{"id":"https://openalex.org/W2787479910","doi":"https://doi.org/10.1109/asru.2017.8268999","title":"The iFLYTEK system for blizzard machine learning challenge 2017-ES1","display_name":"The iFLYTEK system for blizzard machine learning challenge 2017-ES1","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2787479910","doi":"https://doi.org/10.1109/asru.2017.8268999","mag":"2787479910"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2017.8268999","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2017.8268999","pdf_url":null,"source":{"id":"https://openalex.org/S4306498158","display_name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5100343789","display_name":"Lijuan Liu","orcid":"https://orcid.org/0009-0007-0163-7336"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li-Juan Liu","raw_affiliation_strings":["liFLYTEK Research, Hefei, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"liFLYTEK Research, Hefei, P.R. China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113730802","display_name":"Chuang Ding","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chuang Ding","raw_affiliation_strings":["iFLYTEK Research, Hefei, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"iFLYTEK Research, Hefei, P.R. China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059516164","display_name":"Ya-Jun Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ya-Jun Hu","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R. China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059767940","display_name":"Zhen-Hua Ling","orcid":"https://orcid.org/0000-0001-7853-5273"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen-Hua Ling","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R. China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064657549","display_name":"Yuan Jiang","orcid":"https://orcid.org/0000-0003-4307-0562"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuan Jiang","raw_affiliation_strings":["liFLYTEK Research, Hefei, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"liFLYTEK Research, Hefei, P.R. China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100701574","display_name":"Ming Zhou","orcid":"https://orcid.org/0000-0002-5701-1996"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ming Zhou","raw_affiliation_strings":["iFLYTEK Research, Hefei, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"iFLYTEK Research, Hefei, P.R. China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050660824","display_name":"Si Wei","orcid":"https://orcid.org/0000-0002-8363-9111"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Si Wei","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R. China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"657","last_page":"664"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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":0.9973999857902527,"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/T10860","display_name":"Speech and Audio Processing","score":0.9937999844551086,"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":0.7723796367645264},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.67523592710495},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5513925552368164},{"id":"https://openalex.org/keywords/principal-component-analysis","display_name":"Principal component analysis","score":0.5393528938293457},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.46921077370643616},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4680235981941223},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4587640166282654},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4458857774734497}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7723796367645264},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.67523592710495},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5513925552368164},{"id":"https://openalex.org/C27438332","wikidata":"https://www.wikidata.org/wiki/Q2873","display_name":"Principal component analysis","level":2,"score":0.5393528938293457},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.46921077370643616},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4680235981941223},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4587640166282654},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4458857774734497},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru.2017.8268999","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2017.8268999","pdf_url":null,"source":{"id":"https://openalex.org/S4306498158","display_name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5699999928474426}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W32588098","https://openalex.org/W648143168","https://openalex.org/W1600722501","https://openalex.org/W2089468765","https://openalex.org/W2099471712","https://openalex.org/W2102003408","https://openalex.org/W2129142580","https://openalex.org/W2173520492","https://openalex.org/W2194775991","https://openalex.org/W2293634267","https://openalex.org/W2294797155","https://openalex.org/W2403471241","https://openalex.org/W2405756170","https://openalex.org/W2471520273","https://openalex.org/W2519091744","https://openalex.org/W2608338293","https://openalex.org/W2658996865","https://openalex.org/W2666408839","https://openalex.org/W2949999304","https://openalex.org/W2951523806","https://openalex.org/W2962896155","https://openalex.org/W2963073614","https://openalex.org/W2963470893","https://openalex.org/W2963684088","https://openalex.org/W4320013936","https://openalex.org/W6621378261","https://openalex.org/W6675380101","https://openalex.org/W6685352114","https://openalex.org/W6696934422","https://openalex.org/W6713645886","https://openalex.org/W6727340567","https://openalex.org/W6729966448","https://openalex.org/W6737196085","https://openalex.org/W7075637324"],"related_works":["https://openalex.org/W1975632186","https://openalex.org/W4298287631","https://openalex.org/W2953061907","https://openalex.org/W3027745756","https://openalex.org/W3205213561","https://openalex.org/W1847088711","https://openalex.org/W4225394202","https://openalex.org/W3036642985","https://openalex.org/W3032952384","https://openalex.org/W2531880140"],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"the":[3,11,40,96,101,105,126,133,147,169,179,187,196,202,208,216],"speech":[4,36,116,131],"synthesis":[5,37,174],"system":[6,38,52],"submitted":[7,210,220],"by":[8,104,138,153,178],"IFLYTEK":[9],"for":[10,27,75,198],"Blizzard":[12],"Machine":[13],"Learning":[14],"Challenge":[15],"2017-ES1.":[16],"Linguistic":[17],"and":[18,43,68,85,161],"acoustic":[19,44,66,107,135,181],"features":[20,45,136],"from":[21],"a":[22,35,56,69],"4hour":[23],"corpus":[24],"were":[25],"released":[26],"this":[28,110,139],"task.":[29],"Participants":[30],"are":[31,83,183,192],"expected":[32],"to":[33,79,94,113,125,145,186,195],"build":[34,80],"on":[39],"given":[41,100,137,168],"linguist":[42],"without":[46],"using":[47,132,156,166],"any":[48],"external":[49],"data.":[50],"Our":[51],"is":[53,93,144,205],"composed":[54],"of":[55,98,129,150,218],"long":[57],"short":[58],"term":[59],"memory":[60],"(LSTM)":[61],"recurrent":[62],"neural":[63],"network":[64,72],"(RNN)-based":[65],"model":[67,182],"generative":[70],"adversarial":[71],"(GAN)-based":[73],"post-filter":[74,82],"mel-cepstra.":[76],"Two":[77],"approaches":[78],"GAN-based":[81],"implemented":[84],"compared":[86],"in":[87,118,207],"our":[88,119,219],"experiments.":[89],"The":[90,141,212],"first":[91,184],"one":[92],"predict":[95],"residuals":[97],"mel-cepstra":[99,102,152,176],"predicted":[103,177],"LSTM-based":[106],"model.":[108],"However,":[109],"method":[111],"leads":[112],"unstable":[114],"synthetic":[115],"sounds":[117],"experiments,":[120],"which":[121,191],"may":[122],"be":[123],"due":[124],"poor":[127],"quality":[128],"analysis-synthesis":[130],"natural":[134,151],"corpus.":[140],"other":[142],"approach":[143,204],"ignore":[146],"detailed":[148],"components":[149],"dimension":[154],"reduction":[155],"principal":[157],"component":[158],"analysis":[159],"(PCA)":[160],"then":[162,193],"recover":[163],"them":[164],"back":[165],"GAN":[167,197],"main":[170,188],"PCA":[171,189],"components.":[172],"At":[173],"time,":[175],"RNN":[180],"projected":[185],"components,":[190],"sent":[194],"detail":[199],"recovering.":[200],"Finally,":[201],"second":[203],"used":[206],"final":[209],"system.":[211,221],"evaluation":[213],"results":[214],"show":[215],"effectiveness":[217]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}