{"id":"https://openalex.org/W2275445995","doi":"https://doi.org/10.21437/interspeech.2013-549","title":"Discriminatively trained sparse inverse covariance matrices for low resource acoustic modeling","display_name":"Discriminatively trained sparse inverse covariance matrices for low resource acoustic modeling","publication_year":2013,"publication_date":"2013-08-25","ids":{"openalex":"https://openalex.org/W2275445995","doi":"https://doi.org/10.21437/interspeech.2013-549","mag":"2275445995"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2013-549","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2013-549","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2013","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/A5100448766","display_name":"Weibin Zhang","orcid":"https://orcid.org/0000-0002-8453-7555"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weibin Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5065856469","display_name":"Pascale Fung","orcid":"https://orcid.org/0000-0002-0628-7132"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pascale Fung","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2350","last_page":"2354"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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/T10822","display_name":"Acoustic Wave Phenomena Research","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9984999895095825,"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/inverse","display_name":"Inverse","score":0.6634775400161743},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6548970937728882},{"id":"https://openalex.org/keywords/covariance","display_name":"Covariance","score":0.6283292174339294},{"id":"https://openalex.org/keywords/covariance-matrix","display_name":"Covariance matrix","score":0.5656657218933105},{"id":"https://openalex.org/keywords/inverse-problem","display_name":"Inverse problem","score":0.4670407176017761},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4478890001773834},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3936923146247864},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3760640025138855},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3493198752403259},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.25861260294914246},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.22430971264839172}],"concepts":[{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.6634775400161743},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6548970937728882},{"id":"https://openalex.org/C178650346","wikidata":"https://www.wikidata.org/wiki/Q201984","display_name":"Covariance","level":2,"score":0.6283292174339294},{"id":"https://openalex.org/C185142706","wikidata":"https://www.wikidata.org/wiki/Q1134404","display_name":"Covariance matrix","level":2,"score":0.5656657218933105},{"id":"https://openalex.org/C135252773","wikidata":"https://www.wikidata.org/wiki/Q1567213","display_name":"Inverse problem","level":2,"score":0.4670407176017761},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4478890001773834},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3936923146247864},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3760640025138855},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3493198752403259},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25861260294914246},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.22430971264839172},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2013-549","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2013-549","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2013","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-64882","is_oa":false,"landing_page_url":"https://repository.hkust.edu.hk/ir/Record/1783.1-64882","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference paper"},{"id":"pmh:oai:repository.ust.hk:1783.1-64882","is_oa":false,"landing_page_url":"http://repository.ust.hk/ir/Record/1783.1-64882","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7699999809265137,"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":13,"referenced_works":["https://openalex.org/W1564719928","https://openalex.org/W1603573007","https://openalex.org/W1972185335","https://openalex.org/W2056636001","https://openalex.org/W2098318492","https://openalex.org/W2099955057","https://openalex.org/W2106554350","https://openalex.org/W2132555912","https://openalex.org/W2151128232","https://openalex.org/W2168653977","https://openalex.org/W2280267974","https://openalex.org/W2296319761","https://openalex.org/W2405215422"],"related_works":["https://openalex.org/W2788344745","https://openalex.org/W2062336688","https://openalex.org/W2910677864","https://openalex.org/W2046078371","https://openalex.org/W2383820648","https://openalex.org/W2886934452","https://openalex.org/W1489099099","https://openalex.org/W2331917905","https://openalex.org/W2024369332","https://openalex.org/W3155039083"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,157],"method":[3,173,212],"to":[4,17,37,60,67,129,137,142,184],"discriminatively":[5],"train":[6],"acoustic":[7,74,111],"models":[8,28,75,112,140],"with":[9,29,113,201],"sparse":[10,30,77,114],"inverse":[11,31,55,78,115,146],"covariance":[12,32,56,79,116,147],"(precision)":[13],"matrices":[14,33,57,80,117],"in":[15],"order":[16],"improve":[18,96,215],"the":[19,39,51,54,62,97,102,107,119,130,145,164,176,192,196,202,216],"model":[20,177,191],"robustness":[21],"when":[22,43],"training":[23,44,93,110,121,136,208],"data":[24,45,168],"is":[25,46,70,89,127,153],"insufficient.":[26],"Acoustic":[27],"were":[34,81],"previously":[35,73],"proposed":[36,211],"address":[38],"problem":[40,108],"of":[41,50,53,64,109,195],"over-fitting":[42],"inadequate.":[47],"Since":[48],"many":[49],"entries":[52],"are":[58],"driven":[59],"zero,":[61],"number":[63],"free":[65],"parameters":[66],"be":[68,185],"estimated":[69],"reduced.":[71],"However,":[72],"using":[76,83,118],"trained":[82],"maximum":[84,204],"likelihood":[85],"(ML)":[86],"training.":[87],"It":[88],"well-known":[90],"that":[91,171],"discriminative":[92,120,135],"can":[94,189,213],"further":[95],"recognition":[98,217],"accuracy.":[99,218],"Therefore,":[100],"for":[101,134],"first":[103],"time,":[104],"we":[105],"study":[106],"method.":[122],"An":[123],"L1":[124],"regularization":[125],"term":[126],"added":[128],"traditional":[131],"objective":[132,151],"function":[133,152],"penalize":[138],"complex":[139],"and":[141,179],"automatically":[143],"sparsify":[144],"matrices.":[148],"The":[149],"new":[150],"optimized":[154],"by":[155],"maximizing":[156],"weak-sense":[158],"auxiliary":[159],"function.":[160],"Experimental":[161],"results":[162],"on":[163],"Wall":[165],"Street":[166],"Journal":[167],"set":[169],"show":[170],"our":[172,210],"effectively":[174],"regularizes":[175],"complexity":[178],"allows":[180],"more":[181],"Gaussian":[182],"components":[183],"trained.":[186],"Therefore":[187],"it":[188],"better":[190],"non-Gaussian":[193],"nature":[194],"speech":[197],"feature":[198],"vectors.":[199],"Compared":[200],"standard":[203],"mutual":[205],"information":[206],"(MMI)":[207],"method,":[209],"significantly":[214],"Copyright":[219],"\u00a9":[220],"2013":[221],"ISCA.":[222]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}