{"id":"https://openalex.org/W2787693822","doi":"https://doi.org/10.1109/apsipa.2017.8282133","title":"A free Kazakh speech database and a speech recognition baseline","display_name":"A free Kazakh speech database and a speech recognition baseline","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2787693822","doi":"https://doi.org/10.1109/apsipa.2017.8282133","mag":"2787693822"},"language":"en","primary_location":{"id":"doi:10.1109/apsipa.2017.8282133","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipa.2017.8282133","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5102001805","display_name":"Ying Shi","orcid":"https://orcid.org/0000-0001-8445-2300"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Shi","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024320681","display_name":"Askar Hamdullah","orcid":null},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Askar Hamdullah","raw_affiliation_strings":["Xinjiang University, Wulumuqi, Xinjiang, CN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xinjiang University, Wulumuqi, Xinjiang, CN","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056437232","display_name":"Zhiyuan Tang","orcid":"https://orcid.org/0000-0002-3786-7690"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyuan Tang","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100391494","display_name":"Dong Wang","orcid":"https://orcid.org/0000-0002-6992-7950"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dong Wang","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084318285","display_name":"Thomas Fang Zheng","orcid":"https://orcid.org/0000-0002-0249-4767"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Thomas Fang Zheng","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":8,"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":0.9998000264167786,"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":0.9998000264167786,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.994700014591217,"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":0.989300012588501,"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":0.807859480381012},{"id":"https://openalex.org/keywords/kazakh","display_name":"Kazakh","score":0.6104212403297424},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.5689648389816284},{"id":"https://openalex.org/keywords/chinese-speech-synthesis","display_name":"Chinese speech synthesis","score":0.566875696182251},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5212658047676086},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.4944479465484619},{"id":"https://openalex.org/keywords/obstacle","display_name":"Obstacle","score":0.48502084612846375},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.43749701976776123},{"id":"https://openalex.org/keywords/speech-technology","display_name":"Speech technology","score":0.4321352243423462},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.429552286863327},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4236615300178528},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.41548284888267517},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3936520218849182},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3632863759994507},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.3319990038871765},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.31148189306259155},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09260892868041992}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.807859480381012},{"id":"https://openalex.org/C2781297163","wikidata":"https://www.wikidata.org/wiki/Q9252","display_name":"Kazakh","level":2,"score":0.6104212403297424},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.5689648389816284},{"id":"https://openalex.org/C73411735","wikidata":"https://www.wikidata.org/wiki/Q16369","display_name":"Chinese speech synthesis","level":4,"score":0.566875696182251},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5212658047676086},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.4944479465484619},{"id":"https://openalex.org/C2776650193","wikidata":"https://www.wikidata.org/wiki/Q264661","display_name":"Obstacle","level":2,"score":0.48502084612846375},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.43749701976776123},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.4321352243423462},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.429552286863327},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4236615300178528},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.41548284888267517},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3936520218849182},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3632863759994507},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.3319990038871765},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.31148189306259155},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09260892868041992},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipa.2017.8282133","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipa.2017.8282133","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.75,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W300893532","https://openalex.org/W330298975","https://openalex.org/W1524333225","https://openalex.org/W1608367484","https://openalex.org/W1631260214","https://openalex.org/W1779452081","https://openalex.org/W1970663544","https://openalex.org/W2024490156","https://openalex.org/W2147768505","https://openalex.org/W2160815625","https://openalex.org/W2166637769","https://openalex.org/W2284628133","https://openalex.org/W2962826786","https://openalex.org/W4297797495","https://openalex.org/W6631362777","https://openalex.org/W6636811518","https://openalex.org/W6638005537"],"related_works":["https://openalex.org/W2349468610","https://openalex.org/W2356192947","https://openalex.org/W2184371793","https://openalex.org/W2772686614","https://openalex.org/W3206301783","https://openalex.org/W2036933852","https://openalex.org/W4200068392","https://openalex.org/W301864623","https://openalex.org/W2186688931","https://openalex.org/W2537969829"],"abstract_inverted_index":{"Automatic":[0],"speech":[1,54,84,106],"recognition":[2],"(ASR)":[3],"has":[4],"gained":[5],"significant":[6],"improvement":[7],"for":[8,56,147,161,188],"major":[9,111],"languages":[10,190],"such":[11],"as":[12,69],"English":[13],"and":[14,26,59,75,77,87,97,126,152,164],"Chinese,":[15],"partly":[16],"due":[17],"to":[18,183],"the":[19,36,41,60,83,115,145,175],"emergence":[20],"of":[21,29,124],"deep":[22],"neural":[23],"networks":[24],"(DNN)":[25],"large":[27],"amount":[28],"training":[30],"data.":[31],"For":[32],"minority":[33,57,112,189],"languages,":[34,58],"however,":[35],"progress":[37],"is":[38,47,172],"largely":[39],"behind":[40],"main":[42],"stream.":[43],"A":[44],"particularly":[45],"obstacle":[46],"that":[48],"there":[49],"are":[50,64,80,90,129,159],"almost":[51],"no":[52],"large-scale":[53],"databases":[55,63],"only":[61],"few":[62,79],"held":[65],"by":[66,132,168,174,179],"some":[67],"institutes":[68,163],"private":[70],"properties,":[71],"far":[72],"from":[73],"open":[74],"standard,":[76],"very":[78],"free.":[81],"Besides":[82],"database,":[85,120],"phonetic":[86,125],"linguistic":[88,127],"resources":[89,128,158],"also":[91,130],"scarce,":[92],"including":[93],"phone":[94],"set,":[95],"lexicon,":[96],"language":[98,113],"model.":[99],"In":[100],"this":[101,119],"paper,":[102],"we":[103],"publish":[104],"a":[105,110,121,134,149],"database":[107],"in":[108,114,191],"Kazakh,":[109],"western":[116],"China.":[117,192],"Accompanying":[118],"full":[122],"set":[123],"published,":[131],"which":[133,181],"full-fledged":[135],"Kazakh":[136],"ASR":[137,186],"system":[138],"can":[139,165],"be":[140,166],"constructed.":[141],"We":[142],"will":[143],"describe":[144],"recipe":[146],"constructing":[148],"baseline":[150],"system,":[151],"report":[153],"our":[154],"present":[155],"results.":[156],"The":[157,170],"free":[160],"research":[162],"obtained":[167],"request.":[169],"publication":[171],"supported":[173,178],"M2ASR":[176],"project":[177],"NSFC,":[180],"aims":[182],"build":[184],"multilingual":[185],"systems":[187]},"counts_by_year":[{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}