{"id":"https://openalex.org/W2809306619","doi":"https://doi.org/10.21437/interspeech.2018-1898","title":"Quaternion Convolutional Neural Networks for End-to-End Automatic Speech Recognition","display_name":"Quaternion Convolutional Neural Networks for End-to-End Automatic Speech Recognition","publication_year":2018,"publication_date":"2018-08-28","ids":{"openalex":"https://openalex.org/W2809306619","doi":"https://doi.org/10.21437/interspeech.2018-1898","mag":"2809306619"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2018-1898","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1898","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1806.07789","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089505434","display_name":"Titouan Parcollet","orcid":"https://orcid.org/0000-0003-0672-1346"},"institutions":[{"id":"https://openalex.org/I4210119991","display_name":"Laboratoire Informatique d'Avignon","ror":"https://ror.org/02n399288","country_code":"FR","type":"facility","lineage":["https://openalex.org/I198415970","https://openalex.org/I4210119991"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Titouan Parcollet","raw_affiliation_strings":["Laboratoire Informatique d'Avignon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratoire Informatique d'Avignon","institution_ids":["https://openalex.org/I4210119991"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100386104","display_name":"Ying Zhang","orcid":"https://orcid.org/0000-0002-2674-1638"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ying Zhang","raw_affiliation_strings":["Montreal Institute for Learning Algorithms  [Montr\u00e9al]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Montreal Institute for Learning Algorithms  [Montr\u00e9al]","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068392446","display_name":"Mohamed Morchid","orcid":"https://orcid.org/0000-0002-4427-2468"},"institutions":[{"id":"https://openalex.org/I4210119991","display_name":"Laboratoire Informatique d'Avignon","ror":"https://ror.org/02n399288","country_code":"FR","type":"facility","lineage":["https://openalex.org/I198415970","https://openalex.org/I4210119991"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Mohamed Morchid","raw_affiliation_strings":["Laboratoire Informatique d'Avignon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratoire Informatique d'Avignon","institution_ids":["https://openalex.org/I4210119991"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075267599","display_name":"Chiheb Trabelsi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chiheb Trabelsi","raw_affiliation_strings":["Montreal Institute for Learning Algorithms  [Montr\u00e9al]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Montreal Institute for Learning Algorithms  [Montr\u00e9al]","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050508708","display_name":"Georges Linar\u00e8s","orcid":"https://orcid.org/0000-0001-8049-9056"},"institutions":[{"id":"https://openalex.org/I4210119991","display_name":"Laboratoire Informatique d'Avignon","ror":"https://ror.org/02n399288","country_code":"FR","type":"facility","lineage":["https://openalex.org/I198415970","https://openalex.org/I4210119991"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Georges Linares","raw_affiliation_strings":["Laboratoire Informatique d'Avignon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratoire Informatique d'Avignon","institution_ids":["https://openalex.org/I4210119991"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081408760","display_name":"Renato De Mori","orcid":"https://orcid.org/0000-0002-2083-9095"},"institutions":[{"id":"https://openalex.org/I4210119991","display_name":"Laboratoire Informatique d'Avignon","ror":"https://ror.org/02n399288","country_code":"FR","type":"facility","lineage":["https://openalex.org/I198415970","https://openalex.org/I4210119991"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Renato de Mori","raw_affiliation_strings":["Laboratoire Informatique d'Avignon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratoire Informatique d'Avignon","institution_ids":["https://openalex.org/I4210119991"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086198262","display_name":"Yoshua Bengio","orcid":"https://orcid.org/0000-0002-9322-3515"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yoshua Bengio","raw_affiliation_strings":["Montreal Institute for Learning Algorithms  [Montr\u00e9al]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Montreal Institute for Learning Algorithms  [Montr\u00e9al]","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9976,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.76614743,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"22","last_page":"26"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9907000064849854,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9907000064849854,"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/T10320","display_name":"Neural Networks and Applications","score":0.9855999946594238,"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":0.9840999841690063,"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/quaternion","display_name":"Quaternion","score":0.8378517627716064},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6927211284637451},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6898276209831238},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5991555452346802},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.5165630578994751},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49492114782333374},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4932171702384949},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.48707130551338196},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.4755784571170807},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.4638068675994873},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.44612401723861694},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.4369525909423828},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4261641800403595},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.42491692304611206},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.39958417415618896},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.27154573798179626},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.25898104906082153},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17116710543632507}],"concepts":[{"id":"https://openalex.org/C200127275","wikidata":"https://www.wikidata.org/wiki/Q173853","display_name":"Quaternion","level":2,"score":0.8378517627716064},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6927211284637451},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6898276209831238},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5991555452346802},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.5165630578994751},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49492114782333374},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4932171702384949},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.48707130551338196},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.4755784571170807},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.4638068675994873},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.44612401723861694},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.4369525909423828},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4261641800403595},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.42491692304611206},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.39958417415618896},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.27154573798179626},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.25898104906082153},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17116710543632507},{"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},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.21437/interspeech.2018-1898","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1898","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1806.07789","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1806.07789","pdf_url":"https://arxiv.org/pdf/1806.07789","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"mag:2809306619","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1806.07789","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"pmh:oai:HAL:hal-02107611v1","is_oa":true,"landing_page_url":"https://hal.science/hal-02107611","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Interspeech 2018, Sep 2018, HYDERABAD, India. pp.22-26, ⟨10.21437/Interspeech.2018-1898⟩","raw_type":"Conference papers"},{"id":"doi:10.48550/arxiv.1806.07789","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1806.07789","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1806.07789","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1806.07789","pdf_url":"https://arxiv.org/pdf/1806.07789","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2963719423","https://openalex.org/W2901145677","https://openalex.org/W2972574872","https://openalex.org/W2952939375","https://openalex.org/W2734783736","https://openalex.org/W2985332775","https://openalex.org/W3025540705","https://openalex.org/W2911796113","https://openalex.org/W2963235055","https://openalex.org/W2787285847","https://openalex.org/W2964330921","https://openalex.org/W2586489272","https://openalex.org/W3005914890","https://openalex.org/W3084574658","https://openalex.org/W2964590182","https://openalex.org/W3037538309","https://openalex.org/W2599764753","https://openalex.org/W2895358653","https://openalex.org/W2855906180","https://openalex.org/W3082338832"],"abstract_inverted_index":{"Recently,":[0],"the":[1,40,78,88,145,160],"connectionist":[2],"temporal":[3],"classification":[4],"(CTC)":[5],"model":[6,180],"coupled":[7],"with":[8,47,117,144,159,173],"recurrent":[9],"(RNN)":[10],"or":[11],"convolutional":[12,134],"neural":[13,96,135],"networks":[14,97],"(CNN),":[15],"made":[16],"it":[17],"easier":[18],"to":[19,64,73,83,102,108,113,127,138],"train":[20],"speech":[21],"recognition":[22,157],"systems":[23],"in":[24,29,77,132,155],"an":[25],"end-to-end":[26],"fashion.":[27],"However":[28],"real-valued":[30,122,183],"models,":[31],"time":[32],"frame":[33],"components":[34,67],"such":[35,66,75],"as":[36,56,68,106],"mel-filter-bank":[37],"energies":[38],"and":[39,50,82,94,112],"cepstral":[41],"coefficients":[42],"obtained":[43],"from":[44],"them,":[45],"together":[46],"their":[48,100],"first":[49],"second":[51],"order":[52],"derivatives,":[53],"are":[54,150],"processed":[55],"individual":[57],"elements,":[58],"while":[59],"a":[60,167,178],"natural":[61],"alternative":[62],"is":[63],"process":[65,84,103],"composed":[69],"entities.":[70],"We":[71],"propose":[72],"group":[74],"elements":[76],"form":[79],"of":[80],"quaternions":[81,86],"these":[85],"using":[87,152],"established":[89],"quaternion":[90,95],"algebra.":[91],"Quaternion":[92],"numbers":[93],"have":[98],"shown":[99],"efficiency":[101],"multidimensional":[104],"inputs":[105],"entities,":[107],"encode":[109],"internal":[110],"dependencies,":[111],"solve":[114],"many":[115],"tasks":[116],"less":[118,174],"learning":[119,175],"parameters":[120,176],"than":[121,177],"models.":[123],"This":[124],"paper":[125],"proposes":[126],"integrate":[128],"multiple":[129],"feature":[130],"views":[131],"quaternion-valued":[133],"network":[136],"(QCNN),":[137],"be":[139],"used":[140],"for":[141],"sequence-to-sequence":[142],"mapping":[143],"CTC":[146],"model.":[147],"Promising":[148],"results":[149],"reported":[151],"simple":[153],"QCNNs":[154,165],"phoneme":[156,169],"experiments":[158],"TIMIT":[161],"corpus.":[162],"More":[163],"precisely,":[164],"obtain":[166],"lower":[168],"error":[170],"rate":[171],"(PER)":[172],"competing":[179],"based":[181],"on":[182],"CNNs.":[184]},"counts_by_year":[{"year":2021,"cited_by_count":4},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}