{"id":"https://openalex.org/W4386245989","doi":"https://doi.org/10.1145/3617830","title":"A Comparative Study on Selecting Acoustic Modeling Units for WFST-based Mongolian Speech Recognition","display_name":"A Comparative Study on Selecting Acoustic Modeling Units for WFST-based Mongolian Speech Recognition","publication_year":2023,"publication_date":"2023-08-29","ids":{"openalex":"https://openalex.org/W4386245989","doi":"https://doi.org/10.1145/3617830"},"language":"en","primary_location":{"id":"doi:10.1145/3617830","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3617830","pdf_url":null,"source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","raw_type":"journal-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/A5008226894","display_name":"Yonghe Wang","orcid":"https://orcid.org/0000-0003-1647-1539"},"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":"Wang Yonghe","raw_affiliation_strings":["College of Computer Science, Inner Mongolia University, China"],"raw_orcid":"https://orcid.org/0000-0003-1647-1539","affiliations":[{"raw_affiliation_string":"College of Computer Science, Inner Mongolia University, 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, China"],"raw_orcid":"https://orcid.org/0000-0001-7312-1629","affiliations":[{"raw_affiliation_string":"College of Computer Science, Inner Mongolia University, China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111031451","display_name":"Gaunglai Gao","orcid":null},"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":"Gaunglai Gao","raw_affiliation_strings":["College of Computer Science, Inner Mongolia University, China"],"raw_orcid":"https://orcid.org/0009-0005-5513-1192","affiliations":[{"raw_affiliation_string":"College of Computer Science, Inner Mongolia University, 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":0.1586,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.52847964,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"22","issue":"10","first_page":"1","last_page":"20"},"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/T10181","display_name":"Natural Language Processing Techniques","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/T10028","display_name":"Topic Modeling","score":0.9977999925613403,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.9190154671669006},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.8495444059371948},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8321243524551392},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6321213841438293},{"id":"https://openalex.org/keywords/grapheme","display_name":"Grapheme","score":0.6127136945724487},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5458678007125854},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.5246022939682007},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5160295963287354},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.4770752191543579},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4389049708843231},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.43202829360961914},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.2163863182067871},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.16419580578804016}],"concepts":[{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.9190154671669006},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.8495444059371948},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8321243524551392},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6321213841438293},{"id":"https://openalex.org/C2776779415","wikidata":"https://www.wikidata.org/wiki/Q2545446","display_name":"Grapheme","level":3,"score":0.6127136945724487},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5458678007125854},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.5246022939682007},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5160295963287354},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4770752191543579},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4389049708843231},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.43202829360961914},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2163863182067871},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.16419580578804016},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C30080830","wikidata":"https://www.wikidata.org/wiki/Q169917","display_name":"Graphene","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3617830","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3617830","pdf_url":null,"source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.44999998807907104,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G6541469570","display_name":null,"funder_award_id":"62366037, 62066033","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322216","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1510837697","https://openalex.org/W1528411667","https://openalex.org/W1631260214","https://openalex.org/W2053306448","https://openalex.org/W2106652354","https://openalex.org/W2127141656","https://openalex.org/W2160815625","https://openalex.org/W2167655920","https://openalex.org/W2253873513","https://openalex.org/W2293634267","https://openalex.org/W2402146185","https://openalex.org/W2514741789","https://openalex.org/W2520160253","https://openalex.org/W2714176837","https://openalex.org/W2735949438","https://openalex.org/W2885952204","https://openalex.org/W2899879954","https://openalex.org/W2962824709","https://openalex.org/W2963540920","https://openalex.org/W2963979492","https://openalex.org/W3009129170","https://openalex.org/W3082453117","https://openalex.org/W3089901025","https://openalex.org/W3095229326","https://openalex.org/W3097558625","https://openalex.org/W3103909332","https://openalex.org/W3160551958","https://openalex.org/W3160729285","https://openalex.org/W3161324588","https://openalex.org/W3161674998","https://openalex.org/W3163463193","https://openalex.org/W3163936458","https://openalex.org/W3198455051","https://openalex.org/W3202620275","https://openalex.org/W3217723215","https://openalex.org/W4200284299","https://openalex.org/W4224917952","https://openalex.org/W4224918897","https://openalex.org/W4224919682","https://openalex.org/W4297818305"],"related_works":["https://openalex.org/W2506515307","https://openalex.org/W2060656088","https://openalex.org/W2183593636","https://openalex.org/W4391124013","https://openalex.org/W3104532855","https://openalex.org/W2080578089","https://openalex.org/W2179005426","https://openalex.org/W2121652828","https://openalex.org/W1498263237","https://openalex.org/W2054442733"],"abstract_inverted_index":{"Traditional":[0],"weighted":[1],"finite-state":[2],"transducer\u2013":[3],"(WFST)":[4],"based":[5,31,218],"Mongolian":[6,20,51,110,169,200,206,230],"automatic":[7],"speech":[8],"recognition":[9],"(ASR)":[10],"systems":[11],"use":[12],"phonemes":[13,133],"as":[14],"pronunciation":[15,35,46,163,195,216],"lexicon":[16,36,47,196,217],"modeling":[17,178,192,223,243],"units.":[18,136],"However,":[19,71],"is":[21,53,56],"an":[22,28,140,175],"agglutinative,":[23],"low-resource":[24],"language,":[25],"and":[26,82,93,134],"building":[27,239],"ASR":[29,89,201,231,249],"system":[30,250],"on":[32,105,204,219],"the":[33,44,72,76,79,84,87,106,109,129,152,162,168,199,215,220,228,235,240,248],"phoneme":[34,45,158],"remains":[37],"a":[38,61,102,123,205],"challenge":[39],"for":[40,194,198],"various":[41,189],"reasons.":[42],"First,":[43],"manually":[48],"constructed":[49],"by":[50,166],"linguists":[52],"finite,":[54],"which":[55,100],"usually":[57],"used":[58],"to":[59,66,127,145,156,160],"build":[60],"grapheme-to-phoneme":[62,124],"conversion":[63],"(G2P)":[64],"model":[65,81,126],"frequently":[67],"expand":[68,161],"new":[69],"words.":[70],"data":[73],"sparsity":[74],"decreases":[75],"robustness":[77],"of":[78,86,108,150,211],"G2P":[80,154],"affects":[83],"performance":[85],"final":[88],"system.":[90,202,232],"Second,":[91],"homophones":[92],"polysyllabic":[94],"words":[95,147],"are":[96],"common":[97],"in":[98,117],"Mongolian,":[99],"has":[101],"certain":[103],"impact":[104],"construction":[107,180,197],"acoustic":[111,141,176,190,221,241],"model.":[112],"To":[113],"address":[114],"these":[115],"problems,":[116],"this":[118],"work,":[119],"we":[120,138,172,187],"first":[121],"propose":[122,174],"alignment":[125],"obtain":[128],"mapping":[130],"relationship":[131],"between":[132],"subword":[135,142,177,191,222,242],"Then,":[137],"construct":[139,227],"segmentation":[143],"set":[144],"segment":[146],"directly":[148],"instead":[149],"using":[151],"traditional":[153],"method":[155,181],"predict":[157],"sequences":[159],"lexicon.":[164],"Further,":[165,233],"analyzing":[167],"encoding":[170],"form,":[171],"also":[173],"units":[179,193],"that":[182,214],"removes":[183],"control":[184,236],"characters.":[185],"Finally,":[186],"investigate":[188],"Experiments":[203],"dataset":[207],"with":[208],"325":[209],"hours":[210],"training":[212],"show":[213],"unit":[224,244],"can":[225,245],"effectively":[226],"WFST-based":[229],"removing":[234],"characters":[237],"when":[238],"further":[246],"improve":[247],"performance.":[251]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}