{"id":"https://openalex.org/W2125728718","doi":"https://doi.org/10.1109/icassp.2008.4518606","title":"Optimizing the acoustic modeling from an unbalanced bi-lingual corpus","display_name":"Optimizing the acoustic modeling from an unbalanced bi-lingual corpus","publication_year":2008,"publication_date":"2008-03-01","ids":{"openalex":"https://openalex.org/W2125728718","doi":"https://doi.org/10.1109/icassp.2008.4518606","mag":"2125728718"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2008.4518606","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2008.4518606","pdf_url":null,"source":{"id":"https://openalex.org/S4210167542","display_name":"Proceedings of the ... IEEE International Conference on Acoustics, Speech, and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Conference on Acoustics, Speech and Signal Processing","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/A5002032106","display_name":"Dau-Cheng Lyu","orcid":null},"institutions":[{"id":"https://openalex.org/I173093425","display_name":"Chang Gung University","ror":"https://ror.org/00d80zx46","country_code":"TW","type":"education","lineage":["https://openalex.org/I173093425"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Dau-cheng Lyu","raw_affiliation_strings":["Chang Gung University, Taoyuan, Taoyuan, TW","Dept. of Electr. Eng., Chang Gung Univ., TaoYuan"],"affiliations":[{"raw_affiliation_string":"Chang Gung University, Taoyuan, Taoyuan, TW","institution_ids":["https://openalex.org/I173093425"]},{"raw_affiliation_string":"Dept. of Electr. Eng., Chang Gung Univ., TaoYuan","institution_ids":["https://openalex.org/I173093425"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077059176","display_name":"Ren-Yuan Lyu","orcid":"https://orcid.org/0000-0002-6691-6447"},"institutions":[{"id":"https://openalex.org/I173093425","display_name":"Chang Gung University","ror":"https://ror.org/00d80zx46","country_code":"TW","type":"education","lineage":["https://openalex.org/I173093425"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Ren-yuan Lyu","raw_affiliation_strings":["Department of Computer Science and Information Engineering, Chang Gung University, Taiwan","Department of Electrical Engineering, Chang Gung University, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, Chang Gung University, Taiwan","institution_ids":["https://openalex.org/I173093425"]},{"raw_affiliation_string":"Department of Electrical Engineering, Chang Gung University, Taiwan","institution_ids":["https://openalex.org/I173093425"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5002032106"],"corresponding_institution_ids":["https://openalex.org/I173093425"],"apc_list":null,"apc_paid":null,"fwci":0.3539,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.55847458,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4301","last_page":"4304"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9962000250816345,"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":0.9944000244140625,"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":0.8341346979141235},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6462899446487427},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6388117074966431},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6290476322174072},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6179772019386292},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5929149985313416},{"id":"https://openalex.org/keywords/syllable","display_name":"Syllable","score":0.5580918192863464},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5556372404098511},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5305355787277222},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.5229828357696533},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.510466456413269},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5103222727775574},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.508827269077301},{"id":"https://openalex.org/keywords/hierarchical-clustering","display_name":"Hierarchical clustering","score":0.4305534362792969},{"id":"https://openalex.org/keywords/parametric-model","display_name":"Parametric model","score":0.42005470395088196},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3580187261104584},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.30152052640914917}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8341346979141235},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6462899446487427},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6388117074966431},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6290476322174072},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6179772019386292},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5929149985313416},{"id":"https://openalex.org/C109089402","wikidata":"https://www.wikidata.org/wiki/Q8188","display_name":"Syllable","level":2,"score":0.5580918192863464},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5556372404098511},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5305355787277222},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.5229828357696533},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.510466456413269},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5103222727775574},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.508827269077301},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.4305534362792969},{"id":"https://openalex.org/C24574437","wikidata":"https://www.wikidata.org/wiki/Q7135228","display_name":"Parametric model","level":3,"score":0.42005470395088196},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3580187261104584},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.30152052640914917},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"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/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/icassp.2008.4518606","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2008.4518606","pdf_url":null,"source":{"id":"https://openalex.org/S4210167542","display_name":"Proceedings of the ... IEEE International Conference on Acoustics, Speech, and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8100000023841858,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W60702959","https://openalex.org/W83374769","https://openalex.org/W125260059","https://openalex.org/W1588808962","https://openalex.org/W1966926213","https://openalex.org/W2018466475","https://openalex.org/W2030644393","https://openalex.org/W2102728203","https://openalex.org/W2132663820","https://openalex.org/W2151941172","https://openalex.org/W2158069733","https://openalex.org/W2168175751","https://openalex.org/W2405876414","https://openalex.org/W6714018878"],"related_works":["https://openalex.org/W2061937230","https://openalex.org/W2132658536","https://openalex.org/W3081187864","https://openalex.org/W151018310","https://openalex.org/W4380605396","https://openalex.org/W3133352777","https://openalex.org/W2008737763","https://openalex.org/W2584084702","https://openalex.org/W2784059283","https://openalex.org/W3012383599"],"abstract_inverted_index":{"Phoneme":[0],"set":[1,58,73,124],"clustering":[2,86],"of":[3,11,18,96,113,152],"accurate":[4],"modeling":[5,63,104],"is":[6,24,28,75],"important":[7],"in":[8,64,136],"the":[9,19,29,61,71,78,97,111,117,121,126,138,149,153],"task":[10],"multilingual":[12],"speech":[13],"recognition,":[14],"especially":[15],"when":[16],"each":[17,95],"available":[20,127],"language":[21],"training":[22,94,128],"corpora":[23],"mismatched,":[25],"such":[26],"as":[27],"case":[30],"between":[31,120],"a":[32,38,48,55,102],"major":[33],"language,":[34,40],"like":[35,41],"Mandarin,":[36],"and":[37,125],"minor":[39],"Taiwanese.":[42],"In":[43,67],"this":[44,65],"paper,":[45],"we":[46,81,100],"present":[47],"data-driven":[49],"approach":[50,140],"for":[51,77,93,115],"not":[52],"only":[53],"acquiring":[54],"proper":[56],"phoneme":[57,72,123],"but":[59],"optimizing":[60,116],"acoustic":[62,98,118],"situation.":[66],"order":[68],"to":[69,109],"obtain":[70],"that":[74,137],"suitable":[76],"unbalanced":[79],"corpus,":[80],"use":[82],"an":[83],"agglomerative":[84],"hierarchical":[85],"with":[87],"delta":[88],"Bayesian":[89],"information":[90],"criteria.":[91],"Then":[92],"models,":[99],"choose":[101],"parametric":[103],"technique,":[105],"model":[106,119],"complexity":[107],"selection,":[108],"adjust":[110],"number":[112],"mixtures":[114],"new":[122],"data.":[129],"The":[130],"experimental":[131],"results":[132],"are":[133],"very":[134],"encouraging":[135],"proposed":[139],"reduces":[141],"relative":[142],"syllable":[143],"error":[144],"rate":[145],"by":[146],"7.8%":[147],"over":[148],"best":[150],"result":[151],"knowledge-based":[154],"approach.":[155]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}