{"id":"https://openalex.org/W2145203520","doi":null,"title":"Raw Speech Signal-based Continuous Speech Recognition using Convolutional Neural Networks","display_name":"Raw Speech Signal-based Continuous Speech Recognition using Convolutional Neural Networks","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W2145203520","mag":"2145203520"},"language":"en","primary_location":{"id":"pmh:oai:infoscience.epfl.ch:202573","doi":null,"is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/202573","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"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://infoscience.epfl.ch/record/202573","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064459820","display_name":"Dimitri Palaz","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dimitri Palaz","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"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"],"raw_orcid":"https://orcid.org/0000-0002-8714-1409","affiliations":[{"raw_affiliation_string":"IDIAP research institute","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053915453","display_name":"Ronan Collobert","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ronan Collobert","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5957,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.72722054,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":96},"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":0.0,"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/continuous-speech-recognition","display_name":"continuous speech recognition","score":0.906000018119812},{"id":"https://openalex.org/keywords/convolutional-neural-networks","display_name":"convolutional neural networks","score":0.9769999980926514},{"id":"https://openalex.org/keywords/end-to-end-speech-recognition","display_name":"end-to-end speech recognition","score":0.8309999704360962},{"id":"https://openalex.org/keywords/large-vocabulary-speech-recognition","display_name":"large vocabulary speech recognition","score":0.7699999809265137},{"id":"https://openalex.org/keywords/acoustic-modeling","display_name":"acoustic modeling","score":0.527999997138977},{"id":"https://openalex.org/keywords/phone-classification","display_name":"phone classification","score":0.5099999904632568},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"feature extraction","score":0.6380000114440918},{"id":"https://openalex.org/keywords/spectral-properties","display_name":"spectral properties","score":0.4580000042915344},{"id":"https://openalex.org/keywords/neural-network","display_name":"artificial neural networks","score":0.5870000123977661},{"id":"https://openalex.org/keywords/wall-street-journal-corpus","display_name":"Wall Street Journal corpus","score":0.7210000157356262},{"id":"https://openalex.org/keywords/model-complexity","display_name":"model complexity","score":0.3019999861717224},{"id":"https://openalex.org/keywords/phoneme-recognition","display_name":"phoneme recognition","score":0.32600000500679016}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7877386212348938},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7465677261352539},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5987908840179443},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.551196277141571},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5358110070228577},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5317572355270386},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.49088984727859497},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.47337883710861206},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4683702886104584},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.43055811524391174},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.343031108379364},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.30918216705322266},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:infoscience.epfl.ch:202573","doi":null,"is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/202573","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":"pmh:oai:infoscience.tind.io:202573","doi":null,"is_oa":true,"landing_page_url":"https://infoscience.epfl.ch/handle/20.500.14299/107965","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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"report"},{"id":"mag:2145203520","doi":null,"is_oa":false,"landing_page_url":"https://infoscience.epfl.ch/record/202573","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:infoscience.epfl.ch:202573","doi":null,"is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/202573","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"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"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/W1634752325","https://openalex.org/W1993882792","https://openalex.org/W1995314086","https://openalex.org/W2035305631","https://openalex.org/W2090861223","https://openalex.org/W2103088716","https://openalex.org/W2107789863","https://openalex.org/W2112739286","https://openalex.org/W2112796928","https://openalex.org/W2117130368","https://openalex.org/W2117671523","https://openalex.org/W2122028591","https://openalex.org/W2123811694","https://openalex.org/W2132037657","https://openalex.org/W2134557905","https://openalex.org/W2136922672","https://openalex.org/W2140539590","https://openalex.org/W2147768505","https://openalex.org/W2148154194","https://openalex.org/W2148428486","https://openalex.org/W2155273149","https://openalex.org/W2160815625","https://openalex.org/W2163605009","https://openalex.org/W2394932179","https://openalex.org/W2952230511","https://openalex.org/W3028642772"],"related_works":["https://openalex.org/W2964261986","https://openalex.org/W7028400246","https://openalex.org/W562837778","https://openalex.org/W7074593857","https://openalex.org/W7045523659","https://openalex.org/W3099202502","https://openalex.org/W7065700722","https://openalex.org/W424869780","https://openalex.org/W6987007654","https://openalex.org/W3113035403"],"abstract_inverted_index":{"Abstract":[0],"State-of-the-art":[1,50],"automatic":[2],"speech":[3,11,40,52,297,331],"recognition":[4,41,53,298],"systems":[5,55,169,179,308],"model":[6],"the":[7,58,74,92,96,128,154,157,192,196,248,258,262,266,285],"relationship":[8],"be-tween":[9],"acoustic":[10],"signal":[12,332],"and":[13,86,159,191,256,323],"phone":[14],"classes":[15],"in":[16,65,163,174,284],"two":[17,99],"stages,":[18],"namely,":[19],"extractionofspectral-basedfeaturesbasedonpriorknowledgefollowedbytrainingofacous-tic":[20],"model,":[21],"typically":[22,56,201],"an":[23,66,87,175],"articial":[24],"neural":[25,337],"network":[26],"(ANN).":[27],"In":[28,70,124,143],"a":[29,71,82,125,144,270,277],"recent":[30],"work,":[31],"it":[32],"wasshownthatconvolutionneuralnetworks(CNNs)arecapableofmodelingtherela-tionbetweenacousticspeechsignalandphoneclassesdirectly.":[33],"Thispaperextendsthe":[34],"CNN-based":[35],"approach":[36],"to":[37,106,152,203,216,223,229,246,250,252,260,311,335],"large":[38],"vocabulary":[39],"task.":[42],"More":[43],"pre-cisely,wecomparetheCNN-basedapproachagainsttheconventionalANN-basedapproachonWallStreetJournalcorpus.":[44],"OurstudiesshowthattheCNN-basedap-proachwithfewerparametersachievesperformancecomparableorbetterthantheconventional":[45],"ANN-based":[46],"approach.":[47],"1":[48],"Introduction":[49],"Automatic":[51],"(ASR)":[54],"divide":[57],"task":[59,194,272],"into":[60,186],"severalsub-tasks,":[61],"which":[62],"are":[63,150,209,243],"optimized":[64],"independent":[67],"manner":[68],"[1].":[69],"rst":[72],"step,":[73,127,146],"data":[75],"is":[76,136,200,238,276],"transformedinto":[77],"features,":[78],"usually":[79,210],"composed":[80,211],"of":[81,95,130,195,212,220,264,273,281],"dimensionality":[83],"reduction":[84],"phase":[85],"information":[88],"selectionphase,":[89],"based":[90],"on":[91,301],"task-specic":[93],"knowledge":[94],"phenomena.":[97],"These":[98],"phases":[100],"have":[101,166,247,309],"been":[102],"care-fully":[103],"hand-crafted,":[104],"leading":[105],"state-of-the-art":[107],"features":[108,121,268,303,313],"such":[109,133,207,282],"as":[110,333],"mel":[111,319],"frequency":[112],"cepstral":[113,120],"coefcients(MFCCs)":[114],"[2]":[115],"or":[116,141,289],"perceptual":[117],"linear":[118],"prediction":[119],"(PLPs)":[122],"[3].":[123],"second":[126],"like-lihood":[129],"subword":[131],"units":[132],"as,":[134],"phonemes":[135],"estimated":[137],"using":[138,329],"generative":[139],"models":[140],"discriminativemodels.":[142],"nal":[145,193],"dynamic":[147],"programming":[148],"techniques":[149],"used":[151],"recognize":[153],"word":[155],"sequencegiven":[156],"lexical":[158],"syntactical":[160],"constraints.Recent":[161],"advances":[162],"machine":[164],"learning":[165,294],"made":[167],"possible":[168],"that":[170],"can":[171],"be":[172],"trained":[173],"end-to-end":[176],"manner,":[177],"i.e.":[178],"where":[180],"every":[181],"step":[182,237],"islearned":[183],"simultaneously,":[184],"taking":[185],"account":[187],"allthe":[188],"other":[189],"steps":[190],"whole":[197],"system.":[198],"It":[199],"referred":[202],"asdeep":[204],"learning,mainly":[205],"because":[206],"architectures":[208],"many":[213],"layers":[214],"(supposed":[215],"provide":[217],"anincreasing":[218],"level":[219],"abstraction),":[221],"compared":[222],"classical":[224],"\u0093shallow\u0094":[225],"systems.":[226],"As":[227],"opposed":[228],"\u0093divideand":[230],"conquer\u0094":[231],"approaches":[232,242,283,295],"presented":[233],"previously":[234],"(where":[235],"each":[236],"independently":[239],"optimized)":[240],"deeplearning":[241],"often":[244],"claimed":[245],"potential":[249],"lead":[251],"more":[253],"optimal":[254],"systems,":[255],"tohave":[257],"advantage":[259],"alleviate":[261],"need":[263],"nd":[265],"right":[267],"for":[269,296],"given":[271],"interest.":[274],"Whilethere":[275],"good":[278],"success":[279],"record":[280],"computer":[286],"vision":[287],"[4]":[288],"text":[290],"processingelds":[291],"[5],":[292],"deep":[293],"still":[299],"rely":[300],"spectral-based":[302],"suchas":[304],"MFCC":[305],"[6].":[306],"Some":[307],"proposed":[310],"learn":[312],"from":[314],"\u0093intermediate\u0094":[315],"representation":[316],"ofspeech,":[317],"like":[318],"lter":[320],"bank":[321],"energies":[322],"their":[324],"temporal":[325],"derivatives.Inarecentstudy[7],":[326],"itwasshownthatitispossibletoestimatephonemeclassconditionalprobabil-ities":[327],"by":[328],"raw":[330],"input":[334],"convolutional":[336],"networks":[338],"[8]":[339],"(CNNs).":[340],"On":[341],"TIMITphonemerecognitiontask,":[342],"itwasshownthatthesystemisabletolearnfeaturesfromtherawspeech1":[343]},"counts_by_year":[{"year":2016,"cited_by_count":2}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}