{"id":"https://openalex.org/W2911850586","doi":"https://doi.org/10.1109/ialp.2018.8629237","title":"Research on Transfer Learning for Khalkha Mongolian Speech Recognition Based on TDNN","display_name":"Research on Transfer Learning for Khalkha Mongolian Speech Recognition Based on TDNN","publication_year":2018,"publication_date":"2018-11-01","ids":{"openalex":"https://openalex.org/W2911850586","doi":"https://doi.org/10.1109/ialp.2018.8629237","mag":"2911850586"},"language":"en","primary_location":{"id":"doi:10.1109/ialp.2018.8629237","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ialp.2018.8629237","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 International Conference on Asian Language Processing (IALP)","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/A5035725108","display_name":"Linyan Shi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Linyan Shi","raw_affiliation_strings":["College of Computer Science, Inner Mongolian Key Laboratory of Mongolian Information Processing Technology, Hohhot, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science, Inner Mongolian Key Laboratory of Mongolian Information Processing Technology, Hohhot, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014372166","display_name":"Feilong Bao","orcid":"https://orcid.org/0000-0001-7312-1629"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feilong Bao","raw_affiliation_strings":["College of Computer Science, Inner Mongolian Key Laboratory of Mongolian Information Processing Technology, Hohhot, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science, Inner Mongolian Key Laboratory of Mongolian Information Processing Technology, Hohhot, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008226894","display_name":"Yonghe Wang","orcid":"https://orcid.org/0000-0003-1647-1539"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yonghe Wang","raw_affiliation_strings":["College of Computer Science, Inner Mongolian Key Laboratory of Mongolian Information Processing Technology, Hohhot, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science, Inner Mongolian Key Laboratory of Mongolian Information Processing Technology, Hohhot, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076174513","display_name":"Guanglai Gao","orcid":"https://orcid.org/0009-0005-5513-1192"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guanglai Gao","raw_affiliation_strings":["College of Computer Science, Inner Mongolian Key Laboratory of Mongolian Information Processing Technology, Hohhot, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science, Inner Mongolian Key Laboratory of Mongolian Information Processing Technology, Hohhot, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"85","last_page":"89"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9968000054359436,"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":0.9940999746322632,"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":0.8218117952346802},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7215368747711182},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.7182793617248535},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6547123193740845},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5744563341140747},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5423402190208435},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.502565860748291},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4963114857673645},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4700027108192444},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.4360068142414093},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.43468180298805237},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.42546606063842773},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.42494139075279236},{"id":"https://openalex.org/keywords/time-domain","display_name":"Time domain","score":0.4143100082874298},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3545186221599579},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35257917642593384},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.06156438589096069}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8218117952346802},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7215368747711182},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.7182793617248535},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6547123193740845},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5744563341140747},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5423402190208435},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.502565860748291},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4963114857673645},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4700027108192444},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4360068142414093},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.43468180298805237},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.42546606063842773},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.42494139075279236},{"id":"https://openalex.org/C103824480","wikidata":"https://www.wikidata.org/wiki/Q185889","display_name":"Time domain","level":2,"score":0.4143100082874298},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3545186221599579},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35257917642593384},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.06156438589096069},{"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/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ialp.2018.8629237","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ialp.2018.8629237","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 International Conference on Asian Language Processing (IALP)","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":21,"referenced_works":["https://openalex.org/W28953113","https://openalex.org/W1524333225","https://openalex.org/W1585230382","https://openalex.org/W2106652354","https://openalex.org/W2117671523","https://openalex.org/W2127982613","https://openalex.org/W2131042651","https://openalex.org/W2149933564","https://openalex.org/W2171698314","https://openalex.org/W2402146185","https://openalex.org/W2514741789","https://openalex.org/W2533125211","https://openalex.org/W2559311710","https://openalex.org/W2600174029","https://openalex.org/W2746930212","https://openalex.org/W2790783922","https://openalex.org/W4299518610","https://openalex.org/W6679446866","https://openalex.org/W6682132143","https://openalex.org/W6735985974","https://openalex.org/W6749025659"],"related_works":["https://openalex.org/W3201126466","https://openalex.org/W3171384686","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":{"Automated":[0],"speech":[1,121,179],"recognition(ASR)incorporating":[2],"Neural":[3],"Networks":[4],"with":[5,35,93,118,150,175],"Hidden":[6],"Markov":[7],"Models":[8],"(NNs/HMMs)have":[9],"achieved":[10],"the":[11,73,86,94,98,102,114,136,142,146,158,161,176],"state-of-the-art":[12],"in":[13,33,58],"various":[14],"benchmarks.":[15],"Most":[16],"of":[17,23,75,104,135,160,166],"them":[18],"use":[19],"a":[20],"large":[21],"amount":[22],"training":[24],"data.":[25],"However,":[26],"ASR":[27,56,78,107],"research":[28],"is":[29,89,169],"still":[30],"quite":[31],"difficult":[32],"languages":[34],"limited":[36],"resources,":[37],"such":[38],"as":[39,97,152],"Khalkha":[40,76,105,130,178],"Mongolian.":[41],"Transfer":[42],"learning":[43],"methods":[44,117],"have":[45],"been":[46],"shown":[47],"to":[48,54,71,91,100],"be":[49],"effective":[50],"utilizing":[51],"out-of-domain":[52,119],"data":[53],"improve":[55,72],"performance":[57,74,159],"similar":[59],"data-scarce.":[60],"In":[61],"this":[62],"paper,":[63],"we":[64],"investigate":[65],"two":[66],"different":[67],"weight":[68,115],"transfer":[69,108,116],"approaches":[70],"Mongolian":[77,106],"based":[79],"on":[80,129],"Lattice-free":[81],"Maximum":[82],"Mutual":[83],"Information(LF-MMI).":[84],"Moreover,":[85],"i-vector":[87,147],"feature":[88,96],"used":[90],"combine":[92],"MFCCs":[95,151],"input":[99,153],"validate":[101],"effectiveness":[103],"models.":[109],"Experimental":[110],"results":[111],"show":[112],"that":[113],"Chahar":[120],"can":[122,155],"achieve":[123],"great":[124],"improvements":[125],"over":[126],"baseline":[127,180],"model":[128,137,168],"speech.":[131],"And":[132],"transferring":[133,141],"parts":[134],"performs":[138],"better":[139],"than":[140],"whole":[143],"model.":[144,163,181],"Furthermore,":[145],"spliced":[148],"together":[149],"features":[154],"further":[156],"enhance":[157],"acoustic":[162],"The":[164],"WER":[165],"optimal":[167],"relatively":[170],"reduced":[171],"by":[172],"10.96%":[173],"compared":[174],"in-of-domain":[177]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}