{"id":"https://openalex.org/W2085377355","doi":"https://doi.org/10.1109/chinasip.2013.6625314","title":"Improving deep neural network acoustic models using unlabeled data","display_name":"Improving deep neural network acoustic models using unlabeled data","publication_year":2013,"publication_date":"2013-07-01","ids":{"openalex":"https://openalex.org/W2085377355","doi":"https://doi.org/10.1109/chinasip.2013.6625314","mag":"2085377355"},"language":"en","primary_location":{"id":"doi:10.1109/chinasip.2013.6625314","is_oa":false,"landing_page_url":"https://doi.org/10.1109/chinasip.2013.6625314","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE China Summit and International Conference on Signal and Information Processing","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/A5052057753","display_name":"Meng Cai","orcid":"https://orcid.org/0000-0002-0711-5949"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meng Cai","raw_affiliation_strings":["Tsinghua National Laboratory for Information Science and Technology, Department of Electronic Engineering, Tsinghua University, Beijing, China","Dept. of Electron. Eng., TsingHua Univ., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua National Laboratory for Information Science and Technology, Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Dept. of Electron. Eng., TsingHua Univ., Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100692904","display_name":"Wei-Qiang Zhang","orcid":"https://orcid.org/0000-0003-3841-1959"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei-Qiang Zhang","raw_affiliation_strings":["Tsinghua National Laboratory for Information Science and Technology, Department of Electronic Engineering, Tsinghua University, Beijing, China","Dept. of Electron. Eng., TsingHua Univ., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua National Laboratory for Information Science and Technology, Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Dept. of Electron. Eng., TsingHua Univ., Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100409741","display_name":"Jia Liu","orcid":"https://orcid.org/0000-0003-0383-0934"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jia Liu","raw_affiliation_strings":["Tsinghua National Laboratory for Information Science and Technology, Department of Electronic Engineering, Tsinghua University, Beijing, China","Dept. of Electron. Eng., TsingHua Univ., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua National Laboratory for Information Science and Technology, Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Dept. of Electron. Eng., TsingHua Univ., Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.6864,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.69511506,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"137","last_page":"141"},"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":0.9997000098228455,"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":0.9991999864578247,"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":0.774292528629303},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.7158160209655762},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6481682062149048},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5963172316551208},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5757217407226562},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5577241778373718},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.5570131540298462},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5243497490882874},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.5163887143135071},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4794248938560486},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.4493563175201416},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43800660967826843},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.4252725839614868},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3431699872016907},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08379483222961426}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.774292528629303},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.7158160209655762},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6481682062149048},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5963172316551208},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5757217407226562},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5577241778373718},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.5570131540298462},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5243497490882874},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.5163887143135071},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4794248938560486},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.4493563175201416},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43800660967826843},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.4252725839614868},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3431699872016907},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08379483222961426},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/chinasip.2013.6625314","is_oa":false,"landing_page_url":"https://doi.org/10.1109/chinasip.2013.6625314","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE China Summit and International Conference on Signal and Information Processing","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":32,"referenced_works":["https://openalex.org/W44815768","https://openalex.org/W137106866","https://openalex.org/W217970951","https://openalex.org/W1218987319","https://openalex.org/W1498436455","https://openalex.org/W1540578583","https://openalex.org/W1553004968","https://openalex.org/W1984541135","https://openalex.org/W1993882792","https://openalex.org/W1994126409","https://openalex.org/W2095168618","https://openalex.org/W2096635587","https://openalex.org/W2100495367","https://openalex.org/W2120480077","https://openalex.org/W2125964738","https://openalex.org/W2136922672","https://openalex.org/W2139622435","https://openalex.org/W2144792281","https://openalex.org/W2147768505","https://openalex.org/W2160815625","https://openalex.org/W2166637769","https://openalex.org/W2168013545","https://openalex.org/W2253807446","https://openalex.org/W2394932179","https://openalex.org/W2950789693","https://openalex.org/W6608710415","https://openalex.org/W6627792425","https://openalex.org/W6632321275","https://openalex.org/W6678242812","https://openalex.org/W6679053740","https://openalex.org/W6684683940","https://openalex.org/W6711962127"],"related_works":["https://openalex.org/W2153098279","https://openalex.org/W2061937230","https://openalex.org/W4245698648","https://openalex.org/W2405257913","https://openalex.org/W3133710586","https://openalex.org/W2125964738","https://openalex.org/W2098529290","https://openalex.org/W2026402306","https://openalex.org/W2189081180","https://openalex.org/W3045896262"],"abstract_inverted_index":{"The":[0],"Context-Dependent":[1],"Deep-Neural-Network":[2],"HMM,":[3],"or":[4],"CD-DNN-HMM,":[5],"is":[6],"a":[7,37,83,93],"powerful":[8],"acoustic":[9],"modeling":[10],"technique.":[11],"Its":[12],"training":[13,45],"process":[14],"typically":[15],"involves":[16],"unsupervised":[17],"pre-training":[18],"and":[19,58],"supervised":[20],"fine-tuning.":[21],"In":[22,47],"the":[23,28,44,70,101,122],"paper,":[24],"we":[25],"demonstrate":[26],"that":[27,98,114],"performance":[29,116],"of":[30,40,55,61,67,79,124],"DNNs":[31],"can":[32,118],"be":[33,119],"improved":[34],"by":[35,82,121],"utilizing":[36],"large":[38],"amount":[39],"unlabeled":[41,56,88,125],"data":[42,57,63],"in":[43],"procedure.":[46],"our":[48,110],"method,":[49],"CD-DNN-HMM":[50,84],"trained":[51,85],"using":[52,87],"309":[53],"hours":[54,60],"24":[59],"labeled":[62],"achieved":[64],"word-error":[65,77],"rate":[66,78,103],"23.7%":[68],"on":[69],"Hub5'00-SWB":[71],"phone-call":[72],"transcription":[73],"task,":[74],"compared":[75],"to":[76,104],"24.3%":[80],"obtained":[81,120],"without":[86],"data.":[89,126],"We":[90],"also":[91],"applied":[92],"priori":[94],"probability":[95],"smoothing":[96],"algorithm":[97],"further":[99],"reduced":[100],"error":[102],"23.2%.":[105],"On":[106],"RT03S-FSH":[107],"benchmark":[108],"corpus,":[109],"experimental":[111],"results":[112],"show":[113],"similar":[115],"gains":[117],"use":[123]},"counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}