{"id":"https://openalex.org/W2144538561","doi":"https://doi.org/10.1109/icassp.2012.6288289","title":"Learning improved linear transforms for speech recognition","display_name":"Learning improved linear transforms for speech recognition","publication_year":2012,"publication_date":"2012-03-01","ids":{"openalex":"https://openalex.org/W2144538561","doi":"https://doi.org/10.1109/icassp.2012.6288289","mag":"2144538561"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2012.6288289","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288289","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/A5079708487","display_name":"Andrew Senior","orcid":"https://orcid.org/0000-0002-2401-5691"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew Senior","raw_affiliation_strings":["Google, Inc., New York, USA","Google Inc., New York, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, Inc., New York, USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Inc., New York, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087258577","display_name":"Youngmin Cho","orcid":"https://orcid.org/0000-0002-2695-7914"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Youngmin Cho","raw_affiliation_strings":["Department of Computer Science and Engineering, University of California, San Diego, USA","Department of Computer Science and Engineering, UC, San Diego, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of California, San Diego, USA","institution_ids":["https://openalex.org/I36258959"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, UC, San Diego, USA#TAB#","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076635608","display_name":"Jason Weston","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jason Weston","raw_affiliation_strings":["Google, Inc., New York, USA","Google Inc., New York, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, Inc., New York, USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Inc., New York, USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"290","issue":null,"first_page":"1957","last_page":"1960"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9962000250816345,"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/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6431165337562561},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.625319242477417},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6242358088493347},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6157814264297485},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.606269896030426},{"id":"https://openalex.org/keywords/hinge-loss","display_name":"Hinge loss","score":0.592574954032898},{"id":"https://openalex.org/keywords/dimensionality-reduction","display_name":"Dimensionality reduction","score":0.5512585639953613},{"id":"https://openalex.org/keywords/linear-discriminant-analysis","display_name":"Linear discriminant analysis","score":0.548508882522583},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.45254892110824585},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.43604904413223267},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.433135986328125},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.23701825737953186},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.2165021002292633}],"concepts":[{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6431165337562561},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.625319242477417},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6242358088493347},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6157814264297485},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.606269896030426},{"id":"https://openalex.org/C39891107","wikidata":"https://www.wikidata.org/wiki/Q5767098","display_name":"Hinge loss","level":3,"score":0.592574954032898},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.5512585639953613},{"id":"https://openalex.org/C69738355","wikidata":"https://www.wikidata.org/wiki/Q1228929","display_name":"Linear discriminant analysis","level":2,"score":0.548508882522583},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.45254892110824585},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.43604904413223267},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.433135986328125},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.23701825737953186},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.2165021002292633}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp.2012.6288289","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288289","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"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.248.6214","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.248.6214","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://cseweb.ucsd.edu/%7Eyoc002/paper/icassp12_transform.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.308.4729","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.308.4729","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://static.googleusercontent.com/external_content/untrusted_dlcp/research.google.com/en/us/pubs/archive/36901.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.7699999809265137}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W129152403","https://openalex.org/W204572845","https://openalex.org/W1532499126","https://openalex.org/W1989165424","https://openalex.org/W2012897754","https://openalex.org/W2053186076","https://openalex.org/W2080400971","https://openalex.org/W2089322632","https://openalex.org/W2100799972","https://openalex.org/W2106053110","https://openalex.org/W2106554350","https://openalex.org/W2125234026","https://openalex.org/W2130556178","https://openalex.org/W2142416747","https://openalex.org/W2152051032","https://openalex.org/W2152758153","https://openalex.org/W2160773882","https://openalex.org/W2899506040","https://openalex.org/W3028642772","https://openalex.org/W4205130185","https://openalex.org/W4205687621","https://openalex.org/W6605276160","https://openalex.org/W6631637103","https://openalex.org/W6675751002","https://openalex.org/W6756028334","https://openalex.org/W6777926273"],"related_works":["https://openalex.org/W2794812819","https://openalex.org/W2114217318","https://openalex.org/W2587881214","https://openalex.org/W3104072235","https://openalex.org/W2048680804","https://openalex.org/W2370263288","https://openalex.org/W2169311637","https://openalex.org/W3192451249","https://openalex.org/W4367850163","https://openalex.org/W4313343632"],"abstract_inverted_index":{"This":[0],"paper":[1],"explores":[2],"a":[3,10,22,35,46,92],"novel":[4],"large":[5,93],"margin":[6],"approach":[7],"to":[8,30,41,55,86],"learning":[9],"linear":[11,37],"transform":[12,38,73],"for":[13,27,77],"dimensionality":[14],"reduction":[15],"in":[16,91],"speech":[17,95],"recognition.":[18],"The":[19],"method":[20],"assumes":[21],"trained":[23],"Gaussian":[24],"mixture":[25],"model":[26],"each":[28],"class":[29],"be":[31],"discriminated":[32],"and":[33,59,80],"trains":[34],"dimensionality-reducing":[36],"with":[39],"respect":[40],"the":[42,50,53,56,71],"fixed":[43],"model,":[44],"optimizing":[45],"hinge":[47],"loss":[48],"on":[49],"difference":[51],"between":[52],"distance":[54],"nearest":[57],"in-":[58],"out-of-class":[60],"Gaussians":[61],"using":[62],"stochastic":[63],"gradient":[64],"descent.":[65],"Results":[66],"are":[67],"presented":[68],"showing":[69],"that":[70],"learnt":[72],"improves":[74],"state":[75],"classification":[76],"individual":[78],"frames":[79],"reduces":[81],"word":[82],"error":[83],"rate":[84],"compared":[85],"Linear":[87],"Discriminant":[88],"Analysis":[89],"(LDA)":[90],"vocabulary":[94],"recognition":[96],"problem":[97],"even":[98],"after":[99],"discriminative":[100],"training.":[101]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}