{"id":"https://openalex.org/W197151588","doi":"https://doi.org/10.21437/interspeech.2004-337","title":"On using MLP features in LVCSR","display_name":"On using MLP features in LVCSR","publication_year":2004,"publication_date":"2004-10-04","ids":{"openalex":"https://openalex.org/W197151588","doi":"https://doi.org/10.21437/interspeech.2004-337","mag":"197151588"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2004-337","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-337","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2004","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/A5101999009","display_name":"Qifeng Zhu","orcid":"https://orcid.org/0000-0002-5303-9924"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Qifeng Zhu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067651004","display_name":"Barry Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Barry Chen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112003894","display_name":"Nelson Morgan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nelson Morgan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5060979948","display_name":"Andreas Stolcke","orcid":"https://orcid.org/0000-0002-9925-905X"},"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":"Andreas Stolcke","raw_affiliation_strings":["University of California, Berkeley"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101999009"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":11.5532,"has_fulltext":false,"cited_by_count":98,"citation_normalized_percentile":{"value":0.98357914,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"921","last_page":"924"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9973000288009644,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9872000217437744,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.841640830039978},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8357493281364441},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7150881886482239},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.7143040895462036},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6614664196968079},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5868100523948669},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5755740404129028},{"id":"https://openalex.org/keywords/perceptron","display_name":"Perceptron","score":0.5378261208534241},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5227822661399841},{"id":"https://openalex.org/keywords/multilayer-perceptron","display_name":"Multilayer perceptron","score":0.49160489439964294},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.4790133833885193},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.47182899713516235},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.42696359753608704},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.28898632526397705}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.841640830039978},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8357493281364441},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7150881886482239},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.7143040895462036},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6614664196968079},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5868100523948669},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5755740404129028},{"id":"https://openalex.org/C60908668","wikidata":"https://www.wikidata.org/wiki/Q690207","display_name":"Perceptron","level":3,"score":0.5378261208534241},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5227822661399841},{"id":"https://openalex.org/C179717631","wikidata":"https://www.wikidata.org/wiki/Q2991667","display_name":"Multilayer perceptron","level":3,"score":0.49160489439964294},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.4790133833885193},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.47182899713516235},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.42696359753608704},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.28898632526397705},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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":3,"locations":[{"id":"doi:10.21437/interspeech.2004-337","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-337","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2004","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.157.941","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.157.941","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www-speech.sri.com/cgi-bin/run-distill?papers/icslp2004-mlp-lvcsr.ps.gz","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.937.2742","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.937.2742","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://www.sri.com/sites/default/files/publications/on_using_mlp_features_in_lvcsr.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.75,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W114847577","https://openalex.org/W169882265","https://openalex.org/W2070725064","https://openalex.org/W2103203308","https://openalex.org/W2106554350","https://openalex.org/W2137644731","https://openalex.org/W2142694085","https://openalex.org/W2165712214"],"related_works":["https://openalex.org/W2167155152","https://openalex.org/W161037869","https://openalex.org/W2076543106","https://openalex.org/W2523437662","https://openalex.org/W89844371","https://openalex.org/W2019891950","https://openalex.org/W2085842814","https://openalex.org/W4286643620","https://openalex.org/W4387048144","https://openalex.org/W2492135063"],"abstract_inverted_index":{"One":[0],"of":[1,30,33,39,110],"the":[2,7,37,40,98,119,142,152],"major":[3],"research":[4],"thrusts":[5],"in":[6,20,55,133],"speech":[8,22,137],"group":[9],"at":[10],"ICSI":[11],"is":[12],"to":[13,96,101],"use":[14],"Multi-Layer":[15],"Perceptron":[16],"(MLP)":[17],"based":[18],"features":[19,42,50,54,63,112,127],"automatic":[21],"recognition":[23,131,138],"(ASR).":[24],"This":[25],"paper":[26,77],"presents":[27],"a":[28,104],"study":[29],"three":[31],"aspects":[32],"this":[34],"effort:":[35],"1)":[36],"properties":[38],"MLP":[41,49,62,80,126],"which":[43,88],"make":[44,97],"them":[45],"useful,":[46],"2)":[47],"incorporating":[48],"together":[51],"with":[52,148],"PLP":[53],"ASR,":[56],"and":[57,64,73,159],"3)":[58],"possible":[59],"redundancy":[60],"between":[61],"more":[65,108],"conventional":[66],"system":[67,74,160],"refinements":[68],"such":[69],"as":[70],"discriminative":[71,157],"training":[72,158],"combination.":[75],"The":[76],"shows":[78],"that":[79,84,125],"transformations":[81],"yield":[82],"variables":[83],"have":[85],"regular":[86],"distributions,":[87],"can":[89,113,128],"be":[90,115],"further":[91],"modified":[92],"by":[93,103],"using":[94],"logarithm":[95],"distribution":[99],"easier":[100],"model":[102],"Gaussian-HMM.":[105],"Two":[106],"or":[107],"vectors":[109],"these":[111],"easily":[114],"combined":[116],"without":[117],"increasing":[118],"feature":[120],"dimension.":[121],"Recognition":[122],"results":[123],"show":[124],"significantly":[129],"improve":[130],"performance":[132],"large":[134],"vocabulary":[135],"continuous":[136],"(LVCSR)":[139],"tasks":[140],"for":[141],"NIST":[143],"2001":[144],"Hub-5":[145],"evaluation":[146],"set":[147],"models":[149],"trained":[150],"on":[151],"Switchboard":[153],"Corpus,":[154],"even":[155],"when":[156],"combination":[161],"are":[162],"used.":[163],"1.":[164]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":10},{"year":2012,"cited_by_count":5}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}