{"id":"https://openalex.org/W2057566829","doi":"https://doi.org/10.1109/iscslp.2012.6423501","title":"Acoustic space partition based on broad phonetic class for ensemble acoustic modeling","display_name":"Acoustic space partition based on broad phonetic class for ensemble acoustic modeling","publication_year":2012,"publication_date":"2012-12-01","ids":{"openalex":"https://openalex.org/W2057566829","doi":"https://doi.org/10.1109/iscslp.2012.6423501","mag":"2057566829"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp.2012.6423501","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2012.6423501","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 8th International Symposium on Chinese Spoken Language 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/A5034792613","display_name":"Xugang Lu","orcid":"https://orcid.org/0000-0001-7075-448X"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Xugang Lu","raw_affiliation_strings":["National Institute of Information and Communications Technology, Japan","National institute of information and communications technology, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology, Japan","institution_ids":["https://openalex.org/I90023481"]},{"raw_affiliation_string":"National institute of information and communications technology, Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044008055","display_name":"Yu Tsao","orcid":"https://orcid.org/0000-0001-6956-0418"},"institutions":[{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]},{"id":"https://openalex.org/I29955533","display_name":"Center for Information Technology","ror":"https://ror.org/03jh5a977","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I29955533"]}],"countries":["TW","US"],"is_corresponding":false,"raw_author_name":"Yu Tsao","raw_affiliation_strings":["Research Center for Information Technology Innovation, Academic Sinica, Taiwan","Research Center for Information Technology Innovation, Academic Sinica, Taiwan#TAB#"],"affiliations":[{"raw_affiliation_string":"Research Center for Information Technology Innovation, Academic Sinica, Taiwan","institution_ids":["https://openalex.org/I4210086894"]},{"raw_affiliation_string":"Research Center for Information Technology Innovation, Academic Sinica, Taiwan#TAB#","institution_ids":["https://openalex.org/I29955533"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077037266","display_name":"Shigeki Matsuda","orcid":null},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shigeki Matsuda","raw_affiliation_strings":["National Institute of Information and Communications Technology, Japan","National institute of information and communications technology, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology, Japan","institution_ids":["https://openalex.org/I90023481"]},{"raw_affiliation_string":"National institute of information and communications technology, Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001601327","display_name":"Chiori Hori","orcid":"https://orcid.org/0000-0002-4201-7578"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Chiori Hori","raw_affiliation_strings":["National Institute of Information and Communications Technology, Japan","National institute of information and communications technology, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology, Japan","institution_ids":["https://openalex.org/I90023481"]},{"raw_affiliation_string":"National institute of information and communications technology, Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108760549","display_name":"Hideki Kashioka","orcid":null},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hideki Kashioka","raw_affiliation_strings":["National Institute of Information and Communications Technology, Japan","National institute of information and communications technology, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology, Japan","institution_ids":["https://openalex.org/I90023481"]},{"raw_affiliation_string":"National institute of information and communications technology, Japan","institution_ids":["https://openalex.org/I90023481"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5034792613"],"corresponding_institution_ids":["https://openalex.org/I90023481"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.105132,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"16","issue":null,"first_page":"311","last_page":"314"},"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/T11309","display_name":"Music and Audio Processing","score":0.9986000061035156,"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":0.9959999918937683,"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/acoustic-space","display_name":"Acoustic space","score":0.7774061560630798},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6498661637306213},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6469032168388367},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.6177948117256165},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5734439492225647},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.48456087708473206},{"id":"https://openalex.org/keywords/stress","display_name":"Stress (linguistics)","score":0.4538716673851013},{"id":"https://openalex.org/keywords/principal-component-analysis","display_name":"Principal component analysis","score":0.4510974586009979},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35460418462753296},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34236323833465576},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.26198333501815796},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.2398848831653595},{"id":"https://openalex.org/keywords/acoustic-wave","display_name":"Acoustic wave","score":0.18375274538993835},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18107491731643677}],"concepts":[{"id":"https://openalex.org/C108250783","wikidata":"https://www.wikidata.org/wiki/Q4674710","display_name":"Acoustic space","level":3,"score":0.7774061560630798},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6498661637306213},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6469032168388367},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.6177948117256165},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5734439492225647},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.48456087708473206},{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.4538716673851013},{"id":"https://openalex.org/C27438332","wikidata":"https://www.wikidata.org/wiki/Q2873","display_name":"Principal component analysis","level":2,"score":0.4510974586009979},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35460418462753296},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34236323833465576},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.26198333501815796},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.2398848831653595},{"id":"https://openalex.org/C204723758","wikidata":"https://www.wikidata.org/wiki/Q3882459","display_name":"Acoustic wave","level":2,"score":0.18375274538993835},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18107491731643677},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp.2012.6423501","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2012.6423501","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 8th International Symposium on Chinese Spoken Language Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.800000011920929,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W21249823","https://openalex.org/W1534477342","https://openalex.org/W1895481600","https://openalex.org/W2101066392","https://openalex.org/W2108446915","https://openalex.org/W2143693287","https://openalex.org/W2147147599","https://openalex.org/W2160237783","https://openalex.org/W6676666668"],"related_works":["https://openalex.org/W4367680763","https://openalex.org/W2364370872","https://openalex.org/W2053269318","https://openalex.org/W2739335048","https://openalex.org/W2121652828","https://openalex.org/W3033124456","https://openalex.org/W2057566829","https://openalex.org/W2604496056","https://openalex.org/W2696259631","https://openalex.org/W4384343528"],"abstract_inverted_index":{"Ensemble":[0,157],"acoustic":[1,14,59,63,89,102,107,122,158,176],"modeling":[2,60,117],"can":[3],"be":[4,85],"used":[5],"to":[6,20,36,42],"model":[7],"different":[8,18],"factors":[9],"that":[10,79,150,174],"cause":[11],"variability":[12,64],"of":[13,24,30,91,118,130],"space,":[15],"and":[16,68,81,154,184,190],"provide":[17],"combination":[19],"improve":[21],"the":[22,31,38,125,131,144,163,181],"performance":[23],"automatic":[25],"speech":[26,75],"recognition":[27,76,171],"(ASR).":[28],"One":[29],"main":[32],"concerns":[33],"is":[34],"how":[35],"partition":[37,109],"training":[39],"data":[40,141,165],"set":[41],"several":[43],"subsets":[44],"based":[45,111,133,179],"on":[46,57,112,162,167,180],"which":[47],"ensemble":[48,58,121],"models":[49,159,177],"are":[50],"trained.":[51],"In":[52],"this":[53],"study,":[54],"we":[55,104,136],"focus":[56],"concerned":[61,151],"with":[62,152],"caused":[65],"by":[66],"gender":[67,80,153],"accent":[69,82,155],"for":[70,120],"Chinese":[71],"large":[72],"vocabulary":[73],"continuous":[74],"(LVCSR).":[77],"Considering":[78],"information":[83],"may":[84],"encoded":[86],"in":[87,99,143,194],"local":[88],"realizations":[90],"a":[92,100,106],"few":[93],"specific":[94],"phonetic":[95,114],"classes":[96],"rather":[97],"than":[98],"global":[101],"distribution,":[103],"proposed":[105],"space":[108,149],"method":[110],"broad":[113],"class":[115],"(BPC)":[116],"speaker":[119,134,147],"modeling.":[123],"With":[124],"principal":[126],"component":[127],"analysis":[128],"(PCA)":[129],"BPC":[132],"representation,":[135],"designed":[137],"two":[138],"level":[139,183,186],"hierarchical":[140],"partitions":[142,187],"low":[145],"dimensional":[146],"factor":[148],"information.":[156],"were":[160],"trained":[161,178],"partitioned":[164],"sets":[166],"both":[168],"levels.":[169],"Speech":[170],"results":[172],"showed":[173],"using":[175],"first":[182],"second":[185],"got":[188],"9.73%":[189],"32.29%":[191],"relative":[192],"improvements":[193],"character":[195],"error":[196],"reduction":[197],"rate,":[198],"respectively.":[199]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
