{"id":"https://openalex.org/W2145831960","doi":"https://doi.org/10.1109/icassp.2004.1326103","title":"An evaluation of a nonlinear feature transformation for conversational speech recognition","display_name":"An evaluation of a nonlinear feature transformation for conversational speech recognition","publication_year":2004,"publication_date":"2004-09-28","ids":{"openalex":"https://openalex.org/W2145831960","doi":"https://doi.org/10.1109/icassp.2004.1326103","mag":"2145831960"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2004.1326103","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2004.1326103","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Conference on Acoustics, Speech, and Signal Processing","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/A5113697338","display_name":"Mohamed Kamal Omar","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"M.K. Omar","raw_affiliation_strings":["University of Illinois, Urbana-Champaign, Urbana-Champaign, IL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois, Urbana-Champaign, Urbana-Champaign, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003725957","display_name":"Brian Kingsbury","orcid":"https://orcid.org/0000-0002-1343-6837"},"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":"B. Kingsbury","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA"],"raw_orcid":null,"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":2,"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":"1","issue":null,"first_page":"I","last_page":"785"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9983999729156494,"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":0.9925000071525574,"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/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.738739550113678},{"id":"https://openalex.org/keywords/linear-discriminant-analysis","display_name":"Linear discriminant analysis","score":0.7323234677314758},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7144944071769714},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.692118763923645},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6245368719100952},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.537470281124115},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.5313212275505066},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.5145635008811951},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4785112142562866},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.42586076259613037},{"id":"https://openalex.org/keywords/kernel-fisher-discriminant-analysis","display_name":"Kernel Fisher discriminant analysis","score":0.41978731751441956},{"id":"https://openalex.org/keywords/facial-recognition-system","display_name":"Facial recognition system","score":0.07860934734344482}],"concepts":[{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.738739550113678},{"id":"https://openalex.org/C69738355","wikidata":"https://www.wikidata.org/wiki/Q1228929","display_name":"Linear discriminant analysis","level":2,"score":0.7323234677314758},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7144944071769714},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.692118763923645},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6245368719100952},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.537470281124115},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.5313212275505066},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.5145635008811951},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4785112142562866},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.42586076259613037},{"id":"https://openalex.org/C181367576","wikidata":"https://www.wikidata.org/wiki/Q6394184","display_name":"Kernel Fisher discriminant analysis","level":4,"score":0.41978731751441956},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.07860934734344482},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2004.1326103","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2004.1326103","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Conference on Acoustics, Speech, and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6899999976158142,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W13802415","https://openalex.org/W203708726","https://openalex.org/W1591607137","https://openalex.org/W1667165204","https://openalex.org/W2046245205","https://openalex.org/W2070545637","https://openalex.org/W2099262442","https://openalex.org/W2106554350","https://openalex.org/W2124629003","https://openalex.org/W2135722170","https://openalex.org/W2163718582","https://openalex.org/W2545353681","https://openalex.org/W2567948266","https://openalex.org/W6684206990"],"related_works":["https://openalex.org/W2141981133","https://openalex.org/W2386228546","https://openalex.org/W2086055175","https://openalex.org/W2365801610","https://openalex.org/W2388048830","https://openalex.org/W2150796457","https://openalex.org/W2902887112","https://openalex.org/W2566759662","https://openalex.org/W2016459271","https://openalex.org/W2788610776"],"abstract_inverted_index":{"We":[0],"test":[1,17],"the":[2,19,45,65,104,108,112,120],"nonlinear":[3],"symplectic":[4],"maximum-likelihood":[5,51],"transformation":[6,43,53],"(SMLT)":[7],"on":[8,37,67,134],"two":[9,143],"large-vocabulary,":[10],"conversational":[11],"speech":[12],"recognition":[13,70],"tasks:":[14],"IBM's":[15],"Superhuman":[16],"and":[18,41,73,83,97,137],"DARPA":[20],"2003":[21],"Rich":[22],"Transcription":[23],"(RT03)":[24],"test.":[25],"Features":[26],"in":[27,146],"these":[28,76],"tests":[29,63,77],"are":[30,93,128,140],"computed":[31],"via":[32],"linear":[33,52],"discriminant":[34],"analysis":[35],"(LDA)":[36],"spliced":[38],"MFCC":[39],"features":[40,47],"subsequent":[42],"of":[44,64,90],"projected":[46],"using":[48,142],"either":[49],"a":[50,79],"(MLLT),":[54],"an":[55,101,125,131,147],"SMLT,":[56],"or":[57],"both.":[58],"In":[59],"contrast":[60],"to":[61],"previous":[62],"SMLT":[66,145],"TIMIT":[68],"phone":[69],"with":[71,130],"static":[72],"delta":[74],"MFCC,":[75],"use":[78],"more":[80,117],"difficult":[81],"task":[82],"very":[84],"different":[85],"features.":[86],"The":[87],"four":[88],"results":[89],"this":[91],"work":[92],"that":[94],"both":[95],"LDA+MLLT":[96,105,126],"LDA+SMLT":[98,109],"systems":[99],"outperform":[100],"LDA-only":[102],"system;":[103],"system":[106,110,127,133],"outperforms":[107],"(but":[111],"MLLT":[113],"has":[114],"20":[115],"times":[116],"parameters":[118],"than":[119],"SMLT);":[121],"small":[122],"improvements":[123,139],"over":[124],"obtained":[129,141],"LDA+MLLT+SMLT":[132,148],"well-matched":[135],"material;":[136],"no":[138],"class-dependent":[144],"system.":[149]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}