{"id":"https://openalex.org/W2787078570","doi":"https://doi.org/10.1109/apsipa.2017.8282215","title":"Tibetan-Mandarin bilingual speech recognition based on end-to-end framework","display_name":"Tibetan-Mandarin bilingual speech recognition based on end-to-end framework","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2787078570","doi":"https://doi.org/10.1109/apsipa.2017.8282215","mag":"2787078570"},"language":"en","primary_location":{"id":"doi:10.1109/apsipa.2017.8282215","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipa.2017.8282215","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/A5053863846","display_name":"Qingnan Wang","orcid":"https://orcid.org/0000-0002-4373-8000"},"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":"Qingnan Wang","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038369085","display_name":"Wu Guo","orcid":"https://orcid.org/0000-0002-3779-7944"},"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":"Wu Guo","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003098301","display_name":"Peixin Chen","orcid":"https://orcid.org/0000-0003-1308-8016"},"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":"Peixin Chen","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100381758","display_name":"Yan Song","orcid":"https://orcid.org/0000-0002-5668-9068"},"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":"Yan Song","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1214","last_page":"1217"},"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/T10860","display_name":"Speech and Audio Processing","score":0.995199978351593,"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/T11309","display_name":"Music and Audio Processing","score":0.991100013256073,"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/hidden-markov-model","display_name":"Hidden Markov model","score":0.8410634994506836},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.7911036014556885},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7840877771377563},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7503678798675537},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.6188571453094482},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5306932926177979},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47767290472984314},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.4287046790122986},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3555091619491577},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.33853209018707275},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.15012431144714355},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14569911360740662}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8410634994506836},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.7911036014556885},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7840877771377563},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7503678798675537},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.6188571453094482},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5306932926177979},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47767290472984314},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.4287046790122986},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3555091619491577},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.33853209018707275},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.15012431144714355},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14569911360740662},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipa.2017.8282215","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipa.2017.8282215","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W47568227","https://openalex.org/W73572011","https://openalex.org/W625641071","https://openalex.org/W1218987319","https://openalex.org/W1518281544","https://openalex.org/W1533416326","https://openalex.org/W1846073453","https://openalex.org/W2005708641","https://openalex.org/W2033436836","https://openalex.org/W2063224314","https://openalex.org/W2096672142","https://openalex.org/W2102113734","https://openalex.org/W2111306781","https://openalex.org/W2127141656","https://openalex.org/W2143612262","https://openalex.org/W2147768505","https://openalex.org/W2160815625","https://openalex.org/W2293634267","https://openalex.org/W2407648438","https://openalex.org/W2963211739","https://openalex.org/W6601939441","https://openalex.org/W6674389704","https://openalex.org/W6675365184","https://openalex.org/W6696934422"],"related_works":["https://openalex.org/W2990005675","https://openalex.org/W2374317326","https://openalex.org/W2136763963","https://openalex.org/W2109705048","https://openalex.org/W2940588515","https://openalex.org/W1909151225","https://openalex.org/W1987783679","https://openalex.org/W2160030256","https://openalex.org/W4253235840","https://openalex.org/W3151937861"],"abstract_inverted_index":{"Tibetan-Mandarin":[0,153],"bilingual":[1,33,134],"speech":[2],"recognition":[3],"is":[4,11,23,56,81,130],"addressed":[5],"in":[6,37,87],"this":[7,60,102],"paper.":[8],"Because":[9],"there":[10],"a":[12,27],"great":[13],"difference":[14],"between":[15],"the":[16,32,38,64,67,72,75,114,121,133,137,150,162],"phoneme":[17,29],"sets":[18],"of":[19,71,78,136],"these":[20],"languages,":[21],"it":[22],"difficult":[24],"to":[25,58,100,132,140],"find":[26],"universal":[28],"set":[30],"for":[31],"acoustic":[34],"model":[35,42,79,89,106],"(AM)":[36],"conventional":[39],"hidden":[40],"Markov":[41],"(HMM)":[43],"framework.":[44],"The":[45,110,144],"end-to-end":[46],"framework":[47],"based":[48],"on":[49,149],"connectionist":[50],"temporal":[51],"classification":[52],"(CTC)":[53],"loss":[54],"function":[55],"proposed":[57,163],"solve":[59],"problem":[61,77],"by":[62,160],"using":[63,161],"character":[65],"as":[66,120],"modeling":[68],"unit":[69],"instead":[70],"phoneme.":[73],"However,":[74],"sparseness":[76],"units":[80,107],"an":[82,126],"intractable":[83],"and":[84,113],"ineluctable":[85],"fact":[86],"CTC":[88,122],"training,":[90],"particularly":[91],"under":[92],"low-resource":[93],"conditions.":[94],"This":[95],"paper":[96],"explores":[97],"two":[98],"methods":[99],"address":[101],"problem.":[103],"First,":[104],"different":[105],"are":[108,118,146],"selected.":[109],"Tibetan":[111],"characters":[112],"Mandarin":[115,142],"non-tonal":[116],"syllables":[117],"used":[119],"output":[123],"units.":[124],"Second,":[125],"adding":[127],"noise":[128],"algorithm":[129],"applied":[131],"part":[135],"training":[138],"corpus":[139],"augment":[141],"speech.":[143],"experiments":[145],"carried":[147],"out":[148],"hybrid":[151],"IFLYTEK":[152],"corpus.":[154],"Obvious":[155],"improvements":[156],"can":[157],"be":[158],"observed":[159],"methods.":[164]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}