{"id":"https://openalex.org/W2164225659","doi":"https://doi.org/10.1109/icassp.2009.4960443","title":"Large margin semi-tied covariance transforms for discriminative training","display_name":"Large margin semi-tied covariance transforms for discriminative training","publication_year":2009,"publication_date":"2009-04-01","ids":{"openalex":"https://openalex.org/W2164225659","doi":"https://doi.org/10.1109/icassp.2009.4960443","mag":"2164225659"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2009.4960443","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960443","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Acoustics, Speech and Signal 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/A5079994647","display_name":"George Saon","orcid":"https://orcid.org/0009-0004-6837-5009"},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"George Saon","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA"],"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]}]},{"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/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Povey","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA"],"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010878109","display_name":"Hagen Soltau","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hagen Soltau","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA"],"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5079994647"],"corresponding_institution_ids":["https://openalex.org/I4210114115"],"apc_list":null,"apc_paid":null,"fwci":3.1614,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.9252938,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"3753","last_page":"3756"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"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":0.9994000196456909,"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":0.993399977684021,"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":0.9107000231742859,"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":0.9659055471420288},{"id":"https://openalex.org/keywords/covariance","display_name":"Covariance","score":0.7959940433502197},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.662628710269928},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6582619547843933},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5951991677284241},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5343244671821594},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.5072759985923767},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4480639696121216},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.41544416546821594},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.41048648953437805},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3924473524093628},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3717638850212097},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2648794651031494},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.10635209083557129}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.9659055471420288},{"id":"https://openalex.org/C178650346","wikidata":"https://www.wikidata.org/wiki/Q201984","display_name":"Covariance","level":2,"score":0.7959940433502197},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.662628710269928},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6582619547843933},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5951991677284241},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5343244671821594},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.5072759985923767},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4480639696121216},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.41544416546821594},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.41048648953437805},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3924473524093628},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3717638850212097},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2648794651031494},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.10635209083557129},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2009.4960443","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960443","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.538.6867","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.538.6867","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://wiki.inf.ed.ac.uk/twiki/pub/CSTR/Listen/lm_stc.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.7799999713897705}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W43454013","https://openalex.org/W169377849","https://openalex.org/W233468731","https://openalex.org/W2002342963","https://openalex.org/W2034292845","https://openalex.org/W2097003869","https://openalex.org/W2097635532","https://openalex.org/W2098794778","https://openalex.org/W2111977926","https://openalex.org/W2120019470","https://openalex.org/W2124629003","https://openalex.org/W2125234026","https://openalex.org/W2126033156","https://openalex.org/W2147467930","https://openalex.org/W2150907703","https://openalex.org/W2164115090","https://openalex.org/W3142174018","https://openalex.org/W3149335959","https://openalex.org/W6607023580","https://openalex.org/W6608993760","https://openalex.org/W6683953266"],"related_works":["https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W259157601","https://openalex.org/W2142324288","https://openalex.org/W2146591867","https://openalex.org/W1965383186","https://openalex.org/W2075383893","https://openalex.org/W156213964","https://openalex.org/W2050960118"],"abstract_inverted_index":{"We":[0,61],"discuss":[1],"the":[2,9,35,40,43,49,63],"applicability":[3],"of":[4,11,18,42,52,65],"large":[5],"margin":[6],"techniques":[7,47],"to":[8,38],"problem":[10],"estimating":[12],"linear":[13],"transforms":[14,67],"for":[15,30,80],"discriminative":[16,45,72],"training":[17,46,73],"a":[19,56,81],"semi-tied":[20],"covariance":[21],"(STC)":[22],"model.":[23],"Since":[24],"STC":[25],"models":[26],"are":[27],"good":[28],"proxies":[29],"full-covariance":[31],"(FC)":[32],"Gaussian":[33],"models,":[34],"idea":[36],"is":[37],"combine":[39],"benefit":[41],"latest":[44],"and":[48,70],"modeling":[50],"advantage":[51],"FC":[53],"Gaussians":[54],"at":[55],"much":[57],"lower":[58],"computational":[59],"cost.":[60],"study":[62],"interaction":[64],"these":[66],"with":[68],"feature-space":[69],"model-space":[71],"on":[74],"state-of-the-art":[75],"speaker":[76],"adapted":[77],"systems":[78],"built":[79],"large-scale":[82],"Arabic":[83],"broadcast":[84],"news":[85],"transcription":[86],"task.":[87]},"counts_by_year":[{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":3}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}