{"id":"https://openalex.org/W2963236196","doi":"https://doi.org/10.21437/interspeech.2018-1086","title":"Extending Recurrent Neural Aligner for Streaming End-to-End Speech Recognition in Mandarin","display_name":"Extending Recurrent Neural Aligner for Streaming End-to-End Speech Recognition in Mandarin","publication_year":2018,"publication_date":"2018-08-28","ids":{"openalex":"https://openalex.org/W2963236196","doi":"https://doi.org/10.21437/interspeech.2018-1086","mag":"2963236196"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2018-1086","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1086","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/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":"funder","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"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Linhao Dong","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, China","University of Chinese Academy of Sciences, China"],"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101400153","display_name":"Shiyu Zhou","orcid":"https://orcid.org/0000-0002-6889-0316"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"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"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiyu Zhou","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, China","University of Chinese Academy of Sciences, China"],"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100344294","display_name":"Wei Chen","orcid":"https://orcid.org/0000-0001-5090-9915"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Chen","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, China"],"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210112150","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":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Xu","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, China"],"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5000236213"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150","https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":2.606,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.92219531,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"816","last_page":"820"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9957000017166138,"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":0.993399977684021,"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":0.7435581088066101},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6899571418762207},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.6845659613609314},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.5222262144088745},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5051758885383606},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3847629129886627},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3015231192111969},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08551910519599915}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7435581088066101},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6899571418762207},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.6845659613609314},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.5222262144088745},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5051758885383606},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3847629129886627},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3015231192111969},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08551910519599915},{"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.2018-1086","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1086","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":[{"score":0.44999998807907104,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1485009520","https://openalex.org/W1526236009","https://openalex.org/W1828163288","https://openalex.org/W2112796928","https://openalex.org/W2131774270","https://openalex.org/W2178654303","https://openalex.org/W2193413348","https://openalex.org/W2327501763","https://openalex.org/W2395416438","https://openalex.org/W2514741789","https://openalex.org/W2530876040","https://openalex.org/W2567070169","https://openalex.org/W2577366047","https://openalex.org/W2605141709","https://openalex.org/W2627092829","https://openalex.org/W2746192915","https://openalex.org/W2963240019","https://openalex.org/W3173163413","https://openalex.org/W4297798436","https://openalex.org/W4300428005","https://openalex.org/W4301368689","https://openalex.org/W4327845728","https://openalex.org/W4394666973"],"related_works":["https://openalex.org/W2374317326","https://openalex.org/W2990005675","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/W2393726922","https://openalex.org/W2578422401"],"abstract_inverted_index":{"End-to-end":[0],"models":[1],"have":[2],"been":[3,40],"showing":[4],"superiority":[5],"in":[6,76],"Automatic":[7],"Speech":[8],"Recognition":[9],"(ASR).At":[10],"the":[11,14,72,85,89,98,106,146],"same":[12],"time,":[13],"capacity":[15],"of":[16,74],"streaming":[17],"recognition":[18,123],"has":[19,39],"become":[20],"a":[21,94,102,114],"growing":[22],"requirement":[23],"for":[24],"end-to-end":[25],"models.Following":[26],"these":[27],"trends,":[28],"an":[29],"encoder-decoder":[30],"recurrent":[31],"neural":[32],"network":[33],"called":[34],"Recurrent":[35],"Neural":[36],"Aligner":[37],"(RNA)":[38],"freshly":[41],"proposed":[42],"and":[43,62,79,92,109],"shown":[44],"its":[45],"competitiveness":[46],"on":[47,145],"two":[48,117],"English":[49],"ASR":[50],"tasks.However,":[51],"it":[52,131],"is":[53,139],"not":[54],"clear":[55],"if":[56],"RNA":[57,75],"can":[58],"be":[59],"further":[60],"improved":[61],"applied":[63],"to":[64,104,141],"other":[65],"spoken":[66],"language.In":[67],"this":[68],"work,":[69],"we":[70,87,100],"explore":[71],"applicability":[73],"Mandarin":[77,118],"Chinese":[78,119],"present":[80],"four":[81],"effective":[82],"extensions:":[83],"In":[84],"encoder,":[86],"redesign":[88],"temporal":[90],"downsampling":[91],"introduce":[93],"powerful":[95],"convolutional":[96],"structure.In":[97],"decoder,":[99],"utilize":[101],"regularizer":[103],"smooth":[105],"output":[107],"distribution":[108],"conduct":[110],"joint":[111],"training":[112],"with":[113],"language":[115],"model.On":[116],"conversational":[120],"telephone":[121],"speech":[122],"(MTS)":[124],"datasets,":[125],"our":[126],"Extended-RNA":[127],"obtains":[128],"promising":[129],"performance.Particularly,":[130],"achieves":[132],"27.7%":[133],"character":[134],"error":[135],"rate":[136],"(CER),":[137],"which":[138],"superior":[140],"current":[142],"state-of-the-art":[143],"result":[144],"popular":[147],"HKUST":[148],"task.":[149]},"counts_by_year":[{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}