{"id":"https://openalex.org/W2964261986","doi":null,"title":"Learning linearly separable features for speech recognition using convolutional neural networks","display_name":"Learning linearly separable features for speech recognition using convolutional neural networks","publication_year":2015,"publication_date":"2015-01-01","ids":{"openalex":"https://openalex.org/W2964261986","mag":"2964261986"},"language":"en","primary_location":{"id":"pmh:oai:infoscience.tind.io:210028","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1412.7110","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I5124864","host_organization_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","host_organization_lineage":["https://openalex.org/I5124864"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"report"},"volume":null,"type":"report","is_traditional":false,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://arxiv.org/abs/1412.7110","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064459820","display_name":"Dimitri Palaz","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Dimitri Palaz","raw_affiliation_strings":["Idiap Research Institute, Martigny-Combe, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Martigny-Combe, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043551083","display_name":"Mathew Magimai.-Doss","orcid":"https://orcid.org/0000-0002-8714-1409","observed_orcids":["https://orcid.org/0000-0002-8714-1409"]},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Mathew Magimai.-Doss","raw_affiliation_strings":["Idiap Research Institute, Martigny-Combe, Switzerland"],"raw_orcid":"https://orcid.org/0000-0002-8714-1409","affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Martigny-Combe, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053915453","display_name":"Ronan Collobert","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Ronan Collobert","raw_affiliation_strings":["Idiap Research Institute, Martigny-Combe, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Martigny-Combe, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I7495430"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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/T10860","display_name":"Speech and Audio Processing","score":9.999999747378752e-05,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.0,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-recognition","display_name":"speech recognition","score":0.6909999847412109},{"id":"https://openalex.org/keywords/convolutional-neural-networks","display_name":"convolutional neural networks","score":0.9819999933242798},{"id":"https://openalex.org/keywords/linear-classifiers","display_name":"linear classifiers","score":0.6420000195503235},{"id":"https://openalex.org/keywords/phoneme-recognition","display_name":"phoneme recognition","score":0.8080000281333923},{"id":"https://openalex.org/keywords/continuous-speech-recognition","display_name":"continuous speech recognition","score":0.6850000023841858},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"feature extraction","score":0.42899999022483826},{"id":"https://openalex.org/keywords/mel-frequency-cepstral-coefficients","display_name":"Mel-frequency cepstral coefficients","score":0.5740000009536743},{"id":"https://openalex.org/keywords/plp","display_name":"PLP","score":0.7829999923706055},{"id":"https://openalex.org/keywords/cepstral-features","display_name":"cepstral features","score":0.6579999923706055}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7770557403564453},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.771706223487854},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.7038912773132324},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6573061943054199},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5582980513572693},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5112369060516357},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.4954577684402466},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4862312376499176},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.46885475516319275},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.46253326535224915},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.46051493287086487},{"id":"https://openalex.org/C59883199","wikidata":"https://www.wikidata.org/wiki/Q1826438","display_name":"Linear predictive coding","level":3,"score":0.4546211361885071},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.4515957534313202}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:infoscience.tind.io:210028","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1412.7110","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I5124864","host_organization_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","host_organization_lineage":["https://openalex.org/I5124864"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"report"},{"id":"pmh:oai:infoscience.epfl.ch:210028","doi":null,"is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/210028","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I5124864","host_organization_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","host_organization_lineage":["https://openalex.org/I5124864"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"mag:2964261986","doi":null,"is_oa":false,"landing_page_url":"https://dblp.uni-trier.de/db/conf/iclr/iclr2015w.html#PalazMC14","pdf_url":null,"source":{"id":"https://openalex.org/S4306419637","display_name":"International Conference on Learning Representations","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"International Conference on Learning Representations","raw_type":null}],"best_oa_location":{"id":"pmh:oai:infoscience.tind.io:210028","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1412.7110","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I5124864","host_organization_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","host_organization_lineage":["https://openalex.org/I5124864"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"report"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W88081813","https://openalex.org/W169539560","https://openalex.org/W183625566","https://openalex.org/W753012316","https://openalex.org/W811578723","https://openalex.org/W1969851134","https://openalex.org/W1993882792","https://openalex.org/W2035305631","https://openalex.org/W2077804127","https://openalex.org/W2090861223","https://openalex.org/W2103088716","https://openalex.org/W2107789863","https://openalex.org/W2112739286","https://openalex.org/W2122028591","https://openalex.org/W2123811694","https://openalex.org/W2127375207","https://openalex.org/W2132037657","https://openalex.org/W2136922672","https://openalex.org/W2148154194","https://openalex.org/W2155273149","https://openalex.org/W2160815625","https://openalex.org/W2168249605","https://openalex.org/W2408093180","https://openalex.org/W3028642772"],"related_works":["https://openalex.org/W2145203520","https://openalex.org/W7028400246","https://openalex.org/W1639210279","https://openalex.org/W7065700722","https://openalex.org/W7074593857","https://openalex.org/W562837778","https://openalex.org/W3099202502","https://openalex.org/W2888451110","https://openalex.org/W424869780","https://openalex.org/W7045523659"],"abstract_inverted_index":{"Automatic":[0],"speech":[1,24,27,54,81],"recognition":[2,74,82],"systems":[3],"usually":[4],"rely":[5],"on":[6,19,72,77],"spectral-based":[7],"features,":[8],"such":[9,22,116],"as":[10,56,130],"MFCC":[11],"of":[12,95],"PLP.":[13],"These":[14],"features":[15,109,129],"are":[16],"extracted":[17],"based":[18,70,125],"prior":[20],"knowledge":[21],"as,":[23],"perception":[25],"or/and":[26],"production.":[28],"Recently,":[29],"convolutional":[30],"neural":[31],"networks":[32],"have":[33],"been":[34],"shown":[35,61],"to":[36,39,62],"be":[37],"able":[38],"estimate":[40],"phoneme":[41,73],"conditional":[42],"probabilities":[43],"in":[44,99],"a":[45],"completely":[46],"data-driven":[47],"manner,":[48],"i.e.":[49],"using":[50,84,127],"directly":[51],"temporal":[52],"raw":[53,111],"signal":[55],"input.":[57,131],"This":[58],"system":[59,71,117,126],"was":[60],"yield":[63],"similar":[64,119],"or":[65,120],"better":[66,121],"performance":[67,122],"than":[68,123],"HMM/ANN":[69],"task":[75],"and":[76],"large":[78],"scale":[79],"continuous":[80],"task,":[83],"less":[85],"parameters.":[86],"Motivated":[87],"by":[88],"these":[89],"studies,":[90],"we":[91],"investigate":[92],"the":[93,100,104],"use":[94],"simple":[96],"linear":[97],"classifier":[98],"CNN-based":[101],"framework.":[102],"Thus,":[103],"network":[105],"learns":[106],"linearly":[107],"separable":[108],"from":[110],"speech.":[112],"We":[113],"show":[114],"that":[115],"yields":[118],"MLP":[124],"cepstral-based":[128]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2019-07-30T00:00:00"}