{"id":"https://openalex.org/W2295119550","doi":"https://doi.org/10.21437/interspeech.2013-48","title":"Improved feature processing for deep neural networks","display_name":"Improved feature processing for deep neural networks","publication_year":2013,"publication_date":"2013-08-25","ids":{"openalex":"https://openalex.org/W2295119550","doi":"https://doi.org/10.21437/interspeech.2013-48","mag":"2295119550"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2013-48","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2013-48","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2013","raw_type":"proceedings-article"},"type":"conference-paper","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/A5024123814","display_name":"Shakti P. Rath","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shakti P. Rath","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084286453","display_name":"Daniel Povey","orcid":"https://orcid.org/0000-0002-0611-3634"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Daniel Povey","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045351360","display_name":"Karel Vesel\u00fd","orcid":"https://orcid.org/0000-0002-3568-7493"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Karel Vesel\u00fd","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5045539248","display_name":"Ja\u0148 \u010cernock\u00fd","orcid":"https://orcid.org/0000-0002-8800-0210"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jan \u010cernock\u00fd","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":14.8725,"has_fulltext":false,"cited_by_count":188,"citation_normalized_percentile":{"value":0.99401152,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"109","last_page":"113"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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/T10860","display_name":"Speech and Audio Processing","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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7308925986289978},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6310216188430786},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5880999565124512},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5763864517211914},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.43275177478790283},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3555043339729309}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7308925986289978},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6310216188430786},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5880999565124512},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5763864517211914},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.43275177478790283},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3555043339729309},{"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:10.21437/interspeech.2013-48","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2013-48","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2013","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7300000190734863,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W156213964","https://openalex.org/W1524333225","https://openalex.org/W1553004968","https://openalex.org/W2002342963","https://openalex.org/W2072349636","https://openalex.org/W2106554350","https://openalex.org/W2124629003","https://openalex.org/W2125234026","https://openalex.org/W2148154194","https://openalex.org/W2160306971","https://openalex.org/W2160815625","https://openalex.org/W2296748324","https://openalex.org/W2799061466"],"related_works":["https://openalex.org/W2391251536","https://openalex.org/W2977677679","https://openalex.org/W2362198218","https://openalex.org/W1992327129","https://openalex.org/W1984922432","https://openalex.org/W2381986121","https://openalex.org/W1982750869","https://openalex.org/W2375008505","https://openalex.org/W2033914206","https://openalex.org/W2042327336"],"abstract_inverted_index":{"In":[0,111],"this":[1,112],"paper,":[2,113],"we":[3,60,114],"investigate":[4,102,115],"alternative":[5],"ways":[6,103],"of":[7,57,69,82,84,108],"processing":[8],"MFCC-based":[9],"features":[10,71,121,140],"to":[11,16,42,46,91,101,104,118,150],"use":[12],"as":[13],"the":[14,31,44,55,67,80,92,106,109,148],"input":[15,93],"Deep":[17],"Neural":[18],"Networks":[19],"(DNNs).":[20],"Our":[21,128,157],"baseline":[22,136],"is":[23,75,87,131,160,171],"a":[24,85,172],"conventional":[25],"feature":[26,94],"pipeline":[27],"that":[28,62,79],"involves":[29],"splicing":[30,134],"13-dimensional":[32],"front-end":[33],"MFCCs":[34],"across":[35,142],"9":[36,143],"frames,":[37,144],"followed":[38,145],"by":[39,146],"applying":[40],"LDA":[41],"reduce":[43],"dimension":[45,95,107,149],"40":[47],"and":[48,122],"then":[49],"further":[50],"decorrelation":[51],"using":[52,72,154],"MLLT.":[53],"Confirming":[54],"results":[56],"other":[58],"groups,":[59],"show":[61],"speaker":[63,138],"adaptation":[64],"applied":[65],"on":[66],"top":[68],"these":[70],"feature-space":[73],"MLLR":[74],"helpful.":[76],"The":[77],"fact":[78],"number":[81],"parameters":[83],"DNN":[86],"not":[88],"strongly":[89],"sensitive":[90],"(unlike":[96],"GMM-based":[97],"systems)":[98],"motivated":[99],"us":[100],"increase":[105],"features.":[110],"several":[116],"approaches":[117],"derive":[119],"higher-dimensional":[120],"verify":[123],"their":[124],"performance":[125],"with":[126],"DNN.":[127],"best":[129,167],"result":[130,159],"obtained":[132],"from":[133],"our":[135,166],"40-dimensional":[137],"adapted":[139],"again":[141],"reducing":[147],"200":[151],"or":[152],"300":[153],"another":[155],"LDA.":[156],"final":[158],"about":[161],"3%":[162],"absolute":[163],"better":[164],"than":[165],"GMM":[168],"system,":[169],"which":[170],"discriminatively":[173],"trained":[174],"model.":[175]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":17},{"year":2019,"cited_by_count":28},{"year":2018,"cited_by_count":19},{"year":2017,"cited_by_count":28},{"year":2016,"cited_by_count":34},{"year":2015,"cited_by_count":19},{"year":2014,"cited_by_count":11},{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}