":"https://orcid.org/0009-0001-4760-9708","observed_orcids":["https://orcid.org/0009-0001-4760-9708"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiaming Zhou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088716214","display_name":"Yong Qin","orcid":"https://orcid.org/0000-0002-6519-8316","observed_orcids":["https://orcid.org/0000-0002-6519-8316"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yong Qin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Binbin Zhang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Binbin Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103586766","display_name":"Jun Bao Du","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jun Du","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104281427","display_name":"Jia Bin","orcid":"https://orcid.org/0009-0002-2967-5039","observed_orcids":["https://orcid.org/0009-0002-2967-5039"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jia Bin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100317339","display_name":"Ming Li","orcid":"https://orcid.org/0000-0002-4965-2670","observed_orcids":["https://orcid.org/0000-0002-4965-2670"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ming Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":21,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5098","last_page":"5102"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9916999936103821,"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":0.9916999936103821,"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/T12684","display_name":"Stuttering Research and Treatment","score":0.007300000172108412,"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/T10860","display_name":"Speech and Audio Processing","score":0.0003000000142492354,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/stuttered-speech","display_name":"stuttered speech","score":0.8690000176429749},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.6800000071525574},{"id":"https://openalex.org/keywords/conversational-speech","display_name":"conversational speech","score":0.7870000004768372},{"id":"https://openalex.org/keywords/manual-transcription","display_name":"manual transcription","score":0.6610000133514404},{"id":"https://openalex.org/keywords/atypical-speech","display_name":"atypical speech","score":0.8019999861717224}],"concepts":[{"id":"https://openalex.org/C2781371259","wikidata":"https://www.wikidata.org/wiki/Q186676","display_name":"Stuttering","level":2,"score":0.9302552938461304},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.8678175210952759},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7545225620269775},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5953620672225952},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5431292653083801},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3799417018890381},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32480424642562866},{"id":"https://openalex.org/C548259974","wikidata":"https://www.wikidata.org/wiki/Q569965","display_name":"Audiology","level":1,"score":0.25502899289131165},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.24140343070030212},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.044027179479599},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2024-918","doi":"https://doi.org/10.21437/interspeech.2024-918","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-918","pdf_url":null,"source":{"id":"https://openalex.org/S4393918409","display_name":"Interspeech (USB)","issn_l":"2308-457X","issn":["2308-457X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2406.07256","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.07256","pdf_url":"https://arxiv.org/pdf/2406.07256","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2406.07256","doi":"https://doi.org/10.48550/arxiv.2406.07256","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2406.07256","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:2406.07256","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.07256","pdf_url":"https://arxiv.org/pdf/2406.07256","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":"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/W4402111964.pdf","grobid_xml":"https://content.openalex.org/works/W4402111964.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2511489569","https://openalex.org/W6962699381","https://openalex.org/W2978609544","https://openalex.org/W7027056219","https://openalex.org/W1998260193","https://openalex.org/W2036842033","https://openalex.org/W18159819","https://openalex.org/W4402111489","https://openalex.org/W187723304","https://openalex.org/W178457378"],"abstract_inverted_index":{"The":[0],"rapid":[1],"advancements":[2],"in":[3,16,60,110,124],"speech":[4,20,51],"technologies":[5],"over":[6],"the":[7,27,45,57,105,111],"past":[8],"two":[9],"decades":[10],"have":[11],"led":[12],"to":[13,35],"human-level":[14],"performance":[15],"tasks":[17],"like":[18],"automatic":[19],"recognition":[21],"(ASR)":[22],"for":[23,78,92],"fluent":[24],"speech.":[25,127],"However,":[26],"efficacy":[28],"of":[29],"these":[30],"models":[31],"diminishes":[32],"when":[33],"applied":[34],"atypical":[36],"speech,":[37,69],"such":[38],"as":[39,56],"stuttering.":[40],"This":[41],"paper":[42],"introduces":[43],"AS-70,":[44],"first":[46],"publicly":[47],"available":[48],"Mandarin":[49],"stuttered":[50,126],"dataset,":[52],"which":[53],"stands":[54],"out":[55],"largest":[58],"dataset":[59,103],"its":[61],"category.":[62],"Encompassing":[63],"conversational":[64],"and":[65,87,94,117],"voice":[66],"command":[67],"reading":[68],"AS-70":[70],"includes":[71],"verbatim":[72],"manual":[73],"transcription,":[74],"rendering":[75],"it":[76],"suitable":[77],"various":[79],"speech-related":[80],"tasks.":[81,99],"Furthermore,":[82],"baseline":[83],"systems":[84],"are":[85,90,119],"established,":[86],"experimental":[88],"results":[89],"presented":[91],"ASR":[93,113],"stuttering":[95],"event":[96],"detection":[97],"(SED)":[98],"By":[100],"incorporating":[101],"this":[102],"into":[104],"model":[106],"fine-tuning,":[107],"significant":[108],"improvements":[109],"state-of-the-art":[112],"models,":[114],"e.g.,":[115],"Whisper":[116],"Hubert,":[118],"observed,":[120],"enhancing":[121],"their":[122],"inclusivity":[123],"addressing":[125]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":4}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2024-09-02T00:00:00"}
