{"id":"https://openalex.org/W1506666725","doi":"https://doi.org/10.1109/chinasip.2015.7230354","title":"Improving HMM/DNN in ASR of under-resourced languages using probabilistic sampling","display_name":"Improving HMM/DNN in ASR of under-resourced languages using probabilistic sampling","publication_year":2015,"publication_date":"2015-07-01","ids":{"openalex":"https://openalex.org/W1506666725","doi":"https://doi.org/10.1109/chinasip.2015.7230354","mag":"1506666725"},"language":"en","primary_location":{"id":"doi:10.1109/chinasip.2015.7230354","is_oa":false,"landing_page_url":"https://doi.org/10.1109/chinasip.2015.7230354","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE China Summit and International Conference on Signal and Information Processing (ChinaSIP)","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/A5047784934","display_name":"Meixu Song","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/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Meixu Song","raw_affiliation_strings":["The Key Laboratory of Speech Acoustics and Content Understanding, Chinese Academy of Sciences, Beijing, China","The Key Laboratory of Speech Acoustics and Content Understanding  Chinese Academy of Sciences  Beijing 100190  China"],"affiliations":[{"raw_affiliation_string":"The Key Laboratory of Speech Acoustics and Content Understanding, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I19820366"]},{"raw_affiliation_string":"The Key Laboratory of Speech Acoustics and Content Understanding  Chinese Academy of Sciences  Beijing 100190  China","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100375543","display_name":"Qingqing Zhang","orcid":"https://orcid.org/0000-0002-1464-6203"},"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/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingqing Zhang","raw_affiliation_strings":["The Key Laboratory of Speech Acoustics and Content Understanding, Chinese Academy of Sciences, Beijing, China","The Key Laboratory of Speech Acoustics and Content Understanding  Chinese Academy of Sciences  Beijing 100190  China"],"affiliations":[{"raw_affiliation_string":"The Key Laboratory of Speech Acoustics and Content Understanding, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I19820366"]},{"raw_affiliation_string":"The Key Laboratory of Speech Acoustics and Content Understanding  Chinese Academy of Sciences  Beijing 100190  China","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111847664","display_name":"Jielin Pan","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/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jielin Pan","raw_affiliation_strings":["The Key Laboratory of Speech Acoustics and Content Understanding, Chinese Academy of Sciences, Beijing, China","The Key Laboratory of Speech Acoustics and Content Understanding  Chinese Academy of Sciences  Beijing 100190  China"],"affiliations":[{"raw_affiliation_string":"The Key Laboratory of Speech Acoustics and Content Understanding, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I19820366"]},{"raw_affiliation_string":"The Key Laboratory of Speech Acoustics and Content Understanding  Chinese Academy of Sciences  Beijing 100190  China","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100425112","display_name":"Yonghong Yan","orcid":"https://orcid.org/0000-0001-6907-5770"},"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/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yonghong Yan","raw_affiliation_strings":["The Key Laboratory of Speech Acoustics and Content Understanding, Chinese Academy of Sciences, Beijing, China","The Key Laboratory of Speech Acoustics and Content Understanding  Chinese Academy of Sciences  Beijing 100190  China"],"affiliations":[{"raw_affiliation_string":"The Key Laboratory of Speech Acoustics and Content Understanding, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I19820366"]},{"raw_affiliation_string":"The Key Laboratory of Speech Acoustics and Content Understanding  Chinese Academy of Sciences  Beijing 100190  China","institution_ids":["https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5047784934"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210099069"],"apc_list":null,"apc_paid":null,"fwci":0.8629,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.8122475,"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":"20","last_page":"24"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9986000061035156,"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/T12326","display_name":"Network Packet Processing and Optimization","score":0.9968000054359436,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/hidden-markov-model","display_name":"Hidden Markov model","score":0.8185802102088928},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7534880638122559},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.7074078321456909},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6308419704437256},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5453067421913147},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4684814214706421},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36148756742477417},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10970130562782288},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.06748205423355103}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8185802102088928},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7534880638122559},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.7074078321456909},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6308419704437256},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5453067421913147},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4684814214706421},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36148756742477417},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10970130562782288},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.06748205423355103}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/chinasip.2015.7230354","is_oa":false,"landing_page_url":"https://doi.org/10.1109/chinasip.2015.7230354","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE China Summit and International Conference on Signal and Information Processing (ChinaSIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/1","display_name":"No poverty","score":0.5400000214576721}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W97072897","https://openalex.org/W1500890010","https://openalex.org/W1554663460","https://openalex.org/W1574715085","https://openalex.org/W1978660892","https://openalex.org/W1994606281","https://openalex.org/W2025198378","https://openalex.org/W2025357764","https://openalex.org/W2064244481","https://openalex.org/W2091267617","https://openalex.org/W2106440210","https://openalex.org/W2107553890","https://openalex.org/W2153682659","https://openalex.org/W2160815625","https://openalex.org/W2164499211","https://openalex.org/W2394932179","https://openalex.org/W4234643200","https://openalex.org/W4388297464","https://openalex.org/W6603931906","https://openalex.org/W6634333142","https://openalex.org/W6649207683","https://openalex.org/W6999740765"],"related_works":["https://openalex.org/W2053269318","https://openalex.org/W2364370872","https://openalex.org/W2136763963","https://openalex.org/W2109705048","https://openalex.org/W2940588515","https://openalex.org/W1909151225","https://openalex.org/W1987783679","https://openalex.org/W2160030256","https://openalex.org/W4253235840","https://openalex.org/W3151937861"],"abstract_inverted_index":{"In":[0,22],"HMM/DNN":[1],"automatic":[2],"speech":[3],"recognition":[4],"(ASR)":[5],"systems,":[6],"the":[7,10,25,48,51,55,84,88,94,106,109,123,127,135],"DNNs":[8],"model":[9],"posterior":[11],"probabilities":[12],"for":[13,59],"triphone":[14,17],"states.":[15],"However,":[16],"states":[18,38,43],"are":[19],"unevenly":[20],"distributed.":[21],"this":[23,65],"situation,":[24],"training":[26,52],"algorithm":[27],"tends":[28],"to":[29,31,37,122],"converge":[30],"a":[32,69,80,113,139],"local":[33],"optimum":[34],"more":[35],"related":[36],"with":[39,44,64],"rich":[40],"data":[41,53],"than":[42],"poor":[45],"data.":[46],"Thus,":[47],"imbalance":[49],"of":[50,93],"decreases":[54],"ASR":[56,103],"performances,":[57],"especially":[58],"under-resourced":[60,102],"languages.":[61],"To":[62],"deal":[63],"issue,":[66],"we":[67],"explore":[68],"resampling":[70],"technique,":[71],"called":[72],"\u201cprobabilistic":[73],"sampling\u201d,":[74],"which":[75],"can":[76],"be":[77],"seen":[78],"as":[79,134],"linear":[81],"smoothing":[82],"between":[83],"original":[85],"sampling":[86,96],"and":[87,137],"uniform":[89],"sampling.":[90],"The":[91],"effectiveness":[92],"probabilistic":[95,107],"has":[97],"been":[98],"studied":[99],"in":[100],"two":[101],"experiments.":[104],"With":[105],"sampling,":[108],"first":[110],"experiment":[111,129],"got":[112],"6.3%":[114],"relative":[115,141],"phone":[116],"error":[117],"rate":[118],"(PER)":[119],"reduction":[120],"compared":[121],"conventional":[124],"DNN":[125,133],"baseline;":[126],"second":[128],"used":[130],"shared-hidden-layer":[131],"multilingual":[132],"baseline,":[136],"obtained":[138],"4.9%":[140],"PER":[142],"reduction.":[143]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}