{"id":"https://openalex.org/W1576884575","doi":"https://doi.org/10.21437/interspeech.2005-692","title":"Improved MLP structures for data-driven feature extraction for ASR","display_name":"Improved MLP structures for data-driven feature extraction for ASR","publication_year":2005,"publication_date":"2005-09-04","ids":{"openalex":"https://openalex.org/W1576884575","doi":"https://doi.org/10.21437/interspeech.2005-692","mag":"1576884575"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2005-692","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2005-692","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2005","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":[{"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":true,"raw_author_name":"Qifeng Zhu","raw_affiliation_strings":["University of California, Berkeley"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021511902","display_name":"Barry Y. 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 Y. Chen","raw_affiliation_strings":["University of California, Berkeley"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112655592","display_name":"Franti\u0161ek Gr\u00e9zl","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":"Frantisek Grezl","raw_affiliation_strings":["University of California, Berkeley"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112003894","display_name":"Nelson Morgan","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":"Nelson Morgan","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":["https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":1.3701,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.84069613,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"2129","last_page":"2132"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9990000128746033,"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":0.9919000267982483,"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/computer-science","display_name":"Computer science","score":0.7625600099563599},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.7007759809494019},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.6625999212265015},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6141655445098877},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6133444309234619},{"id":"https://openalex.org/keywords/multilayer-perceptron","display_name":"Multilayer perceptron","score":0.6002348065376282},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5848761200904846},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.554552435874939},{"id":"https://openalex.org/keywords/perceptron","display_name":"Perceptron","score":0.4891979694366455},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.48364555835723877},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.42823994159698486},{"id":"https://openalex.org/keywords/dimensionality-reduction","display_name":"Dimensionality reduction","score":0.41223621368408203},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.36891376972198486},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.06745091080665588}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7625600099563599},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.7007759809494019},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.6625999212265015},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6141655445098877},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6133444309234619},{"id":"https://openalex.org/C179717631","wikidata":"https://www.wikidata.org/wiki/Q2991667","display_name":"Multilayer perceptron","level":3,"score":0.6002348065376282},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5848761200904846},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.554552435874939},{"id":"https://openalex.org/C60908668","wikidata":"https://www.wikidata.org/wiki/Q690207","display_name":"Perceptron","level":3,"score":0.4891979694366455},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.48364555835723877},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.42823994159698486},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.41223621368408203},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.36891376972198486},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.06745091080665588},{"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":2,"locations":[{"id":"doi:10.21437/interspeech.2005-692","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2005-692","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2005","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.63.1381","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.63.1381","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/p1584.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6600000262260437,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W169882265","https://openalex.org/W177307080","https://openalex.org/W197151588","https://openalex.org/W1554663460","https://openalex.org/W2038728370","https://openalex.org/W2165712214"],"related_works":["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","https://openalex.org/W2362514456","https://openalex.org/W2136232598"],"abstract_inverted_index":{"In":[0],"this":[1,25],"paper,":[2],"we":[3],"present":[4],"our":[5,119],"recent":[6],"progress":[7],"on":[8,80,123],"multi-layer":[9],"perceptron":[10],"(MLP)":[11],"based":[12],"data-driven":[13],"feature":[14,76],"extraction":[15,77],"using":[16,89,127],"improved":[17],"MLP":[18,50],"structures.":[19],"Four-layer":[20],"MLPs":[21],"are":[22,31],"used":[23],"in":[24],"study.":[26],"Different":[27],"signal":[28],"processing":[29],"methods":[30],"applied":[32,68],"before":[33],"the":[34,38,43,59,90,106,124],"input":[35],"layer":[36,46],"of":[37,47],"MLP.":[39],"We":[40,95],"show":[41],"that":[42],"first":[44],"hidden":[45],"a":[48,70,81,114],"four-layer":[49],"is":[51,67,112],"able":[52],"to":[53,105,118],"detect":[54],"some":[55],"basic":[56],"patterns":[57],"from":[58],"time-frequency":[60],"plane.":[61],"KLT-based":[62],"dimension":[63],"reduction":[64,103],"along":[65],"time":[66],"as":[69],"modulation":[71],"frequency":[72],"filter.":[73],"The":[74],"new":[75],"was":[78],"tested":[79],"large":[82],"vocabulary":[83],"continuous":[84],"speech":[85],"recognition":[86],"(LVCSR)":[87],"task":[88,126],"NIST":[91],"2001":[92],"evaluation":[93],"set.":[94],"achieved":[96],"11.6%":[97],"relative":[98],"word":[99],"error":[100],"rate":[101],"(WER)":[102],"compared":[104,117],"traditional":[107],"PLP-based":[108],"baseline":[109],"feature.":[110],"This":[111],"also":[113],"significant":[115],"improvement":[116],"previously":[120],"published":[121],"results":[122],"same":[125],"MLP-based":[128],"features":[129],"with":[130],"three-layer":[131],"MLPs.":[132],"1.":[133]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}