{"id":"https://openalex.org/W2155084615","doi":"https://doi.org/10.1109/icassp.2003.1198714","title":"Experiments with linear and nonlinear feature transformations in HMM based phone recognition","display_name":"Experiments with linear and nonlinear feature transformations in HMM based phone recognition","publication_year":2003,"publication_date":"2003-10-08","ids":{"openalex":"https://openalex.org/W2155084615","doi":"https://doi.org/10.1109/icassp.2003.1198714","mag":"2155084615"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2003.1198714","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2003.1198714","pdf_url":null,"source":{"id":"https://openalex.org/S4363608982","display_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","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":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","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/A5004058551","display_name":"Panu Somervuo","orcid":"https://orcid.org/0000-0003-3121-4047"},"institutions":[{"id":"https://openalex.org/I133731052","display_name":"University of Helsinki","ror":"https://ror.org/040af2s02","country_code":"FI","type":"education","lineage":["https://openalex.org/I133731052"]},{"id":"https://openalex.org/I1297971548","display_name":"International Computer Science Institute","ror":"https://ror.org/01ewh7m12","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1297971548"]}],"countries":["FI","US"],"is_corresponding":true,"raw_author_name":"P. Somervuo","raw_affiliation_strings":["International Computer Science Institute, Berkeley, CA, USA","Neural Networks Research Centre, Helsinki University of Technology, Finland"],"affiliations":[{"raw_affiliation_string":"International Computer Science Institute, Berkeley, CA, USA","institution_ids":["https://openalex.org/I1297971548"]},{"raw_affiliation_string":"Neural Networks Research Centre, Helsinki University of Technology, Finland","institution_ids":["https://openalex.org/I133731052"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5004058551"],"corresponding_institution_ids":["https://openalex.org/I1297971548","https://openalex.org/I133731052"],"apc_list":null,"apc_paid":null,"fwci":4.664,"has_fulltext":false,"cited_by_count":38,"citation_normalized_percentile":{"value":0.96423249,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"1","issue":null,"first_page":"I","last_page":"52"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11447","display_name":"Blind Source Separation Techniques","score":0.9991999864578247,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9991999864578247,"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/T10320","display_name":"Neural Networks and Applications","score":0.996399998664856,"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":0.9921000003814697,"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":0.7689284086227417},{"id":"https://openalex.org/keywords/linear-discriminant-analysis","display_name":"Linear discriminant analysis","score":0.6933022141456604},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.683361291885376},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6753222942352295},{"id":"https://openalex.org/keywords/concatenation","display_name":"Concatenation (mathematics)","score":0.6598460078239441},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.6239320039749146},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6166182160377502},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.6084054708480835},{"id":"https://openalex.org/keywords/principal-component-analysis","display_name":"Principal component analysis","score":0.5865075588226318},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5759924054145813},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5526736378669739},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.49950170516967773},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.4697948694229126},{"id":"https://openalex.org/keywords/multilayer-perceptron","display_name":"Multilayer perceptron","score":0.4666305482387543},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4622703492641449},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3190658688545227},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18442216515541077}],"concepts":[{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.7689284086227417},{"id":"https://openalex.org/C69738355","wikidata":"https://www.wikidata.org/wiki/Q1228929","display_name":"Linear discriminant analysis","level":2,"score":0.6933022141456604},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.683361291885376},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6753222942352295},{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.6598460078239441},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.6239320039749146},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6166182160377502},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.6084054708480835},{"id":"https://openalex.org/C27438332","wikidata":"https://www.wikidata.org/wiki/Q2873","display_name":"Principal component analysis","level":2,"score":0.5865075588226318},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5759924054145813},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5526736378669739},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.49950170516967773},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.4697948694229126},{"id":"https://openalex.org/C179717631","wikidata":"https://www.wikidata.org/wiki/Q2991667","display_name":"Multilayer perceptron","level":3,"score":0.4666305482387543},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4622703492641449},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3190658688545227},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18442216515541077},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2003.1198714","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2003.1198714","pdf_url":null,"source":{"id":"https://openalex.org/S4363608982","display_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","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":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.12.6985","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.12.6985","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.icsi.berkeley.edu/ftp/global/pub/speech/papers/icassp03-somervuo.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7200000286102295,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1543743156","https://openalex.org/W1548802052","https://openalex.org/W1554663460","https://openalex.org/W1940991344","https://openalex.org/W2077804127","https://openalex.org/W2165712214","https://openalex.org/W4211083646","https://openalex.org/W4388297464","https://openalex.org/W6632561818","https://openalex.org/W6632744857"],"related_works":["https://openalex.org/W2296543338","https://openalex.org/W2098258572","https://openalex.org/W2129974813","https://openalex.org/W2146076056","https://openalex.org/W2793122029","https://openalex.org/W94476185","https://openalex.org/W2159159665","https://openalex.org/W1569922622","https://openalex.org/W2134274699","https://openalex.org/W40124310"],"abstract_inverted_index":{"Feature":[0],"extraction":[1],"is":[2,90],"the":[3,22,29,63,69,80,94,101],"key":[4],"element":[5],"when":[6],"aiming":[7],"at":[8],"robust":[9],"speech":[10],"recognition.":[11],"Both":[12],"linear":[13,46],"and":[14,50],"nonlinear":[15,55],"data-driven":[16],"feature":[17,26,71,95,106],"transformations":[18],"are":[19,35],"applied":[20],"to":[21],"logarithmic":[23],"mel-spectral":[24],"context":[25],"vectors":[27],"in":[28],"TIMIT":[30],"phone":[31],"recognition":[32],"task.":[33],"Transformations":[34],"based":[36,54,73],"on":[37,74],"principal":[38],"component":[39,43],"analysis":[40,44,48,57],"(PCA),":[41],"independent":[42],"(ICA),":[45],"discriminant":[47,56],"(LDA)":[49],"multilayer":[51],"perceptron":[52],"network":[53],"(NLDA).":[58],"All":[59],"four":[60,105],"methods":[61],"outperform":[62],"baseline":[64],"system":[65],"which":[66],"consists":[67],"of":[68,100,103],"standard":[70],"representation":[72],"MFCCs":[75],"(mel-frequency":[76],"cepstral":[77],"coefficients)":[78],"with":[79],"first-order":[81],"deltas,":[82],"using":[83],"a":[84,98],"mixture-of-Gaussians":[85],"HMM":[86],"recognizer.":[87],"Further":[88],"improvement":[89],"gained":[91],"by":[92],"forming":[93],"vector":[96],"as":[97],"concatenation":[99],"outputs":[102],"all":[104],"transformations.":[107]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}