{"id":"https://openalex.org/W1974979586","doi":"https://doi.org/10.1109/apsipa.2013.6694176","title":"Deep neural networks for syllable based acoustic modeling in Chinese speech recognition","display_name":"Deep neural networks for syllable based acoustic modeling in Chinese speech recognition","publication_year":2013,"publication_date":"2013-10-01","ids":{"openalex":"https://openalex.org/W1974979586","doi":"https://doi.org/10.1109/apsipa.2013.6694176","mag":"1974979586"},"language":"en","primary_location":{"id":"doi:10.1109/apsipa.2013.6694176","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipa.2013.6694176","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference","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/A5081173423","display_name":"Xiangang Li","orcid":"https://orcid.org/0000-0002-7810-1077"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiangang Li","raw_affiliation_strings":["Speech and Hearing Research Center, Peking University, Beijing, China","Key Lab. of Machine Perception (Minist. of Educ.), Peking Univ., Beijing, China#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech and Hearing Research Center, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Key Lab. of Machine Perception (Minist. of Educ.), Peking Univ., Beijing, China#TAB#","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009558909","display_name":"Caifu Hong","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Caifu Hong","raw_affiliation_strings":["Speech and Hearing Research Center, Peking University, Beijing, China","Key Lab. of Machine Perception (Minist. of Educ.), Peking Univ., Beijing, China#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech and Hearing Research Center, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Key Lab. of Machine Perception (Minist. of Educ.), Peking Univ., Beijing, China#TAB#","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101909361","display_name":"Yuning Yang","orcid":"https://orcid.org/0000-0003-4503-4784"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuning Yang","raw_affiliation_strings":["Speech and Hearing Research Center, Peking University, Beijing, China","Key Lab. of Machine Perception (Minist. of Educ.), Peking Univ., Beijing, China#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech and Hearing Research Center, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Key Lab. of Machine Perception (Minist. of Educ.), Peking Univ., Beijing, China#TAB#","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084685506","display_name":"Xihong Wu","orcid":"https://orcid.org/0009-0004-5236-7469"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xihong Wu","raw_affiliation_strings":["Speech and Hearing Research Center, Peking University, Beijing, China","Key Lab. of Machine Perception (Minist. of Educ.), Peking Univ., Beijing, China#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech and Hearing Research Center, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Key Lab. of Machine Perception (Minist. of Educ.), Peking Univ., Beijing, China#TAB#","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5081173423"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":0.9883,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.8155418,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"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/T11309","display_name":"Music and Audio Processing","score":0.9984999895095825,"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/T10860","display_name":"Speech and Audio Processing","score":0.9977999925613403,"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":0.79043048620224},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7792404890060425},{"id":"https://openalex.org/keywords/syllable","display_name":"Syllable","score":0.7060952186584473},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.6028699278831482},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5698336958885193},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.5370928049087524},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5172308087348938},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5102570056915283},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.47210875153541565},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45989611744880676},{"id":"https://openalex.org/keywords/decision-tree","display_name":"Decision tree","score":0.45886585116386414},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4409027099609375},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.38104185461997986},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3464326858520508},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1268196702003479}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.79043048620224},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7792404890060425},{"id":"https://openalex.org/C109089402","wikidata":"https://www.wikidata.org/wiki/Q8188","display_name":"Syllable","level":2,"score":0.7060952186584473},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.6028699278831482},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5698336958885193},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.5370928049087524},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5172308087348938},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5102570056915283},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.47210875153541565},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45989611744880676},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.45886585116386414},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4409027099609375},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.38104185461997986},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3464326858520508},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1268196702003479},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/apsipa.2013.6694176","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipa.2013.6694176","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.961.6634","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.961.6634","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.apsipa.org/proceedings_2013/papers/207_PID2932703.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7699999809265137,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W44815768","https://openalex.org/W88081813","https://openalex.org/W217970951","https://openalex.org/W299739017","https://openalex.org/W1534536260","https://openalex.org/W1571745681","https://openalex.org/W1860547055","https://openalex.org/W1993882792","https://openalex.org/W2147768505","https://openalex.org/W2160815625","https://openalex.org/W2180711486","https://openalex.org/W2184045248","https://openalex.org/W2888226713","https://openalex.org/W4231109964","https://openalex.org/W4285719527","https://openalex.org/W6601785968","https://openalex.org/W6608710415","https://openalex.org/W6753776127"],"related_works":["https://openalex.org/W2053269318","https://openalex.org/W2121652828","https://openalex.org/W2992378684","https://openalex.org/W2964829415","https://openalex.org/W642007152","https://openalex.org/W2122233706","https://openalex.org/W2105439218","https://openalex.org/W3143423642","https://openalex.org/W2131711534","https://openalex.org/W2341426843"],"abstract_inverted_index":{"Recently,":[0],"the":[1,22,46,53,83,96,107,113,132],"deep":[2],"neural":[3],"networks":[4],"(DNNs)":[5],"based":[6,29,57,86,91,110],"acoustic":[7,30,97],"modeling":[8,31,58,69,111,116],"methods":[9],"have":[10],"been":[11],"successfully":[12],"applied":[13],"to":[14,134],"many":[15,62],"speech":[16,35],"recognition":[17,36],"tasks.":[18],"This":[19],"paper":[20],"reports":[21],"work":[23],"about":[24,65],"applying":[25],"DNNs":[26,90,119],"for":[27,95,123,138],"syllable":[28,42,56,115],"in":[32,49],"Chinese":[33,139],"automatic":[34],"(ASR).":[37],"Compared":[38],"with":[39,106],"initial/finals":[40],"(IFs),":[41],"can":[43],"implicitly":[44],"model":[45,98],"intra-syllable":[47],"variations":[48],"better":[50,136],"accuracy.":[51],"However,":[52],"context":[54],"dependent":[55],"set":[59],"holds":[60],"too":[61],"units,":[63],"bringing":[64],"heavy":[66],"problems":[67],"on":[68],"and":[70,89],"decoding":[71,78],"implementation.":[72],"In":[73],"this":[74],"paper,":[75],"a":[76],"WFST":[77],"framework":[79],"is":[80,120],"applied.":[81],"Moreover,":[82],"decision":[84],"tree":[85],"state":[87],"tying":[88],"models":[92],"are":[93],"discussed":[94],"training.":[99],"The":[100],"experimental":[101],"results":[102],"show":[103],"that":[104,129],"compared":[105],"traditional":[108],"IFs":[109],"method,":[112],"proposed":[114],"method":[117],"using":[118],"more":[121],"robust":[122],"data":[124],"sparsity":[125],"problem,":[126],"which":[127],"indicates":[128],"it":[130],"has":[131],"potential":[133],"obtain":[135],"performance":[137],"ASR.":[140]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}