{"id":"https://openalex.org/W3197742413","doi":"https://doi.org/10.21437/interspeech.2021-1259","title":"speechocean762: An Open-Source Non-Native English Speech Corpus for Pronunciation Assessment","display_name":"speechocean762: An Open-Source Non-Native English Speech Corpus for Pronunciation Assessment","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3197742413","doi":"https://doi.org/10.21437/interspeech.2021-1259","mag":"3197742413"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-1259","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1259","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100778479","display_name":"Junbo Zhang","orcid":"https://orcid.org/0000-0001-5947-1374"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junbo Zhang","raw_affiliation_strings":["Xiaomi Corporation, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaomi Corporation, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100611977","display_name":"Zhiwen Zhang","orcid":"https://orcid.org/0000-0002-3123-8885"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhiwen Zhang","raw_affiliation_strings":["SpeechOcean Ltd., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SpeechOcean Ltd., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107143533","display_name":"Yongqing Wang","orcid":"https://orcid.org/0000-0002-4679-0760"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yongqing Wang","raw_affiliation_strings":["Xiaomi Corporation, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaomi Corporation, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113948981","display_name":"Zhiyong Yan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhiyong Yan","raw_affiliation_strings":["Xiaomi Corporation, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaomi Corporation, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053875219","display_name":"Qiong Song","orcid":"https://orcid.org/0000-0001-9828-5611"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiong Song","raw_affiliation_strings":["SpeechOcean Ltd., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SpeechOcean Ltd., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102764010","display_name":"Yukai Huang","orcid":"https://orcid.org/0000-0002-2200-3697"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yukai Huang","raw_affiliation_strings":["SpeechOcean Ltd., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SpeechOcean Ltd., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100343450","display_name":"Ke Li","orcid":"https://orcid.org/0000-0001-7200-4244"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ke Li","raw_affiliation_strings":["SpeechOcean Ltd., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SpeechOcean Ltd., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084286453","display_name":"Daniel Povey","orcid":"https://orcid.org/0000-0002-0611-3634"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Daniel Povey","raw_affiliation_strings":["Xiaomi Corporation, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaomi Corporation, Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100362598","display_name":"Yujun Wang","orcid":"https://orcid.org/0000-0002-0921-0122"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yujun Wang","raw_affiliation_strings":["Xiaomi Corporation, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaomi Corporation, Beijing, China","institution_ids":[]}]}],"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":false,"cited_by_count":62,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3710","last_page":"3714"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9894000291824341,"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":0.9894000291824341,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9794999957084656,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.8266710638999939},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7260183095932007},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5321767926216125},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5137056112289429},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.4603566527366638},{"id":"https://openalex.org/keywords/open-source","display_name":"Open source","score":0.42483046650886536},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40100544691085815},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3839396834373474},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.314360648393631},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.04879477620124817}],"concepts":[{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.8266710638999939},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7260183095932007},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5321767926216125},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5137056112289429},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.4603566527366638},{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.42483046650886536},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40100544691085815},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3839396834373474},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.314360648393631},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.04879477620124817},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2021-1259","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1259","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6700000166893005,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W101533558","https://openalex.org/W1753200545","https://openalex.org/W1895481600","https://openalex.org/W2082367183","https://openalex.org/W2091856355","https://openalex.org/W2137226992","https://openalex.org/W2397238603","https://openalex.org/W2401916374","https://openalex.org/W2404722202","https://openalex.org/W2407533274","https://openalex.org/W2552635739","https://openalex.org/W2556576367","https://openalex.org/W2559844874","https://openalex.org/W2571017604","https://openalex.org/W2741510257","https://openalex.org/W2770743368","https://openalex.org/W2888954148","https://openalex.org/W2888996995","https://openalex.org/W2938386610","https://openalex.org/W2976346930","https://openalex.org/W3001687786","https://openalex.org/W3015231007","https://openalex.org/W3043352754","https://openalex.org/W3096091920","https://openalex.org/W3097515180","https://openalex.org/W3112683920"],"related_works":["https://openalex.org/W4200068392","https://openalex.org/W2772686614","https://openalex.org/W2036933852","https://openalex.org/W2152945827","https://openalex.org/W2015513221","https://openalex.org/W2181773877","https://openalex.org/W301864623","https://openalex.org/W2757826346","https://openalex.org/W2184371793","https://openalex.org/W2349468610"],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"a":[3],"new":[4],"open-source":[5],"speech":[6,88],"corpus":[7,59],"named":[8],"\"speechocean762\"":[9],"designed":[10],"for":[11,66,73],"pronunciation":[12,53],"assessment":[13,54],"use,":[14],"consisting":[15],"of":[16,26,34],"5000":[17],"English":[18],"utterances":[19,36],"from":[20,76],"250":[21],"non-native":[22],"speakers,":[23],"where":[24],"half":[25],"the":[27,35,51,79,86],"speakers":[28],"are":[29],"children.Five":[30],"experts":[31],"annotated":[32],"each":[33],"at":[37],"sentence-level,":[38],"wordlevel":[39],"and":[40,68,78],"phoneme-level.A":[41],"baseline":[42,81],"system":[43,82],"is":[44,60,71,83],"released":[45],"in":[46,85],"open":[47],"source":[48],"to":[49,62],"illustrate":[50],"phoneme-level":[52],"workflow":[55],"on":[56],"this":[57],"corpus.This":[58],"allowed":[61],"be":[63],"used":[64],"freely":[65],"commercial":[67],"non-commercial":[69],"purposes.It":[70],"available":[72],"free":[74],"download":[75],"OpenSLR,":[77],"corresponding":[80],"published":[84],"Kaldi":[87],"recognition":[89],"toolkit.":[90]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":20},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
