{"id":"https://openalex.org/W2143262579","doi":"https://doi.org/10.1109/asru.2007.4430128","title":"State-dependent mixture tying with variable codebook size for accented speech recognition","display_name":"State-dependent mixture tying with variable codebook size for accented speech recognition","publication_year":2007,"publication_date":"2007-01-01","ids":{"openalex":"https://openalex.org/W2143262579","doi":"https://doi.org/10.1109/asru.2007.4430128","mag":"2143262579"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2007.4430128","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2007.4430128","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU)","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/A5100330618","display_name":"Yi Liu","orcid":"https://orcid.org/0000-0003-1399-7420"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yi Liu","raw_affiliation_strings":["Tsinghua Nat. Lab. for Inf. Sci. & Technol., Beijing"],"affiliations":[{"raw_affiliation_string":"Tsinghua Nat. Lab. for Inf. Sci. & Technol., Beijing","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064687463","display_name":"Zheng Fang","orcid":"https://orcid.org/0000-0003-3887-3141"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fang Zheng","raw_affiliation_strings":["Tsinghua Nat. Lab. for Inf. Sci. & Technol., Beijing"],"affiliations":[{"raw_affiliation_string":"Tsinghua Nat. Lab. for Inf. Sci. & Technol., Beijing","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100893284","display_name":"Lei He","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lei He","raw_affiliation_strings":["Tsinghua Nat. Lab. for Inf. Sci. & Technol., Beijing"],"affiliations":[{"raw_affiliation_string":"Tsinghua Nat. Lab. for Inf. Sci. & Technol., Beijing","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069555295","display_name":"Yunqing Xia","orcid":"https://orcid.org/0009-0005-8608-574X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yunqing Xia","raw_affiliation_strings":["Tsinghua Nat. Lab. for Inf. Sci. & Technol., Beijing"],"affiliations":[{"raw_affiliation_string":"Tsinghua Nat. Lab. for Inf. Sci. & Technol., Beijing","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100330618"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1188534,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"300","last_page":"305"},"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/T10860","display_name":"Speech and Audio Processing","score":0.998199999332428,"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":0.9955999851226807,"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/codebook","display_name":"Codebook","score":0.8011380434036255},{"id":"https://openalex.org/keywords/tying","display_name":"Tying","score":0.6529533863067627},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5936727523803711},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.5814307332038879},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5306545495986938},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4913095533847809},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.46067604422569275},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4520159363746643},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3952244520187378},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3778778314590454},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.34400302171707153}],"concepts":[{"id":"https://openalex.org/C127759330","wikidata":"https://www.wikidata.org/wiki/Q637416","display_name":"Codebook","level":2,"score":0.8011380434036255},{"id":"https://openalex.org/C2780938662","wikidata":"https://www.wikidata.org/wiki/Q973710","display_name":"Tying","level":2,"score":0.6529533863067627},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5936727523803711},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.5814307332038879},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5306545495986938},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4913095533847809},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.46067604422569275},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4520159363746643},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3952244520187378},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3778778314590454},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.34400302171707153},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru.2007.4430128","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2007.4430128","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.699999988079071,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W311969337","https://openalex.org/W1578856370","https://openalex.org/W1608231129","https://openalex.org/W1950777589","https://openalex.org/W1977806456","https://openalex.org/W2113328195","https://openalex.org/W2143217142","https://openalex.org/W2167188741","https://openalex.org/W2169941844","https://openalex.org/W6611024320","https://openalex.org/W6636534325","https://openalex.org/W6676778771","https://openalex.org/W6681665012","https://openalex.org/W6684614936"],"related_works":["https://openalex.org/W2293149949","https://openalex.org/W2026099691","https://openalex.org/W4284672201","https://openalex.org/W2377486419","https://openalex.org/W2943202426","https://openalex.org/W2137816434","https://openalex.org/W4324119469","https://openalex.org/W2164868312","https://openalex.org/W2146591867","https://openalex.org/W2160650576"],"abstract_inverted_index":{"In":[0],"this":[1,148],"paper,":[2],"we":[3],"propose":[4],"a":[5,42,68,101,111,159],"state-dependent":[6],"tied":[7,179],"mixture":[8,32,44,77,174],"(SDTM)":[9],"models":[10],"with":[11,171],"variable":[12],"codebook":[13,84,107,118],"size":[14,85,108,119],"to":[15,36,41,53,59,73,92],"improve":[16],"the":[17,47,55,60,75,93,104,141],"model":[18,26,49,66,81,88,115,143],"robustness":[19],"for":[20,79,110],"accented":[21,128,154],"phonetic":[22,129,178],"variations":[23],"while":[24],"maintaining":[25],"discriminative":[27],"ability.":[28],"State":[29],"tying":[30,33,45,52,63,175],"and":[31,163,176],"are":[34],"combined":[35],"generate":[37],"SDTM":[38,48,87],"models.":[39],"Compared":[40],"pure":[43],"system,":[46,64],"uses":[50,67],"state":[51,56,62,102,123,172],"reserve":[54],"identity;":[57],"compared":[58,170],"sole":[61],"such":[65],"small":[69],"set":[70],"of":[71,86,96,114,127,147],"parameters":[72],"discard":[74],"overlapping":[76],"distributions":[78],"robust":[80],"estimation.":[82],"The":[83,98,117,145],"is":[89,120,150],"varied":[90],"according":[91],"confusion":[94],"probability":[95,126],"states.":[97],"more":[99],"confusable":[100],"is,":[103],"larger":[105],"its":[106],"gets":[109],"higher":[112],"degree":[113],"resolution.":[116],"governed":[121],"by":[122,136],"level":[124],"variation":[125],"confusions":[130],"which":[131],"can":[132],"be":[133],"automatically":[134],"extracted":[135],"frame-to-state":[137],"alignment":[138],"based":[139],"on":[140,152],"local":[142],"mismatch.":[144],"effectiveness":[146],"approach":[149],"evaluated":[151],"Mandarin":[153],"speech.":[155],"Our":[156],"method":[157],"yields":[158],"significant":[160],"2.1%,":[161],"9.5%":[162],"3.5%":[164],"absolute":[165],"word":[166],"error":[167],"rate":[168],"reduction":[169],"tying,":[173],"state-based":[177],"mixtures,":[180],"respectively.":[181]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}