{"id":"https://openalex.org/W2962778134","doi":"https://doi.org/10.21437/interspeech.2018-1107","title":"Syllable-Based Sequence-to-Sequence Speech Recognition with the Transformer in Mandarin Chinese","display_name":"Syllable-Based Sequence-to-Sequence Speech Recognition with the Transformer in Mandarin Chinese","publication_year":2018,"publication_date":"2018-08-28","ids":{"openalex":"https://openalex.org/W2962778134","doi":"https://doi.org/10.21437/interspeech.2018-1107","mag":"2962778134"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2018-1107","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1107","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"},"type":"article","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/A5101400153","display_name":"Shiyu Zhou","orcid":"https://orcid.org/0000-0002-6889-0316"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shiyu Zhou","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences","University of Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000236213","display_name":"Linhao Dong","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linhao Dong","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences","University of Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102732438","display_name":"Shuang Xu","orcid":"https://orcid.org/0000-0003-1804-4012"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuang Xu","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108642431","display_name":"Bo Xu","orcid":"https://orcid.org/0000-0002-1111-1529"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Xu","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101400153"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":10.2617,"has_fulltext":false,"cited_by_count":102,"citation_normalized_percentile":{"value":0.98468825,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"791","last_page":"795"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9952999949455261,"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":0.9754999876022339,"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/mandarin-chinese","display_name":"Mandarin Chinese","score":0.8583760857582092},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6851240396499634},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6686145067214966},{"id":"https://openalex.org/keywords/syllable","display_name":"Syllable","score":0.639647901058197},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6280385255813599},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.6232492327690125},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.436207115650177},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3766634464263916},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2245941162109375},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14384916424751282},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.09393352270126343},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.08944669365882874}],"concepts":[{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.8583760857582092},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6851240396499634},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6686145067214966},{"id":"https://openalex.org/C109089402","wikidata":"https://www.wikidata.org/wiki/Q8188","display_name":"Syllable","level":2,"score":0.639647901058197},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6280385255813599},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6232492327690125},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.436207115650177},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3766634464263916},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2245941162109375},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14384916424751282},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.09393352270126343},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.08944669365882874},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"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.2018-1107","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1107","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5299999713897705}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1489125746","https://openalex.org/W1522301498","https://openalex.org/W1526236009","https://openalex.org/W1553004968","https://openalex.org/W1855892484","https://openalex.org/W2109886035","https://openalex.org/W2167200294","https://openalex.org/W2183341477","https://openalex.org/W2271840356","https://openalex.org/W2513938599","https://openalex.org/W2514969556","https://openalex.org/W2515801922","https://openalex.org/W2530876040","https://openalex.org/W2627092829","https://openalex.org/W2749514303","https://openalex.org/W2750499125","https://openalex.org/W2786031273","https://openalex.org/W2888226713","https://openalex.org/W2963240019","https://openalex.org/W3173163413","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2094188777","https://openalex.org/W342262962","https://openalex.org/W2399404538","https://openalex.org/W3214626309","https://openalex.org/W2384978429","https://openalex.org/W2592735450","https://openalex.org/W202627859","https://openalex.org/W2147532497","https://openalex.org/W1995315771","https://openalex.org/W1548541242"],"abstract_inverted_index":{"Sequence-to-sequence":[0],"attention-based":[1,35,79],"models":[2],"have":[3],"recently":[4],"shown":[5],"very":[6],"promising":[7],"results":[8],"on":[9,39,52,71,81,125],"automatic":[10],"speech":[11,68],"recognition":[12],"(ASR)":[13],"tasks,":[14],"which":[15,151],"integrate":[16],"an":[17],"acoustic,":[18],"pronunciation":[19],"and":[20,69,94,119,142],"language":[21],"model":[22,36,80,93,99,132],"into":[23,122],"a":[24,32,47,88,106,144],"single":[25],"neural":[26,53],"network.In":[27],"these":[28],"models,":[29],"the":[30,58,62,74,101,111,134,155,161],"Transformer,":[31,63],"new":[33,48],"sequence-to-sequence":[34,78],"relying":[37],"entirely":[38],"self-attention":[40],"without":[41],"using":[42],"RNNs":[43],"or":[44],"convolutions,":[45],"achieves":[46,143],"single-model":[49],"state-of-the-art":[50,156],"BLEU":[51],"machine":[54],"translation":[55],"(NMT)":[56],"tasks.Since":[57],"outstanding":[59],"performance":[60],"of":[61,77,149,158],"we":[64,86],"extend":[65],"it":[66,72],"to":[67,154],"concentrate":[70],"as":[73],"basic":[75],"architecture":[76],"Mandarin":[82,104],"Chinese":[83],"ASR":[84],"tasks.Furthermore,":[85],"investigate":[87],"comparison":[89],"between":[90],"syllable":[91,120,130],"based":[92,98,131,140,164],"context-independent":[95],"phoneme":[96],"(CI-phoneme)":[97],"with":[100,110,133],"Transformer":[102,112,135],"in":[103],"Chinese.Additionally,":[105],"greedy":[107],"cascading":[108],"decoder":[109],"is":[113,152],"proposed":[114],"for":[115],"mapping":[116],"CI-phoneme":[117,139],"sequences":[118,121],"word":[123],"sequences.Experiments":[124],"HKUST":[126],"datasets":[127],"demonstrate":[128],"that":[129],"performs":[136],"better":[137],"than":[138],"counterpart,":[141],"character":[145],"error":[146],"rate":[147],"(CER)":[148],"28.77%,":[150],"competitive":[153],"CER":[157],"28.0%":[159],"by":[160],"joint":[162],"CTC-attention":[163],"encoder-decoder":[165],"network.":[166]},"counts_by_year":[{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":15},{"year":2021,"cited_by_count":20},{"year":2020,"cited_by_count":18},{"year":2019,"cited_by_count":22},{"year":2018,"cited_by_count":3}],"updated_date":"2026-02-15T05:58:04.055770","created_date":"2025-10-10T00:00:00"}