{"id":"https://openalex.org/W45755234","doi":"https://doi.org/10.21437/eurospeech.2003-174","title":"Feature transformations and combinations for improving ASR performance","display_name":"Feature transformations and combinations for improving ASR performance","publication_year":2003,"publication_date":"2003-09-01","ids":{"openalex":"https://openalex.org/W45755234","doi":"https://doi.org/10.21437/eurospeech.2003-174","mag":"45755234"},"language":"en","primary_location":{"id":"doi:10.21437/eurospeech.2003-174","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2003-174","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"8th European Conference on Speech Communication and Technology (Eurospeech 2003)","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/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Panu Somervuo","raw_affiliation_strings":["University of California, Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067651004","display_name":"Barry Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Barry Chen","raw_affiliation_strings":["University of California, Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101999009","display_name":"Qifeng Zhu","orcid":"https://orcid.org/0000-0002-5303-9924"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qifeng Zhu","raw_affiliation_strings":["Helsinki University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Helsinki University of Technology","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4065,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.83625159,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"477","last_page":"480"},"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":0.9976999759674072,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9926000237464905,"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":0.7532678246498108},{"id":"https://openalex.org/keywords/concatenation","display_name":"Concatenation (mathematics)","score":0.6800169944763184},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6769722104072571},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6569074392318726},{"id":"https://openalex.org/keywords/principal-component-analysis","display_name":"Principal component analysis","score":0.6428067684173584},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6159060001373291},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.57854163646698},{"id":"https://openalex.org/keywords/linear-discriminant-analysis","display_name":"Linear discriminant analysis","score":0.5723093748092651},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5602946877479553},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.5461335182189941},{"id":"https://openalex.org/keywords/multilayer-perceptron","display_name":"Multilayer perceptron","score":0.5154600739479065},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4969065487384796},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.49503058195114136},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.4460926651954651},{"id":"https://openalex.org/keywords/perceptron","display_name":"Perceptron","score":0.4426339268684387},{"id":"https://openalex.org/keywords/transformation-matrix","display_name":"Transformation matrix","score":0.43800753355026245},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.4315444231033325},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.30509060621261597},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20698606967926025}],"concepts":[{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.7532678246498108},{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.6800169944763184},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6769722104072571},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6569074392318726},{"id":"https://openalex.org/C27438332","wikidata":"https://www.wikidata.org/wiki/Q2873","display_name":"Principal component analysis","level":2,"score":0.6428067684173584},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6159060001373291},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.57854163646698},{"id":"https://openalex.org/C69738355","wikidata":"https://www.wikidata.org/wiki/Q1228929","display_name":"Linear discriminant analysis","level":2,"score":0.5723093748092651},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5602946877479553},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.5461335182189941},{"id":"https://openalex.org/C179717631","wikidata":"https://www.wikidata.org/wiki/Q2991667","display_name":"Multilayer perceptron","level":3,"score":0.5154600739479065},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4969065487384796},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.49503058195114136},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.4460926651954651},{"id":"https://openalex.org/C60908668","wikidata":"https://www.wikidata.org/wiki/Q690207","display_name":"Perceptron","level":3,"score":0.4426339268684387},{"id":"https://openalex.org/C165443888","wikidata":"https://www.wikidata.org/wiki/Q1482183","display_name":"Transformation matrix","level":3,"score":0.43800753355026245},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.4315444231033325},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.30509060621261597},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20698606967926025},{"id":"https://openalex.org/C74650414","wikidata":"https://www.wikidata.org/wiki/Q11397","display_name":"Classical mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C39920418","wikidata":"https://www.wikidata.org/wiki/Q11476","display_name":"Kinematics","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/eurospeech.2003-174","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2003-174","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"8th European Conference on Speech Communication and Technology (Eurospeech 2003)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.14.5528","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.14.5528","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/panus_eur03.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.7300000190734863}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W1548802052","https://openalex.org/W1554663460","https://openalex.org/W1904457459","https://openalex.org/W2098773974","https://openalex.org/W2104448323","https://openalex.org/W2155084615","https://openalex.org/W2165712214"],"related_works":["https://openalex.org/W2373577936","https://openalex.org/W4387678054","https://openalex.org/W3095575180","https://openalex.org/W2888091758","https://openalex.org/W2134209752","https://openalex.org/W2120446725","https://openalex.org/W1494724239","https://openalex.org/W2111680118","https://openalex.org/W4246803324","https://openalex.org/W2159897332"],"abstract_inverted_index":{"In":[0],"this":[1],"work,":[2],"linear":[3,32],"and":[4,23,35,51,66,70,114,132],"nonlinear":[5],"feature":[6,60,77,98,103,111,134],"transformations":[7,16,28,78],"have":[8],"been":[9],"experimented":[10],"in":[11,88,145],"ASR":[12],"front":[13],"end.":[14],"Unsupervised":[15],"were":[17,29,42,53,109,122],"based":[18,30,136],"on":[19,31,137],"principal":[20],"component":[21,25],"analysis":[22,34],"independent":[24],"analysis.":[26],"Discriminative":[27],"discriminant":[33],"multilayer":[36,138],"perceptron":[37,139],"networks.":[38],"The":[39,141],"acoustic":[40],"models":[41],"trained":[43],"using":[44,55,118,124],"a":[45],"subset":[46],"of":[47,63,75,127],"HUB5":[48],"training":[49],"data":[50],"they":[52],"tested":[54],"OGI":[56],"Numbers":[57],"corpus.":[58],"Baseline":[59],"vector":[61,112],"consisted":[62],"PLP":[64,130],"cepstrum":[65,131],"energy":[67],"with":[68,101],"first":[69],"second":[71],"order":[72],"deltas.":[73],"None":[74],"the":[76,81,89,96,102,125,128,133,146],"could":[79],"outperform":[80],"baseline":[82,97,129],"when":[83,95],"used":[84],"alone,":[85],"but":[86],"improvement":[87],"word":[90,142],"error":[91,143],"rate":[92,144],"was":[93,99,150],"gained":[94],"combined":[100],"transformation":[104],"stream.":[105],"Two":[106],"combination":[107,117,126],"methods":[108],"experimented:":[110],"concatenation":[113],"n-best":[115],"list":[116],"ROVER.":[119],"Best":[120],"results":[121],"obtained":[123],"transform":[135],"network.":[140],"number":[147],"recognition":[148],"task":[149],"reduced":[151],"from":[152],"4.1":[153],"to":[154],"3.1.":[155]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}