{"id":"https://openalex.org/W2168249605","doi":"https://doi.org/10.1109/icassp.2015.7178781","title":"Convolutional Neural Networks-based continuous speech recognition using raw speech signal","display_name":"Convolutional Neural Networks-based continuous speech recognition using raw speech signal","publication_year":2015,"publication_date":"2015-04-01","ids":{"openalex":"https://openalex.org/W2168249605","doi":"https://doi.org/10.1109/icassp.2015.7178781","mag":"2168249605"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178781","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://publications.idiap.ch/attachments/reports/2014/Palaz_Idiap-RR-18-2014.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064459820","display_name":"Dimitri Palaz","orcid":null},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]},{"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","Switzerland Ecole Polytechnique Federale de Lausanne (EPFL), Lausanne, Switzerland"],"affiliations":[{"raw_affiliation_string":"Switzerland Ecole Polytechnique Federale de Lausanne (EPFL), Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]},{"raw_affiliation_string":"Idiap Research Institute, Martigny","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"},"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"],"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Martigny","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053915453","display_name":"Ronan Collobert","orcid":null},"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"],"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Martigny","institution_ids":["https://openalex.org/I7495430"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":8.172,"has_fulltext":true,"fulltext_origin":"pdf","cited_by_count":165,"citation_normalized_percentile":{"value":0.999876,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition Technology","score":0.9998,"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 Technology","score":0.9998,"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":"Audio Signal Classification and Analysis","score":0.9989,"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 Enhancement Techniques","score":0.9977,"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/audio-visual-speech-recognition","display_name":"Audio-Visual Speech Recognition","score":0.599499},{"id":"https://openalex.org/keywords/automatic-speech-recognition","display_name":"Automatic Speech Recognition","score":0.593761},{"id":"https://openalex.org/keywords/end-to-end-speech-recognition","display_name":"End-to-End Speech Recognition","score":0.574249},{"id":"https://openalex.org/keywords/acoustic-modeling","display_name":"Acoustic Modeling","score":0.572854},{"id":"https://openalex.org/keywords/environmental-sound-recognition","display_name":"Environmental Sound Recognition","score":0.552666},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.50837153},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.44994017}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.81578386},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.73879236},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.73007846},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.62509215},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.60514},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.56127894},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5490362},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5357688},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.50837153},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4995215},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.45858097},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.44994017},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.42570433},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.42387205},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40881947},{"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},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178781","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"http://publications.idiap.ch/index.php/publications/showcite/Palaz_Idiap-RR-18-2014","pdf_url":"https://publications.idiap.ch/attachments/reports/2014/Palaz_Idiap-RR-18-2014.pdf","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,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"mit","license_id":"https://openalex.org/licenses/mit","version":"submittedVersion","is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.718.4960","pdf_url":"http://ronan.collobert.com/pub/matos/2015_rawspeech_icassp.pdf","source":{"id":"https://openalex.org/S4306400349","display_name":"CiteSeer X (The Pennsylvania State University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I130769515","host_organization_name":"Pennsylvania State University","host_organization_lineage":["https://openalex.org/I130769515"],"host_organization_lineage_names":["Pennsylvania State University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"https://infoscience.epfl.ch/record/203464/files/Palaz_Idiap-RR-18-2014.pdf","pdf_url":"https://infoscience.epfl.ch/record/203464/files/Palaz_Idiap-RR-18-2014.pdf","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,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"http://publications.idiap.ch/index.php/publications/showcite/Palaz_Idiap-RR-18-2014","pdf_url":"https://publications.idiap.ch/attachments/reports/2014/Palaz_Idiap-RR-18-2014.pdf","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,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"mit","license_id":"https://openalex.org/licenses/mit","version":"submittedVersion","is_accepted":false,"is_published":false},"sustainable_development_goals":[{"display_name":"Quality education","id":"https://metadata.un.org/sdg/4","score":0.41}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":28,"referenced_works":["https://openalex.org/W1553004968","https://openalex.org/W1634752325","https://openalex.org/W169539560","https://openalex.org/W183625566","https://openalex.org/W1993882792","https://openalex.org/W2035305631","https://openalex.org/W2077804127","https://openalex.org/W2103088716","https://openalex.org/W2107789863","https://openalex.org/W2112739286","https://openalex.org/W2112796928","https://openalex.org/W2122028591","https://openalex.org/W2132037657","https://openalex.org/W2136922672","https://openalex.org/W2147768505","https://openalex.org/W2148428486","https://openalex.org/W2155273149","https://openalex.org/W2158899491","https://openalex.org/W2160815625","https://openalex.org/W2394932179","https://openalex.org/W2408093180","https://openalex.org/W2504108613","https://openalex.org/W2952230511","https://openalex.org/W2963175699","https://openalex.org/W3028642772","https://openalex.org/W753012316","https://openalex.org/W811578723","https://openalex.org/W88081813"],"related_works":["https://openalex.org/W642007152","https://openalex.org/W3033124456","https://openalex.org/W2992378684","https://openalex.org/W2964829415","https://openalex.org/W2153098279","https://openalex.org/W2131711534","https://openalex.org/W2122233706","https://openalex.org/W2121652828","https://openalex.org/W2105439218","https://openalex.org/W2092406870"],"abstract_inverted_index":{"State-of-the-art":[0],"automatic":[1],"speech":[2,10,58,78,126],"recognition":[3,79],"systems":[4],"model":[5,52],"the":[6,72,85,89,102,109,121,128],"relationship":[7],"between":[8],"acoustic":[9,31,57],"signal":[11],"and":[12],"phone":[13,53],"classes":[14,54],"in":[15],"two":[16],"stages,":[17],"namely,":[18],"extraction":[19],"of":[20,30],"spectral-based":[21],"features":[22,122],"based":[23],"on":[24,62,93],"prior":[25],"knowledge":[26],"followed":[27],"by":[28,127],"training":[29],"model,":[32],"typically":[33],"an":[34],"artificial":[35],"neural":[36],"network":[37],"(ANN).":[38],"In":[39],"our":[40],"recent":[41],"work,":[42],"it":[43],"was":[44],"shown":[45],"that":[46,101,120],"Convolutional":[47],"Neural":[48],"Networks":[49],"(CNNs)":[50],"can":[51],"from":[55,124],"raw":[56,125],"signal,":[59],"reaching":[60],"performance":[61,107],"par":[63],"with":[64,113],"other":[65],"existing":[66],"feature-based":[67],"approaches.":[68],"This":[69],"paper":[70],"extends":[71],"CNN-based":[73,86,103,129],"approach":[74,87,92,104,112,130],"to":[75],"large":[76],"vocabulary":[77],"task.":[80],"More":[81],"precisely,":[82],"we":[83],"compare":[84],"against":[88],"conventional":[90,110],"ANN-based":[91,111],"Wall":[94],"Street":[95],"Journal":[96],"corpus.":[97],"Our":[98],"studies":[99],"show":[100,119],"achieves":[105],"better":[106],"than":[108],"as":[114],"many":[115],"parameters.":[116],"We":[117],"also":[118],"learned":[123],"could":[131],"generalize":[132],"across":[133],"different":[134],"databases.":[135]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2168249605","counts_by_year":[{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":17},{"year":2022,"cited_by_count":17},{"year":2021,"cited_by_count":29},{"year":2020,"cited_by_count":18},{"year":2019,"cited_by_count":24},{"year":2018,"cited_by_count":23},{"year":2017,"cited_by_count":17},{"year":2016,"cited_by_count":10},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":1}],"updated_date":"2024-11-08T00:16:06.540873","created_date":"2016-06-24"}
