{"id":"https://openalex.org/W139772320","doi":"https://doi.org/10.21437/interspeech.2011-229","title":"State-level data borrowing for low-resource speech recognition based on subspace GMMs","display_name":"State-level data borrowing for low-resource speech recognition based on subspace GMMs","publication_year":2011,"publication_date":"2011-08-27","ids":{"openalex":"https://openalex.org/W139772320","doi":"https://doi.org/10.21437/interspeech.2011-229","mag":"139772320"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2011-229","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2011-229","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2011","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/A5100341993","display_name":"Yanmin Qian","orcid":"https://orcid.org/0000-0002-0314-3790"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanmin Qian","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084286453","display_name":"Daniel Povey","orcid":"https://orcid.org/0000-0002-0611-3634"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Daniel Povey","raw_affiliation_strings":["Microsoft"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100409741","display_name":"Jia Liu","orcid":"https://orcid.org/0000-0003-0383-0934"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jia Liu","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.3164,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.95242252,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"553","last_page":"556"},"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":0.9954000115394592,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9932000041007996,"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/mixture-model","display_name":"Mixture model","score":0.8604243993759155},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8293572068214417},{"id":"https://openalex.org/keywords/subspace-topology","display_name":"Subspace topology","score":0.7712793946266174},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6218230724334717},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6093114614486694},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6079820990562439},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5679134130477905},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5315290093421936},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.5123163461685181},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.48571711778640747},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4328807592391968},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.4285963177680969},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4158143103122711},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.4084811508655548},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33919525146484375}],"concepts":[{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.8604243993759155},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8293572068214417},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.7712793946266174},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6218230724334717},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6093114614486694},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6079820990562439},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5679134130477905},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5315290093421936},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.5123163461685181},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.48571711778640747},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4328807592391968},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.4285963177680969},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4158143103122711},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.4084811508655548},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33919525146484375},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/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},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2011-229","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2011-229","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2011","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W28619450","https://openalex.org/W39446388","https://openalex.org/W1631260214","https://openalex.org/W1932968309","https://openalex.org/W1981706894","https://openalex.org/W2000688218","https://openalex.org/W2123798005","https://openalex.org/W2130414229","https://openalex.org/W2151402979","https://openalex.org/W2152195628","https://openalex.org/W2164499211","https://openalex.org/W2165436104","https://openalex.org/W2166637769","https://openalex.org/W2170306297"],"related_works":["https://openalex.org/W2053269318","https://openalex.org/W2364370872","https://openalex.org/W1980381208","https://openalex.org/W2025614924","https://openalex.org/W4324119469","https://openalex.org/W2164868312","https://openalex.org/W2151402979","https://openalex.org/W2160650576","https://openalex.org/W1992295166","https://openalex.org/W2143508933"],"abstract_inverted_index":{"Large":[0],"vocabulary":[1],"continuous":[2],"speech":[3,144],"recognition":[4],"is":[5,12,24,91],"always":[6],"a":[7,42,94,131],"difficult":[8],"task,":[9],"and":[10,71],"it":[11],"particularly":[13],"so":[14],"for":[15,120,137],"low-resource":[16,146],"languages.":[17],"The":[18,98],"scenario":[19],"we":[20,116,122],"focus":[21],"on":[22,41,62,67],"here":[23],"having":[25],"only":[26],"1":[27],"hour":[28],"of":[29,127],"acoustic":[30],"training":[31],"data":[32,43,58,106,129],"in":[33],"the":[34,48,85,108,112,118,124],"\u201ctarget\u201d":[35],"language.":[36],"This":[37],"paper":[38],"presents":[39],"work":[40],"borrowing":[44,59,105,128],"strategy":[45],"combined":[46],"with":[47],"recently":[49],"proposed":[50],"Subspace":[51],"Gaussian":[52],"Mixture":[53],"Model":[54],"(SGMM).":[55],"We":[56,81],"developed":[57],"strategies":[60],"based":[61,66],"two":[63],"approaches:":[64],"one":[65,72],"minimizing":[68],"K-L":[69],"Divergence,":[70],"that":[73],"also":[74],"takes":[75],"into":[76],"account":[77],"state":[78],"occupation":[79],"counts.":[80],"demonstrate":[82],"improvements":[83],"versus":[84],"baseline":[86],"SGMM":[87],"setup,":[88],"which":[89],"itself":[90],"better":[92],"than":[93],"conventional":[95,138],"HMM-GMM":[96],"system.":[97],"SGMMs":[99],"are":[100],"more":[101],"robustly":[102],"estimated":[103],"by":[104],"from":[107,130],"non-target":[109,132],"language":[110,133],"at":[111],"acousticstate":[113],"level.":[114],"Although":[115],"tested":[117],"approach":[119],"SGMMs,":[121],"expect":[123],"general":[125],"idea":[126],"to":[134],"be":[135],"applicable":[136],"GMMs":[139],"as":[140],"well.":[141],"Index":[142],"Terms:":[143],"recognition,":[145],"language,":[147],"subspace":[148],"gaussian":[149],"mixture":[150],"model":[151]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":8},{"year":2012,"cited_by_count":6}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}