{"id":"https://openalex.org/W1967269193","doi":"https://doi.org/10.1109/icassp.2002.5743866","title":"Application of variational Bayesian PCA for speech feature extraction","display_name":"Application of variational Bayesian PCA for speech feature extraction","publication_year":2002,"publication_date":"2002-05-01","ids":{"openalex":"https://openalex.org/W1967269193","doi":"https://doi.org/10.1109/icassp.2002.5743866","mag":"1967269193"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2002.5743866","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2002.5743866","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"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/A5000031464","display_name":"Oh\u2010Wook Kwon","orcid":"https://orcid.org/0000-0002-5301-126X"},"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":true,"raw_author_name":"Oh-Wook Kwon","raw_affiliation_strings":["Institute for Neural Computation, University of California, San Diego, La Jolla, CA, USA","Institute for Neural Computation, University of California, San Diego, 8500 Oilman Drive, La Jolla, 92059-0523, USA"],"affiliations":[{"raw_affiliation_string":"Institute for Neural Computation, University of California, San Diego, La Jolla, CA, USA","institution_ids":["https://openalex.org/I36258959"]},{"raw_affiliation_string":"Institute for Neural Computation, University of California, San Diego, 8500 Oilman Drive, La Jolla, 92059-0523, USA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022408850","display_name":"Te-Won Lee","orcid":null},"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":"Te-Won Lee","raw_affiliation_strings":["Institute for Neural Computation, University of California, San Diego, La Jolla, CA, USA","Institute for Neural Computation, University of California, San Diego, 8500 Oilman Drive, La Jolla, 92059-0523, USA"],"affiliations":[{"raw_affiliation_string":"Institute for Neural Computation, University of California, San Diego, La Jolla, CA, USA","institution_ids":["https://openalex.org/I36258959"]},{"raw_affiliation_string":"Institute for Neural Computation, University of California, San Diego, 8500 Oilman Drive, La Jolla, 92059-0523, USA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109557032","display_name":"Kwokleung Chan","orcid":null},"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":"Kwokleung Chan","raw_affiliation_strings":["Institute for Neural Computation, University of California, San Diego, La Jolla, CA, USA","Institute for Neural Computation, University of California, San Diego, 8500 Oilman Drive, La Jolla, 92059-0523, USA"],"affiliations":[{"raw_affiliation_string":"Institute for Neural Computation, University of California, San Diego, La Jolla, CA, USA","institution_ids":["https://openalex.org/I36258959"]},{"raw_affiliation_string":"Institute for Neural Computation, University of California, San Diego, 8500 Oilman Drive, La Jolla, 92059-0523, USA","institution_ids":["https://openalex.org/I36258959"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5000031464"],"corresponding_institution_ids":["https://openalex.org/I36258959"],"apc_list":null,"apc_paid":null,"fwci":1.9449,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.84153461,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"I","last_page":"825"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9954000115394592,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9926999807357788,"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/timit","display_name":"TIMIT","score":0.818472146987915},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.6884865760803223},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.6755133867263794},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6649590134620667},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6606270670890808},{"id":"https://openalex.org/keywords/principal-component-analysis","display_name":"Principal component analysis","score":0.6141635179519653},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.595978319644928},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5580824017524719},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.5345930457115173},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5191218256950378},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.502629280090332},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.4956871271133423},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4954026937484741},{"id":"https://openalex.org/keywords/maximization","display_name":"Maximization","score":0.4357939064502716},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4272938072681427},{"id":"https://openalex.org/keywords/expectation\u2013maximization-algorithm","display_name":"Expectation\u2013maximization algorithm","score":0.42056962847709656},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.39398691058158875},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.33047711849212646},{"id":"https://openalex.org/keywords/maximum-likelihood","display_name":"Maximum likelihood","score":0.2914543151855469},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.1258838176727295},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08061456680297852}],"concepts":[{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.818472146987915},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.6884865760803223},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.6755133867263794},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6649590134620667},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6606270670890808},{"id":"https://openalex.org/C27438332","wikidata":"https://www.wikidata.org/wiki/Q2873","display_name":"Principal component analysis","level":2,"score":0.6141635179519653},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.595978319644928},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5580824017524719},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.5345930457115173},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5191218256950378},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.502629280090332},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.4956871271133423},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4954026937484741},{"id":"https://openalex.org/C2776330181","wikidata":"https://www.wikidata.org/wiki/Q18358244","display_name":"Maximization","level":2,"score":0.4357939064502716},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4272938072681427},{"id":"https://openalex.org/C182081679","wikidata":"https://www.wikidata.org/wiki/Q1275153","display_name":"Expectation\u2013maximization algorithm","level":3,"score":0.42056962847709656},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.39398691058158875},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.33047711849212646},{"id":"https://openalex.org/C49781872","wikidata":"https://www.wikidata.org/wiki/Q1045555","display_name":"Maximum likelihood","level":2,"score":0.2914543151855469},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1258838176727295},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08061456680297852},{"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/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2002.5743866","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2002.5743866","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE International Conference on Acoustics Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5699999928474426}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W88081813","https://openalex.org/W1585842607","https://openalex.org/W1906499012","https://openalex.org/W1940991344","https://openalex.org/W2091571775","https://openalex.org/W2103139809","https://openalex.org/W2125027820","https://openalex.org/W2146610201","https://openalex.org/W2151454335","https://openalex.org/W2294460823","https://openalex.org/W4285719527","https://openalex.org/W6603616073","https://openalex.org/W6673457980","https://openalex.org/W6682350343","https://openalex.org/W6696835939","https://openalex.org/W7011386669"],"related_works":["https://openalex.org/W2473373438","https://openalex.org/W3009295899","https://openalex.org/W2370972896","https://openalex.org/W2368486525","https://openalex.org/W2077224612","https://openalex.org/W2153481672","https://openalex.org/W2153238387","https://openalex.org/W2052112670","https://openalex.org/W4312864369","https://openalex.org/W2048014685"],"abstract_inverted_index":{"In":[0,58],"a":[1,77],"standard":[2],"mel-frequency":[3,45],"cepstral":[4],"coefficient-based":[5],"speech":[6,96,114],"recognizer,":[7],"it":[8],"is":[9],"common":[10],"to":[11,28],"use":[12,29],"the":[13,18,42,50,59,63,67,81,85,88,94,108,111],"same":[14],"feature":[15],"dimension":[16],"and":[17,32,66,104,123],"number":[19,34,68],"of":[20,35,62,69,76,80,84,102,110,120],"Gaussian":[21,64],"mixtures":[22,36,65,70],"for":[23,37,113],"all":[24],"subunits.":[25],"We":[26,40,106],"proposed":[27],"different":[30,33],"transformations":[31,43],"each":[38],"subunit.":[39],"obtained":[41],"from":[44],"band":[46],"energies":[47],"by":[48,116],"using":[49],"variational":[51],"Bayesian":[52],"principal":[53],"component":[54],"analysis":[55],"(PCA)":[56],"method.":[57],"method,":[60],"hyperparameters":[61],"are":[71],"automatically":[72],"learned":[73],"through":[74],"maximization":[75],"lower":[78],"bound":[79],"evidence":[82],"instead":[83],"likelihood":[86,91],"in":[87],"conventional":[89],"maximum":[90],"paradigm.":[92],"Analyzing":[93],"TIMIT":[95],"data,":[97],"we":[98],"revealed":[99],"intrinsic":[100],"structures":[101],"vowels":[103],"consonants.":[105],"demonstrated":[107],"userfulness":[109],"method":[112],"recognition":[115],"performing":[117],"phoneme":[118],"classification":[119],"/b/,":[121],"/d/":[122],"/g/":[124],"phonemes.":[125]},"counts_by_year":[{"year":2015,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}