{"id":"https://openalex.org/W3095817316","doi":"https://doi.org/10.1109/slt48900.2021.9383546","title":"IEEE SLT 2021 Alpha-Mini Speech Challenge: Open Datasets, Tracks, Rules and Baselines","display_name":"IEEE SLT 2021 Alpha-Mini Speech Challenge: Open Datasets, Tracks, Rules and Baselines","publication_year":2021,"publication_date":"2021-01-19","ids":{"openalex":"https://openalex.org/W3095817316","doi":"https://doi.org/10.1109/slt48900.2021.9383546","mag":"3095817316"},"language":"en","primary_location":{"id":"doi:10.1109/slt48900.2021.9383546","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383546","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2011.02198","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010250251","display_name":"Yihui Fu","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yihui Fu","raw_affiliation_strings":["Audio, Speech and Language Processing Group (ASLP), School of Computer Science, Northwestern Polytechnical University, Xi\u2019an, China","Audio, Speech and Language Processing Group (ASLP)School of Computer Science, Northwestern Polytechnical University, Xi'an, China#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP), School of Computer Science, Northwestern Polytechnical University, Xi\u2019an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP)School of Computer Science, Northwestern Polytechnical University, Xi'an, China#TAB#","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109482068","display_name":"Zhuoyuan Yao","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhuoyuan Yao","raw_affiliation_strings":["Audio, Speech and Language Processing Group (ASLP), School of Computer Science, Northwestern Polytechnical University, Xi\u2019an, China","Audio, Speech and Language Processing Group (ASLP)School of Computer Science, Northwestern Polytechnical University, Xi'an, China#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP), School of Computer Science, Northwestern Polytechnical University, Xi\u2019an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP)School of Computer Science, Northwestern Polytechnical University, Xi'an, China#TAB#","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103162780","display_name":"Weipeng He","orcid":"https://orcid.org/0000-0002-3874-3083"},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Weipeng He","raw_affiliation_strings":["Idiap Research Institute, Switzerland","IDIAP Research Institute, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Switzerland","institution_ids":["https://openalex.org/I7495430"]},{"raw_affiliation_string":"IDIAP Research Institute, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101674460","display_name":"Jian Wu","orcid":"https://orcid.org/0000-0002-3101-7011"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Wu","raw_affiliation_strings":["Audio, Speech and Language Processing Group (ASLP), School of Computer Science, Northwestern Polytechnical University, Xi\u2019an, China","Audio, Speech and Language Processing Group (ASLP)School of Computer Science, Northwestern Polytechnical University, Xi'an, China#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP), School of Computer Science, Northwestern Polytechnical University, Xi\u2019an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP)School of Computer Science, Northwestern Polytechnical University, Xi'an, China#TAB#","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101814724","display_name":"Xiong Wang","orcid":"https://orcid.org/0000-0002-2155-9044"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiong Wang","raw_affiliation_strings":["Audio, Speech and Language Processing Group (ASLP), School of Computer Science, Northwestern Polytechnical University, Xi\u2019an, China","Audio, Speech and Language Processing Group (ASLP)School of Computer Science, Northwestern Polytechnical University, Xi'an, China#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP), School of Computer Science, Northwestern Polytechnical University, Xi\u2019an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP)School of Computer Science, Northwestern Polytechnical University, Xi'an, China#TAB#","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056581663","display_name":"Zhanheng Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhanheng Yang","raw_affiliation_strings":["Audio, Speech and Language Processing Group (ASLP), School of Computer Science, Northwestern Polytechnical University, Xi\u2019an, China","Audio, Speech and Language Processing Group (ASLP)School of Computer Science, Northwestern Polytechnical University, Xi'an, China#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP), School of Computer Science, Northwestern Polytechnical University, Xi\u2019an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP)School of Computer Science, Northwestern Polytechnical University, Xi'an, China#TAB#","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100630316","display_name":"Shimin Zhang","orcid":"https://orcid.org/0009-0004-4344-5218"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shimin Zhang","raw_affiliation_strings":["Audio, Speech and Language Processing Group (ASLP), School of Computer Science, Northwestern Polytechnical University, Xi\u2019an, China","Audio, Speech and Language Processing Group (ASLP)School of Computer Science, Northwestern Polytechnical University, Xi'an, China#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP), School of Computer Science, Northwestern Polytechnical University, Xi\u2019an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP)School of Computer Science, Northwestern Polytechnical University, Xi'an, China#TAB#","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100668966","display_name":"Lei Xie","orcid":"https://orcid.org/0000-0001-8234-0823"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Xie","raw_affiliation_strings":["Audio, Speech and Language Processing Group (ASLP), School of Computer Science, Northwestern Polytechnical University, Xi\u2019an, China","Audio, Speech and Language Processing Group (ASLP)School of Computer Science, Northwestern Polytechnical University, Xi'an, China#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP), School of Computer Science, Northwestern Polytechnical University, Xi\u2019an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP)School of Computer Science, Northwestern Polytechnical University, Xi'an, China#TAB#","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091779986","display_name":"Dongyan Huang","orcid":"https://orcid.org/0000-0001-8844-8579"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dongyan Huang","raw_affiliation_strings":["UBTECH Technology Co., Ltd, Shenzhen, China","UBTECH Technology Co., Ltd,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UBTECH Technology Co., Ltd, Shenzhen, China","institution_ids":[]},{"raw_affiliation_string":"UBTECH Technology Co., Ltd,Shenzhen,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101791717","display_name":"Hui Bu","orcid":"https://orcid.org/0000-0003-1883-8496"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hui Bu","raw_affiliation_strings":["AISHELL Technology Co., Ltd., Beijing, China","AISHELL Technology Co., Ltd.,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AISHELL Technology Co., Ltd., Beijing, China","institution_ids":[]},{"raw_affiliation_string":"AISHELL Technology Co., Ltd.,Beijing,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076409146","display_name":"Petr Motl\u00ed\u010dek","orcid":"https://orcid.org/0000-0001-6467-1119"},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Petr Motlicek","raw_affiliation_strings":["Idiap Research Institute, Switzerland","IDIAP Research Institute, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Switzerland","institution_ids":["https://openalex.org/I7495430"]},{"raw_affiliation_string":"IDIAP Research Institute, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053358969","display_name":"Jean\u2010Marc Odobez","orcid":"https://orcid.org/0000-0002-9537-9898"},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Jean-Marc Odobez","raw_affiliation_strings":["Idiap Research Institute, Switzerland","IDIAP Research Institute, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Switzerland","institution_ids":["https://openalex.org/I7495430"]},{"raw_affiliation_string":"IDIAP Research Institute, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1101","last_page":"1108"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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/T11309","display_name":"Music and Audio Processing","score":0.9959999918937683,"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/computer-science","display_name":"Computer science","score":0.8031478524208069},{"id":"https://openalex.org/keywords/keyword-spotting","display_name":"Keyword spotting","score":0.629584014415741},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6036694645881653},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5438987612724304},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5373887419700623},{"id":"https://openalex.org/keywords/humanoid-robot","display_name":"Humanoid robot","score":0.5243035554885864},{"id":"https://openalex.org/keywords/echo","display_name":"Echo (communications protocol)","score":0.4984009265899658},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4909558594226837},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.475410521030426},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4746066927909851},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.4494627118110657},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32022354006767273},{"id":"https://openalex.org/keywords/sound-pressure","display_name":"Sound pressure","score":0.08235260844230652}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8031478524208069},{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.629584014415741},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6036694645881653},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5438987612724304},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5373887419700623},{"id":"https://openalex.org/C60692881","wikidata":"https://www.wikidata.org/wiki/Q584529","display_name":"Humanoid robot","level":3,"score":0.5243035554885864},{"id":"https://openalex.org/C2779426996","wikidata":"https://www.wikidata.org/wiki/Q18389128","display_name":"Echo (communications protocol)","level":2,"score":0.4984009265899658},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4909558594226837},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.475410521030426},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4746066927909851},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.4494627118110657},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32022354006767273},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.08235260844230652},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/slt48900.2021.9383546","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383546","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2011.02198","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.02198","pdf_url":"https://arxiv.org/pdf/2011.02198","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"mag:3095817316","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2011.02198","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2011.02198","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2011.02198","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"raw_source_name":null,"raw_type":"Preprint"},{"id":"doi:10.17023/kjv3-je60","is_oa":true,"landing_page_url":"https://doi.org/10.17023/kjv3-je60","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Audiovisual"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2011.02198","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.02198","pdf_url":"https://arxiv.org/pdf/2011.02198","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6899999976158142}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3095817316.pdf","grobid_xml":"https://content.openalex.org/works/W3095817316.grobid-xml"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W1496120315","https://openalex.org/W1553469512","https://openalex.org/W1979256737","https://openalex.org/W2015688877","https://openalex.org/W2034940213","https://openalex.org/W2046317813","https://openalex.org/W2056986588","https://openalex.org/W2112028260","https://openalex.org/W2113638573","https://openalex.org/W2114097550","https://openalex.org/W2117671523","https://openalex.org/W2145215282","https://openalex.org/W2164502538","https://openalex.org/W2173629880","https://openalex.org/W2613303405","https://openalex.org/W2701869962","https://openalex.org/W2749335474","https://openalex.org/W2772736377","https://openalex.org/W2797759721","https://openalex.org/W2811405065","https://openalex.org/W2871284238","https://openalex.org/W2886949521","https://openalex.org/W2888793942","https://openalex.org/W2888842465","https://openalex.org/W2897977894","https://openalex.org/W2963242190","https://openalex.org/W2963414149","https://openalex.org/W2963846200","https://openalex.org/W3002439978","https://openalex.org/W3003903817","https://openalex.org/W3007913012","https://openalex.org/W3008311461","https://openalex.org/W3016238098","https://openalex.org/W3029661253","https://openalex.org/W3046669506","https://openalex.org/W3047602798","https://openalex.org/W3047800964","https://openalex.org/W3095321517","https://openalex.org/W3096408984","https://openalex.org/W6772622344","https://openalex.org/W6780998715"],"related_works":["https://openalex.org/W3144243780","https://openalex.org/W3163571828","https://openalex.org/W3206252155","https://openalex.org/W2964323211","https://openalex.org/W2405504744","https://openalex.org/W2977673020","https://openalex.org/W3015995734","https://openalex.org/W3209984917","https://openalex.org/W3135508679","https://openalex.org/W2141835434","https://openalex.org/W3204496078","https://openalex.org/W3046125265","https://openalex.org/W3107298252","https://openalex.org/W3032880114","https://openalex.org/W2395845374","https://openalex.org/W3212414183","https://openalex.org/W2188924248","https://openalex.org/W2564953936","https://openalex.org/W2601477764","https://openalex.org/W3008587939"],"abstract_inverted_index":{"The":[0],"IEEE":[1],"Spoken":[2],"Language":[3],"Technology":[4],"Workshop":[5],"(SLT)":[6],"2021":[7],"Alpha-mini":[8,158],"Speech":[9],"Challenge":[10],"(ASC)":[11],"is":[12,54,83],"intended":[13],"to":[14,56,61,149,191],"improve":[15,62],"research":[16],"on":[17,26,41,126,146],"keyword":[18],"spotting":[19],"(KWS)":[20],"and":[21,39,70,78,95,116,128,152,169,187,196],"sound":[22],"source":[23,43,110],"location":[24],"(SSL)":[25],"humanoid":[27,135],"robots.":[28],"Many":[29],"publications":[30],"report":[31],"significant":[32],"improvements":[33],"in":[34,45,98],"deep":[35,49],"learning":[36,50],"based":[37],"KWS":[38,127],"SSL":[40],"open":[42,109],"datasets":[44],"recent":[46],"years.":[47],"For":[48],"model":[51,64,178],"training,":[52],"it":[53],"necessary":[55],"expand":[57],"the":[58,63,156,174,183],"data":[59,72,94,97],"coverage":[60],"robustness.":[65],"Thus,":[66],"simulating":[67],"multi-channel":[68],"noisy":[69],"reverberant":[71],"from":[73],"single-channel":[74],"speech,":[75,113],"noise,":[76],"echo":[77,103,115,168],"room":[79],"impulsive":[80],"response":[81],"(RIR)":[82],"widely":[84],"adopted.":[85],"However,":[86],"this":[87,106],"approach":[88],"may":[89],"generate":[90],"mismatch":[91],"between":[92],"simulated":[93],"recorded":[96],"real":[99],"application":[100,160],"scenarios,":[101],"especially":[102],"data.":[104],"In":[105],"challenge,":[107],"we":[108,181],"a":[111,134,142],"sizable":[112],"keyword,":[114],"noise":[117,164,171],"corpus":[118],"for":[119,177,189],"promoting":[120],"data-driven":[121],"methods,":[122],"particularly":[123],"deep-learning":[124],"approaches":[125],"SSL.":[129],"We":[130],"also":[131],"choose":[132],"Alpha-mini,":[133],"robot":[136,159,175],"produced":[137],"by":[138,173],"UBTECH":[139],"equipped":[140],"with":[141],"built-in":[143],"four-microphone":[144],"array":[145],"its":[147],"head,":[148],"record":[150],"development":[151],"evaluation":[153,185],"sets":[154],"under":[155],"actual":[157],"scenario,":[161],"including":[162],"environ-mental":[163],"as":[165,167],"well":[166],"mechanical":[170],"generated":[172],"itself":[176],"evaluation.":[179],"Furthermore,":[180],"illustrate":[182],"rules,":[184],"methods":[186],"baselines":[188],"re-searchers":[190],"quickly":[192],"assess":[193],"their":[194,198],"achievements":[195],"optimize":[197],"models.":[199]},"counts_by_year":[{"year":2021,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2022-03-02T00:00:00"}