{"id":"https://openalex.org/W2407648438","doi":"https://doi.org/10.21437/interspeech.2015-717","title":"Towards end-to-end speech recognition for Chinese Mandarin using long short-term memory recurrent neural networks","display_name":"Towards end-to-end speech recognition for Chinese Mandarin using long short-term memory recurrent neural networks","publication_year":2015,"publication_date":"2015-09-06","ids":{"openalex":"https://openalex.org/W2407648438","doi":"https://doi.org/10.21437/interspeech.2015-717","mag":"2407648438"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2015-717","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-717","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","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/A5028530320","display_name":"Jie Li","orcid":"https://orcid.org/0000-0002-7075-4145"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Jie Li","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108051603","display_name":"Heng Zhang","orcid":"https://orcid.org/0000-0002-2836-2965"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Heng Zhang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100844780","display_name":"Xinyuan Cai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xinyuan Cai","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5108642431","display_name":"Bo Xu","orcid":"https://orcid.org/0000-0002-1111-1529"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bo Xu","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5028530320"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.766,"has_fulltext":false,"cited_by_count":32,"citation_normalized_percentile":{"value":0.97359841,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3615","last_page":"3619"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9965000152587891,"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":0.9961000084877014,"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":0.8190721273422241},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7325477600097656},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.7320454120635986},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.7083451747894287},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.6601330041885376},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.6295891404151917},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5225253105163574},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5080246925354004},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.499941349029541},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4845229983329773},{"id":"https://openalex.org/keywords/long-short-term-memory","display_name":"Long short term memory","score":0.4561946988105774},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.44372352957725525},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.08061888813972473},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08013385534286499}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8190721273422241},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7325477600097656},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.7320454120635986},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.7083451747894287},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6601330041885376},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.6295891404151917},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5225253105163574},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5080246925354004},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.499941349029541},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4845229983329773},{"id":"https://openalex.org/C133488467","wikidata":"https://www.wikidata.org/wiki/Q6673524","display_name":"Long short term memory","level":4,"score":0.4561946988105774},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.44372352957725525},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.08061888813972473},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08013385534286499},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2015-717","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-717","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6700000166893005}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1499864241","https://openalex.org/W1710082047","https://openalex.org/W1987238397","https://openalex.org/W2057653135","https://openalex.org/W2087402357","https://openalex.org/W2102113734","https://openalex.org/W2119615570","https://openalex.org/W2125234026","https://openalex.org/W2127141656","https://openalex.org/W2131342762","https://openalex.org/W2143612262","https://openalex.org/W2144499799","https://openalex.org/W2147768505","https://openalex.org/W2160306971","https://openalex.org/W2160815625","https://openalex.org/W2293634267","https://openalex.org/W2403195671"],"related_works":["https://openalex.org/W2990005675","https://openalex.org/W2374317326","https://openalex.org/W1603321096","https://openalex.org/W2394766824","https://openalex.org/W2078713291","https://openalex.org/W2361574037","https://openalex.org/W2386292991","https://openalex.org/W2364440891","https://openalex.org/W2916997151","https://openalex.org/W2949174760"],"abstract_inverted_index":{"End-to-end":[0],"speech":[1,44,164],"recognition":[2,45,165],"systems":[3],"have":[4],"been":[5],"successfully":[6],"designed":[7],"for":[8],"English.":[9],"Taking":[10],"into":[11],"account":[12],"the":[13,68,86,97,116,141,158,162],"distinctive":[14],"characteristics":[15],"between":[16],"Chinese":[17,43,76,155],"Mandarin":[18],"and":[19,67,104,111,130],"English,":[20],"it":[21,108,150],"is":[22,53,80,102,151],"worthy":[23],"to":[24,29,33,40,106,153],"do":[25],"some":[26],"additional":[27],"work":[28],"transfer":[30],"these":[31,134],"approaches":[32],"Chinese.":[34],"In":[35],"this":[36],"paper,":[37],"we":[38],"attempt":[39],"build":[41],"a":[42,56],"system":[46,52],"using":[47,127],"end-to-end":[48],"learning":[49],"method.":[50],"The":[51,75],"based":[54],"on":[55],"combination":[57],"of":[58,143],"deep":[59],"Long":[60],"Short-Term":[61],"Memory":[62],"Projected":[63],"(LSTMP)":[64],"network":[65,129],"architecture":[66],"Connectionist":[69],"Temporal":[70],"Classification":[71],"objective":[72],"function":[73],"(CTC).":[74],"characters":[77,156],"(the":[78],"number":[79],"about":[81],"6,000)":[82],"are":[83,121,136],"used":[84],"as":[85,138,140,157],"output":[87,159],"labels":[88],"directly.":[89],"To":[90],"integrate":[91],"language":[92,131],"model":[93],"information":[94],"during":[95],"decoding,":[96],"CTC":[98],"Beam":[99],"Search":[100],"method":[101],"adopted":[103],"optimized":[105],"make":[107],"more":[109,112],"effective":[110],"efficient.":[113],"We":[114],"present":[115],"first-pass":[117],"decoding":[118,124],"results":[119,135],"which":[120],"obtained":[122],"by":[123],"from":[125],"scratch":[126],"CTC-trained":[128],"model.":[132],"Although":[133],"not":[137],"good":[139],"performance":[142],"DNN-HMMs":[144],"hybrid":[145],"system,":[146],"they":[147],"indicate":[148],"that":[149],"feasible":[152],"choose":[154],"alphabet":[160],"in":[161],"end-toend":[163],"system.":[166]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":9},{"year":2015,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}