{"id":"https://openalex.org/W1513984940","doi":"https://doi.org/10.1109/icassp.2015.7178828","title":"On the importance of modeling and robustness for deep neural network feature","display_name":"On the importance of modeling and robustness for deep neural network feature","publication_year":2015,"publication_date":"2015-04-01","ids":{"openalex":"https://openalex.org/W1513984940","doi":"https://doi.org/10.1109/icassp.2015.7178828","mag":"1513984940"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2015.7178828","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178828","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5001306222","display_name":"Shuo-Yiin Chang","orcid":null},"institutions":[{"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"]},{"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":"Shuo-Yiin Chang","raw_affiliation_strings":["EECS Department, University of California-Berkeley, Berkeley, CA, USA","International Computer Science Institute, Berkeley, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EECS Department, University of California-Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"International Computer Science Institute, Berkeley, CA, USA","institution_ids":["https://openalex.org/I1297971548"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025957537","display_name":"Steven Wegmann","orcid":null},"institutions":[{"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":["US"],"is_corresponding":false,"raw_author_name":"Steven Wegmann","raw_affiliation_strings":["International Computer Science Institute, Berkeley, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Computer Science Institute, Berkeley, CA, USA","institution_ids":["https://openalex.org/I1297971548"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.8969,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.95207861,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"2","issue":null,"first_page":"4530","last_page":"4534"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998000264167786,"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/T11309","display_name":"Music and Audio Processing","score":0.9980000257492065,"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/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.8443214893341064},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.788947343826294},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7843512892723083},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6071776151657104},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5958304405212402},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5938407182693481},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5830176472663879},{"id":"https://openalex.org/keywords/test-data","display_name":"Test data","score":0.5283818244934082},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5227370858192444},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5166733264923096},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4732190668582916},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.43622586131095886}],"concepts":[{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.8443214893341064},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.788947343826294},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7843512892723083},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6071776151657104},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5958304405212402},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5938407182693481},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5830176472663879},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.5283818244934082},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5227370858192444},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5166733264923096},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4732190668582916},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.43622586131095886},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2015.7178828","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178828","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W75470185","https://openalex.org/W197151588","https://openalex.org/W1553004968","https://openalex.org/W1591607137","https://openalex.org/W1627087495","https://openalex.org/W1978741356","https://openalex.org/W1993882792","https://openalex.org/W2030937226","https://openalex.org/W2048608953","https://openalex.org/W2072128103","https://openalex.org/W2072349636","https://openalex.org/W2088489891","https://openalex.org/W2113427327","https://openalex.org/W2121573996","https://openalex.org/W2143612262","https://openalex.org/W2147768505","https://openalex.org/W2160815625","https://openalex.org/W2165712214","https://openalex.org/W2188183693","https://openalex.org/W2293634267","https://openalex.org/W2395106899","https://openalex.org/W6603060513","https://openalex.org/W6632891567","https://openalex.org/W6636776493","https://openalex.org/W6678429839","https://openalex.org/W6696934422"],"related_works":["https://openalex.org/W2053269318","https://openalex.org/W2364370872","https://openalex.org/W2349769824","https://openalex.org/W2097963413","https://openalex.org/W4317383455","https://openalex.org/W2548511587","https://openalex.org/W2422472940","https://openalex.org/W2019475500","https://openalex.org/W2548162870","https://openalex.org/W2144773493"],"abstract_inverted_index":{"A":[0],"large":[1],"body":[2],"of":[3,89,103,112,201],"research":[4],"has":[5],"shown":[6],"that":[7,27,78,158,175,180,227,232],"acoustic":[8],"features":[9,30,35,51,73,211,253],"for":[10,162],"speech":[11,168],"recognition":[12,63,169,202],"can":[13],"be":[14],"learned":[15,29,72],"from":[16,205],"data":[17,46,59,77,97],"using":[18,120],"neural":[19],"networks":[20],"with":[21,146],"multiple":[22],"hidden":[23],"layers":[24],"(DNNs)":[25],"and":[26,139,153,212,217,243,258,263],"these":[28,71],"are":[31,204],"superior":[32,187],"to":[33,48,57,61,75,83,93,95,117,188],"standard":[34],"(e.g.,":[36],"MFCCs).":[37],"However,":[38],"this":[39,106],"superiority":[40],"is":[41,52,68,79,98,185],"usually":[42],"demonstrated":[43],"when":[44],"the":[45,50,58,110,121,141,166,189,194,199,209,221,251,255,266],"used":[47,60],"learn":[49],"very":[53],"similar":[54],"in":[55,81,193,220,254,265],"character":[56,82],"test":[62],"performance.":[64],"An":[65],"open":[66],"question":[67],"how":[69],"well":[70,249],"generalize":[74,94],"realistic":[76],"different":[80],"their":[84],"training":[85,145],"data.":[86],"The":[87,125,149],"ability":[88],"a":[90,99,154,176,228,234],"feature":[91,115,178,230],"representation":[92,179,231],"unfamiliar":[96],"highly":[100],"desirable":[101],"form":[102],"robustness.":[104],"In":[105],"paper":[107],"we":[108,159,225],"investigate":[109],"robustness":[111],"two":[113,195],"DNN-based":[114,177,210,229],"sets":[116],"training/test":[118,131],"mismatch":[119],"ICSI":[122],"meeting":[123],"corpus.":[124],"experiments":[126,150],"were":[127],"performed":[128],"under":[129],"3":[130],"scenarios:":[132],"(1)":[133],"matched":[134,137,196,256],"near-field":[135,144],"(2)":[136],"far-field":[138,147],"(3)":[140],"mismatched":[142,222,267],"condition":[143],"testing.":[148],"leverage":[151],"simulation":[152],"novel":[155],"sampling":[156],"process":[157],"have":[160,214],"developed":[161],"diagnostic":[163,172],"analysis":[164,173],"within":[165],"HMM-based":[167],"framework.":[170],"First,":[171],"shows":[174],"uses":[181,233],"MFCC":[182,191],"inputs":[183],"(MFCC-DNN)":[184],"indeed":[186],"corresponding":[190],"baselines":[192],"scenarios":[197,257],"where":[198],"source":[200],"errors":[203],"incorrect":[206],"model,":[207],"but":[208],"MFCCs":[213,262],"nearly":[215,247],"identical":[216],"poor":[218],"performance":[219],"scenario.":[223,268],"Second,":[224],"show":[226],"more":[235],"robust":[236],"input,":[237],"namely":[238],"power":[239],"normalized":[240],"spectrum":[241],"(PNS)":[242],"Gabor":[244],"filters,":[245],"performs":[246],"as":[248,250],"MFCC-DNN":[252],"much":[259],"better":[260],"than":[261],"MFCC-DNNs":[264]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}