{"id":"https://openalex.org/W2143355529","doi":"https://doi.org/10.1109/icassp.2012.6289014","title":"Region dependent linear transforms in multilingual speech recognition","display_name":"Region dependent linear transforms in multilingual speech recognition","publication_year":2012,"publication_date":"2012-03-01","ids":{"openalex":"https://openalex.org/W2143355529","doi":"https://doi.org/10.1109/icassp.2012.6289014","mag":"2143355529"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2012.6289014","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6289014","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5065253688","display_name":"Martin Karafi\u00e1t","orcid":"https://orcid.org/0000-0001-6474-8366"},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Martin Karafiat","raw_affiliation_strings":["Speech@FIT, Brno University of Technology, Czech Republic"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech@FIT, Brno University of Technology, Czech Republic","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039457010","display_name":"Milo\u0161 Janda","orcid":null},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Milos Janda","raw_affiliation_strings":["Speech@FIT, Brno University of Technology, Czech Republic"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech@FIT, Brno University of Technology, Czech Republic","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045539248","display_name":"Ja\u0148 \u010cernock\u00fd","orcid":"https://orcid.org/0000-0002-8800-0210"},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Jan Cernocky","raw_affiliation_strings":["Speech@FIT, Brno University of Technology, Czech Republic"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech@FIT, Brno University of Technology, Czech Republic","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042273299","display_name":"Luk\u00e1\u0161 Burget","orcid":"https://orcid.org/0000-0002-4951-5908"},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]},{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]},{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ","US"],"is_corresponding":false,"raw_author_name":"Lukas Burget","raw_affiliation_strings":["SRI International, Inc., Menlo Park, CA, USA","Speech@FIT, Brno University of Technology, Czech Republic"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SRI International, Inc., Menlo Park, CA, USA","institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I4210099336"]},{"raw_affiliation_string":"Speech@FIT, Brno University of Technology, Czech Republic","institution_ids":["https://openalex.org/I60587646"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.561,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.84177787,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"4885","last_page":"4888"},"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":0.9991000294685364,"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":0.9991000294685364,"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/discriminative-model","display_name":"Discriminative model","score":0.9190908670425415},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8004106283187866},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7190321087837219},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.6960688829421997},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.690584123134613},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5597342848777771},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5493688583374023},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5072686076164246},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.462709903717041},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4236820340156555},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39380383491516113},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07772603631019592}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.9190908670425415},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8004106283187866},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7190321087837219},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6960688829421997},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.690584123134613},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5597342848777771},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5493688583374023},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5072686076164246},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.462709903717041},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4236820340156555},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39380383491516113},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07772603631019592},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2012.6289014","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6289014","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.7400000095367432,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W156213964","https://openalex.org/W159523117","https://openalex.org/W1981706894","https://openalex.org/W2090764203","https://openalex.org/W2106554350","https://openalex.org/W2125610823","https://openalex.org/W2131042651","https://openalex.org/W2132215870","https://openalex.org/W2164240571","https://openalex.org/W2411442511","https://openalex.org/W3019319563","https://openalex.org/W4285719527","https://openalex.org/W6606333028","https://openalex.org/W6606552489","https://openalex.org/W6679556679","https://openalex.org/W6776070422"],"related_works":["https://openalex.org/W1565453839","https://openalex.org/W2134999511","https://openalex.org/W2167155152","https://openalex.org/W198264392","https://openalex.org/W2729514902","https://openalex.org/W2970216048","https://openalex.org/W2285052147","https://openalex.org/W2806866760","https://openalex.org/W2160356362","https://openalex.org/W2546942002"],"abstract_inverted_index":{"In":[0,23],"today's":[1],"speech":[2,14],"recognition":[3],"systems,":[4],"linear":[5],"or":[6],"nonlinear":[7],"transformations":[8,104],"are":[9,41,82],"usually":[10],"applied":[11],"to":[12,18,48,60],"post-process":[13],"features":[15,58],"forming":[16],"input":[17],"HMM":[19],"based":[20,71],"acoustic":[21,46,72],"models.":[22],"this":[24],"work,":[25],"we":[26,95],"experiment":[27],"with":[28,44],"three":[29],"popular":[30],"transforms:":[31],"HLDA,":[32],"MPE-HLDA":[33],"and":[34,59,111],"Region":[35],"Dependent":[36],"Linear":[37],"Transforms":[38],"(RDLT),":[39],"which":[40],"trained":[42,113],"jointly":[43],"the":[45,52,56,68,102],"model":[47],"extract":[49],"maximum":[50],"of":[51,87],"discriminative":[53],"information":[54],"from":[55,92,116],"raw":[57],"represent":[61],"it":[62],"in":[63],"a":[64],"form":[65],"suitable":[66],"for":[67,84],"following":[69],"GMM-HMM":[70],"model.":[73],"We":[74],"focus":[75],"on":[76],"multi-lingual":[77],"environments,":[78],"where":[79],"limited":[80],"resources":[81],"available":[83],"training":[85],"recognizers":[86],"many":[88],"languages.":[89,118],"Using":[90],"data":[91,115],"GlobalPhone":[93],"database,":[94],"show":[96],"that,":[97],"under":[98],"such":[99],"restrictive":[100],"conditions,":[101],"feature":[103],"can":[105],"be":[106],"advantageously":[107],"shared":[108],"across":[109],"languages":[110],"robustly":[112],"using":[114],"several":[117]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}