{"id":"https://openalex.org/W2600174029","doi":"https://doi.org/10.1109/ialp.2016.7875921","title":"Comparison on Neural Network based acoustic model in Mongolian speech recognition","display_name":"Comparison on Neural Network based acoustic model in Mongolian speech recognition","publication_year":2016,"publication_date":"2016-11-01","ids":{"openalex":"https://openalex.org/W2600174029","doi":"https://doi.org/10.1109/ialp.2016.7875921","mag":"2600174029"},"language":"en","primary_location":{"id":"doi:10.1109/ialp.2016.7875921","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ialp.2016.7875921","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 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/A5100397258","display_name":"Hongwei Zhang","orcid":"https://orcid.org/0000-0002-7718-021X"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongwei Zhang","raw_affiliation_strings":["College of Computer Science, Inner Mongolia University, Hohhot, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science, Inner Mongolia University, Hohhot, China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014372166","display_name":"Feilong Bao","orcid":"https://orcid.org/0000-0001-7312-1629"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feilong Bao","raw_affiliation_strings":["College of Computer Science, Inner Mongolia University, Hohhot, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science, Inner Mongolia University, Hohhot, China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076174513","display_name":"Guanglai Gao","orcid":"https://orcid.org/0009-0005-5513-1192"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guanglai Gao","raw_affiliation_strings":["College of Computer Science, Inner Mongolia University, Hohhot, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science, Inner Mongolia University, Hohhot, China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100715414","display_name":"Hui Zhang","orcid":"https://orcid.org/0000-0001-8012-4684"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Zhang","raw_affiliation_strings":["College of Computer Science, Inner Mongolia University, Hohhot, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science, Inner Mongolia University, Hohhot, China","institution_ids":["https://openalex.org/I2722730"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2722730"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.993399977684021,"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":0.9872000217437744,"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":0.8102824091911316},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7971585988998413},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.6859433054924011},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.657375156879425},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6218916773796082},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5667242407798767},{"id":"https://openalex.org/keywords/dynamic-time-warping","display_name":"Dynamic time warping","score":0.5342478156089783},{"id":"https://openalex.org/keywords/vocal-tract","display_name":"Vocal tract","score":0.5151954293251038},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5051420331001282},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.4747617244720459},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45951974391937256},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.43652772903442383},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3981093466281891},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.2568853497505188}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8102824091911316},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7971585988998413},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.6859433054924011},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.657375156879425},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6218916773796082},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5667242407798767},{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.5342478156089783},{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.5151954293251038},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5051420331001282},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.4747617244720459},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45951974391937256},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.43652772903442383},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3981093466281891},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2568853497505188},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ialp.2016.7875921","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ialp.2016.7875921","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 International Conference on Asian Language Processing (IALP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.4300000071525574,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1499864241","https://openalex.org/W1524333225","https://openalex.org/W1585230382","https://openalex.org/W1631260214","https://openalex.org/W2064675550","https://openalex.org/W2097316030","https://openalex.org/W2106652354","https://openalex.org/W2112739286","https://openalex.org/W2115730999","https://openalex.org/W2142760467","https://openalex.org/W2155273149","https://openalex.org/W2171698314","https://openalex.org/W2253873513","https://openalex.org/W2404568753","https://openalex.org/W6629930100","https://openalex.org/W6631362777","https://openalex.org/W6713570806"],"related_works":["https://openalex.org/W3009759344","https://openalex.org/W2740630172","https://openalex.org/W4255044973","https://openalex.org/W2499802997","https://openalex.org/W2112059504","https://openalex.org/W2727729836","https://openalex.org/W1960256358","https://openalex.org/W2548037963","https://openalex.org/W2464377622","https://openalex.org/W2394963835"],"abstract_inverted_index":{"Deep":[0],"Neural":[1],"Networks":[2],"(DNNs)":[3],"beat":[4],"the":[5,12,29,43,68,80,86,94,121,127,130,136,144],"Gaussian":[6],"Mixture":[7],"Models":[8],"(GMMs),":[9],"and":[10,34,73,115],"become":[11],"state-of-the-art":[13],"techniques":[14],"for":[15],"acoustic":[16,23,63,96],"model.":[17],"Then":[18],"various":[19,105],"neural":[20,60],"networks":[21,61],"based":[22,62],"models":[24],"are":[25,39],"proposed":[26],"to":[27,118],"make":[28],"speech":[30,47,70,132,139],"recognition":[31,71,140],"systems":[32],"better":[33],"better.":[35],"However":[36],"these":[37],"successes":[38],"not":[40],"adopted":[41],"in":[42,52,67],"researches":[44],"of":[45,59,107,123,129],"Mongolian":[46,69,131],"recognition.":[48,133],"This":[49],"study":[50,56],"fills":[51],"this":[53],"gap.":[54],"We":[55,77],"a":[57],"series":[58],"models,":[64],"apply":[65],"them":[66],"systems,":[72],"compare":[74],"their":[75],"performance.":[76],"find":[78],"out":[79],"Long":[81],"Short-Term":[82],"Memory":[83],"(LSTM)":[84],"is":[85],"best":[87,137],"model":[88,97],"among":[89],"them.":[90],"Finally,":[91],"by":[92,150],"using":[93],"LSTM":[95],"together":[98],"with":[99,135],"data":[100],"augmentation":[101],"technique,":[102],"which":[103],"uses":[104],"combinations":[106],"Vocal":[108],"Tract":[109],"Length":[110],"Normalization":[111],"(VTLN)":[112],"warping":[113],"factor":[114,117],"time-warping":[116],"artificially":[119],"expand":[120],"amount":[122],"data,":[124],"we":[125,142],"refresh":[126],"recode":[128],"Compared":[134],"DNN-based":[138],"system,":[141],"cut":[143],"Word":[145],"Error":[146],"Rate":[147],"(WER)":[148],"nearly":[149],"half.":[151]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}