{"id":"https://openalex.org/W2944384275","doi":"https://doi.org/10.1109/iscslp.2018.8706686","title":"An Analysis of Decoding for Attention-Based End-to-End Mandarin Speech Recognition","display_name":"An Analysis of Decoding for Attention-Based End-to-End Mandarin Speech Recognition","publication_year":2018,"publication_date":"2018-11-01","ids":{"openalex":"https://openalex.org/W2944384275","doi":"https://doi.org/10.1109/iscslp.2018.8706686","mag":"2944384275"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp.2018.8706686","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2018.8706686","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 11th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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/A5110582135","display_name":"Dongwei Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I4401726870","display_name":"Didi Chuxing (China)","ror":"https://ror.org/02ksqcf75","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726870"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Dongwei Jiang","raw_affiliation_strings":["AI Labs, Didi Chuxing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"AI Labs, Didi Chuxing, Beijing, China","institution_ids":["https://openalex.org/I4401726870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101808317","display_name":"Wei Zou","orcid":"https://orcid.org/0000-0003-4307-5355"},"institutions":[{"id":"https://openalex.org/I4401726870","display_name":"Didi Chuxing (China)","ror":"https://ror.org/02ksqcf75","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726870"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Zou","raw_affiliation_strings":["AI Labs, Didi Chuxing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"AI Labs, Didi Chuxing, Beijing, China","institution_ids":["https://openalex.org/I4401726870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041886705","display_name":"Shuaijiang Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I4401726870","display_name":"Didi Chuxing (China)","ror":"https://ror.org/02ksqcf75","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726870"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuaijiang Zhao","raw_affiliation_strings":["AI Labs, Didi Chuxing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"AI Labs, Didi Chuxing, Beijing, China","institution_ids":["https://openalex.org/I4401726870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018655903","display_name":"Guilin Yang","orcid":"https://orcid.org/0000-0001-6144-3401"},"institutions":[{"id":"https://openalex.org/I4401726870","display_name":"Didi Chuxing (China)","ror":"https://ror.org/02ksqcf75","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726870"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guilin Yang","raw_affiliation_strings":["AI Labs, Didi Chuxing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"AI Labs, Didi Chuxing, Beijing, China","institution_ids":["https://openalex.org/I4401726870"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081173423","display_name":"Xiangang Li","orcid":"https://orcid.org/0000-0002-7810-1077"},"institutions":[{"id":"https://openalex.org/I4401726870","display_name":"Didi Chuxing (China)","ror":"https://ror.org/02ksqcf75","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726870"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangang Li","raw_affiliation_strings":["AI Labs, Didi Chuxing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"AI Labs, Didi Chuxing, Beijing, China","institution_ids":["https://openalex.org/I4401726870"]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5110582135"],"corresponding_institution_ids":["https://openalex.org/I4401726870"],"apc_list":null,"apc_paid":null,"fwci":0.1629,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.62657953,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":93},"biblio":{"volume":null,"issue":null,"first_page":"384","last_page":"388"},"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/T10860","display_name":"Speech and Audio Processing","score":0.998199999332428,"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":0.9936000108718872,"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":0.8245327472686768},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7828528881072998},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.6834128499031067},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6716129779815674},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.6108908653259277},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.6024851202964783},{"id":"https://openalex.org/keywords/softmax-function","display_name":"Softmax function","score":0.5879412293434143},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5495624542236328},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5113122463226318},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4988367557525635},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.49745872616767883},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.4790452718734741},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.43915557861328125},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.42571690678596497},{"id":"https://openalex.org/keywords/syllable","display_name":"Syllable","score":0.4174741804599762},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.08542898297309875},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07450839877128601}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8245327472686768},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7828528881072998},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.6834128499031067},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6716129779815674},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.6108908653259277},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.6024851202964783},{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.5879412293434143},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5495624542236328},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5113122463226318},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4988367557525635},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.49745872616767883},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.4790452718734741},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.43915557861328125},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.42571690678596497},{"id":"https://openalex.org/C109089402","wikidata":"https://www.wikidata.org/wiki/Q8188","display_name":"Syllable","level":2,"score":0.4174741804599762},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.08542898297309875},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07450839877128601},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"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/iscslp.2018.8706686","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2018.8706686","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 11th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6399999856948853}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W38163879","https://openalex.org/W854541894","https://openalex.org/W1571745681","https://openalex.org/W1600744878","https://openalex.org/W1821462560","https://openalex.org/W1984541135","https://openalex.org/W2076063813","https://openalex.org/W2113411173","https://openalex.org/W2127141656","https://openalex.org/W2133564696","https://openalex.org/W2143612262","https://openalex.org/W2183341477","https://openalex.org/W2193413348","https://openalex.org/W2293634267","https://openalex.org/W2327501763","https://openalex.org/W2514969556","https://openalex.org/W2525778437","https://openalex.org/W2577366047","https://openalex.org/W2581377246","https://openalex.org/W2750499125","https://openalex.org/W2803399609","https://openalex.org/W2888226713","https://openalex.org/W2962778134","https://openalex.org/W2962826786","https://openalex.org/W2963211739","https://openalex.org/W2963240019","https://openalex.org/W2963260202","https://openalex.org/W2963373786","https://openalex.org/W2963850025","https://openalex.org/W2964308564","https://openalex.org/W4297798436","https://openalex.org/W6601528756","https://openalex.org/W6623517193","https://openalex.org/W6638523607","https://openalex.org/W6679434410","https://openalex.org/W6687566353","https://openalex.org/W6696934422","https://openalex.org/W6718379498","https://openalex.org/W6732447497","https://openalex.org/W6732696085","https://openalex.org/W6746574493","https://openalex.org/W6753776127"],"related_works":["https://openalex.org/W3107204728","https://openalex.org/W4287591324","https://openalex.org/W4226420367","https://openalex.org/W2980176872","https://openalex.org/W2222951281","https://openalex.org/W2272290179","https://openalex.org/W156219719","https://openalex.org/W2068412075","https://openalex.org/W27484908","https://openalex.org/W2268150819"],"abstract_inverted_index":{"Many":[0],"of":[1,19,43,148],"the":[2,57,64,67,109,132,146],"current":[3],"state-of-the-art":[4],"Mandarin":[5,83,114],"Large":[6],"Vocabulary":[7],"Continuous":[8],"Speech":[9],"Recognition":[10],"(LVCSR)":[11],"Systems":[12],"are":[13],"built":[14],"either":[15],"with":[16,30,35,63,95],"a":[17,96,138],"hybrid":[18],"Deep":[20],"Neural":[21,31],"Network":[22,32],"(DNN)":[23],"and":[24,69,79,118,124,159],"Hidden":[25],"Markov":[26],"Models":[27],"(HMM)":[28],"or":[29],"model":[33],"trained":[34,100],"Connectionist":[36],"Temporal":[37],"Classification":[38],"(CTC)":[39],"criterion.":[40],"In":[41],"both":[42],"these":[44],"models,":[45],"decoding":[46,110,133,149],"is":[47,76],"conducted":[48],"by":[49],"Weighted":[50],"Finite":[51],"State":[52],"Transducer":[53],"(WFST)":[54],"that":[55,144],"searches":[56],"word":[58,129],"sequence":[59],"which":[60],"matches":[61],"best":[62],"speech":[65,84],"given":[66],"acoustic":[68,121],"language":[70],"models.":[71],"Recently,":[72],"attention-based":[73,113],"end-to-end":[74,103],"method":[75,88],"becoming":[77],"more":[78,80],"popular":[81],"for":[82,112],"recognition.":[85],"This":[86],"new":[87],"advocates":[89],"replacing":[90],"complex":[91],"data":[92],"processing":[93],"pipelines":[94],"single":[97],"neural":[98],"network":[99],"in":[101],"an":[102],"fashion.In":[104],"this":[105],"paper,":[106],"we":[107],"investigate":[108],"process":[111],"models":[115],"using":[116],"syllable":[117],"character":[119],"as":[120],"modeling":[122],"units":[123],"discuss":[125],"how":[126],"to":[127],"combine":[128],"information":[130],"into":[131],"process.":[134],"We":[135],"also":[136],"conduct":[137],"detailed":[139],"analysis":[140],"on":[141],"various":[142],"factors":[143],"affect":[145],"performance":[147],"including":[150],"beam":[151],"size,":[152],"label":[153],"smoothing,":[154],"softmax":[155],"temperature,":[156],"attention":[157],"smoothing":[158],"coverage.":[160]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}