{"id":"https://openalex.org/W3005914890","doi":"https://doi.org/10.1109/icassp40776.2020.9054220","title":"CGCNN: Complex Gabor Convolutional Neural Network on Raw Speech","display_name":"CGCNN: Complex Gabor Convolutional Neural Network on Raw Speech","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3005914890","doi":"https://doi.org/10.1109/icassp40776.2020.9054220","mag":"3005914890"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054220","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054220","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/2002.04569","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5006577555","display_name":"\u202aPaul-Gauthier No\u00e9\u202c","orcid":"https://orcid.org/0000-0002-2304-9830"},"institutions":[{"id":"https://openalex.org/I198415970","display_name":"Universit\u00e9 d'Avignon et des Pays de Vaucluse","ror":"https://ror.org/00mfpxb84","country_code":"FR","type":"education","lineage":["https://openalex.org/I198415970"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Paul-Gauthier Noe","raw_affiliation_strings":["LIA, Universit\u00e9 d'Avignon, France#TAB#"],"affiliations":[{"raw_affiliation_string":"LIA, Universit\u00e9 d'Avignon, France#TAB#","institution_ids":["https://openalex.org/I198415970"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089505434","display_name":"Titouan Parcollet","orcid":"https://orcid.org/0000-0003-0672-1346"},"institutions":[{"id":"https://openalex.org/I198415970","display_name":"Universit\u00e9 d'Avignon et des Pays de Vaucluse","ror":"https://ror.org/00mfpxb84","country_code":"FR","type":"education","lineage":["https://openalex.org/I198415970"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Titouan Parcollet","raw_affiliation_strings":["LIA, Universit\u00e9 d'Avignon, France#TAB#"],"affiliations":[{"raw_affiliation_string":"LIA, Universit\u00e9 d'Avignon, France#TAB#","institution_ids":["https://openalex.org/I198415970"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068392446","display_name":"Mohamed Morchid","orcid":"https://orcid.org/0000-0002-4427-2468"},"institutions":[{"id":"https://openalex.org/I198415970","display_name":"Universit\u00e9 d'Avignon et des Pays de Vaucluse","ror":"https://ror.org/00mfpxb84","country_code":"FR","type":"education","lineage":["https://openalex.org/I198415970"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Mohamed Morchid","raw_affiliation_strings":["LIA, Universit\u00e9 d'Avignon, France#TAB#"],"affiliations":[{"raw_affiliation_string":"LIA, Universit\u00e9 d'Avignon, France#TAB#","institution_ids":["https://openalex.org/I198415970"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5006577555"],"corresponding_institution_ids":["https://openalex.org/I198415970"],"apc_list":null,"apc_paid":null,"fwci":0.5438,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.72504184,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"7724","last_page":"7728"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9995999932289124,"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":0.9994999766349792,"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/computer-science","display_name":"Computer science","score":0.8133509159088135},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.7468105554580688},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7391082644462585},{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.725139856338501},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6471192836761475},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4840802252292633},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.479978084564209},{"id":"https://openalex.org/keywords/lossless-compression","display_name":"Lossless compression","score":0.47483164072036743},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.44191479682922363},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.41760265827178955},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.41332128643989563},{"id":"https://openalex.org/keywords/gabor-filter","display_name":"Gabor filter","score":0.4131099283695221},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.2671726644039154},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.11288616061210632},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.11276495456695557},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.1001049280166626}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8133509159088135},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.7468105554580688},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7391082644462585},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.725139856338501},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6471192836761475},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4840802252292633},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.479978084564209},{"id":"https://openalex.org/C81081738","wikidata":"https://www.wikidata.org/wiki/Q55542","display_name":"Lossless compression","level":3,"score":0.47483164072036743},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.44191479682922363},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.41760265827178955},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.41332128643989563},{"id":"https://openalex.org/C2779883129","wikidata":"https://www.wikidata.org/wiki/Q2447890","display_name":"Gabor filter","level":3,"score":0.4131099283695221},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2671726644039154},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.11288616061210632},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.11276495456695557},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.1001049280166626},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054220","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054220","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2002.04569","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2002.04569","pdf_url":"https://arxiv.org/pdf/2002.04569","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":"","raw_type":"text"},{"id":"mag:3005914890","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2002.04569.pdf","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-02474746v1","is_oa":true,"landing_page_url":"https://hal.science/hal-02474746","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":"ICASSP 2020, May 2020, Barcelona, Spain","raw_type":"Conference papers"},{"id":"doi:10.48550/arxiv.2002.04569","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2002.04569","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:2002.04569","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2002.04569","pdf_url":"https://arxiv.org/pdf/2002.04569","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":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1934935867","display_name":null,"funder_award_id":"Engineering and Physical Sciences R","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G6851345361","display_name":null,"funder_award_id":"Grant","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G8099590239","display_name":null,"funder_award_id":"EP/S001530","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3005914890.pdf","grobid_xml":"https://content.openalex.org/works/W3005914890.grobid-xml"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W228380312","https://openalex.org/W1524333225","https://openalex.org/W1542280630","https://openalex.org/W1545083717","https://openalex.org/W1634752325","https://openalex.org/W1635512741","https://openalex.org/W1665214252","https://openalex.org/W2102113734","https://openalex.org/W2115755118","https://openalex.org/W2193413348","https://openalex.org/W2408093180","https://openalex.org/W2492400030","https://openalex.org/W2516608830","https://openalex.org/W2526425061","https://openalex.org/W2795935804","https://openalex.org/W2903799412","https://openalex.org/W2906042495","https://openalex.org/W2932319281","https://openalex.org/W2949640717","https://openalex.org/W2962780374","https://openalex.org/W2962901777","https://openalex.org/W2962913459","https://openalex.org/W2962953733","https://openalex.org/W2963071736","https://openalex.org/W2963403664","https://openalex.org/W2964052309","https://openalex.org/W2964227577","https://openalex.org/W2973053574","https://openalex.org/W2973215447","https://openalex.org/W2973818247","https://openalex.org/W2975176027","https://openalex.org/W4297970144","https://openalex.org/W6631362777","https://openalex.org/W6636687593","https://openalex.org/W6637242042","https://openalex.org/W6675365184","https://openalex.org/W6682747227","https://openalex.org/W6725896364","https://openalex.org/W6738884980","https://openalex.org/W6757084628"],"related_works":["https://openalex.org/W3007948068","https://openalex.org/W2404926044","https://openalex.org/W2155273149","https://openalex.org/W2401869809","https://openalex.org/W2891437363","https://openalex.org/W2529337537","https://openalex.org/W2587717635","https://openalex.org/W2921005841","https://openalex.org/W2515753980","https://openalex.org/W3083164447","https://openalex.org/W2792873414","https://openalex.org/W2964590182","https://openalex.org/W2405476549","https://openalex.org/W3122728801","https://openalex.org/W1555696814","https://openalex.org/W2794150026","https://openalex.org/W2883588054","https://openalex.org/W2952112541","https://openalex.org/W3127824595","https://openalex.org/W2892483709"],"abstract_inverted_index":{"Convolutional":[0],"Neural":[1],"Networks":[2],"(CNN)":[3],"have":[4],"been":[5],"used":[6],"in":[7,53],"Automatic":[8],"Speech":[9],"Recognition":[10],"(ASR)":[11],"to":[12,35,40,55,70,81,87],"learn":[13],"representations":[14],"directly":[15],"from":[16],"the":[17,41,47,50,58,61,72,98,105,112],"raw":[18],"signal":[19],"instead":[20],"of":[21,49,60,91,97],"hand-crafted":[22],"acoustic":[23,38,63],"features,":[24],"providing":[25],"a":[26],"richer":[27],"and":[28,65,96],"lossless":[29],"input":[30],"signal.":[31],"Recent":[32],"researches":[33],"propose":[34,69],"inject":[36],"prior":[37],"knowledge":[39],"first":[42],"convolutional":[43],"layer":[44],"by":[45],"integrating":[46],"shape":[48],"impulse":[51],"responses":[52],"order":[54],"increase":[56],"both":[57],"interpretability":[59],"learnt":[62],"model,":[64],"its":[66,92],"performances.":[67],"We":[68],"combine":[71],"complex":[73,99],"Gabor":[74],"filter":[75],"with":[76],"complex-valued":[77],"deep":[78],"neural":[79],"networks":[80],"replace":[82],"usual":[83],"CNN":[84],"weights":[85],"kernels,":[86],"fully":[88],"take":[89],"advantage":[90],"optimal":[93],"time-frequency":[94],"resolution":[95],"domain.":[100],"The":[101],"conducted":[102],"experiments":[103],"on":[104],"TIMIT":[106],"phoneme":[107],"recognition":[108],"task":[109],"shows":[110],"that":[111],"proposed":[113],"approach":[114],"reaches":[115],"top-of-the-line":[116],"performances":[117],"while":[118],"remaining":[119],"interpretable.":[120]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}