{"id":"https://openalex.org/W3207018606","doi":"https://doi.org/10.1109/icassp43922.2022.9747914","title":"Cognitive Coding Of Speech","display_name":"Cognitive Coding Of Speech","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W3207018606","doi":"https://doi.org/10.1109/icassp43922.2022.9747914","mag":"3207018606"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747914","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747914","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075959406","display_name":"Reza Lotfidereshgi","orcid":null},"institutions":[{"id":"https://openalex.org/I135117807","display_name":"Universit\u00e9 de Sherbrooke","ror":"https://ror.org/00kybxq39","country_code":"CA","type":"education","lineage":["https://openalex.org/I135117807"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Reza Lotfidereshgi","raw_affiliation_strings":["Speech and Audio Research Group Université de Sherbrooke,Sherbrooke (Québec),Canada,J1K 2R1"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech and Audio Research Group Université de Sherbrooke,Sherbrooke (Québec),Canada,J1K 2R1","institution_ids":["https://openalex.org/I135117807"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011508393","display_name":"Philippe Gournay","orcid":null},"institutions":[{"id":"https://openalex.org/I135117807","display_name":"Universit\u00e9 de Sherbrooke","ror":"https://ror.org/00kybxq39","country_code":"CA","type":"education","lineage":["https://openalex.org/I135117807"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Philippe Gournay","raw_affiliation_strings":["Speech and Audio Research Group Université de Sherbrooke,Sherbrooke (Québec),Canada,J1K 2R1"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech and Audio Research Group Université de Sherbrooke,Sherbrooke (Québec),Canada,J1K 2R1","institution_ids":["https://openalex.org/I135117807"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I135117807"],"apc_list":null,"apc_paid":null,"fwci":0.9228,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.7267226,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"7772","last_page":"7776"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9987999796867371,"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/T11309","display_name":"Music and Audio Processing","score":0.9987999796867371,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9977999925613403,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9922000169754028,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.7410281300544739},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6676110625267029},{"id":"https://openalex.org/keywords/abstraction","display_name":"Abstraction","score":0.6476858854293823},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.5488161444664001},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.4694601595401764},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4467947781085968},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.41986513137817383},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.39267635345458984},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33833029866218567},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08889728784561157}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7410281300544739},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6676110625267029},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.6476858854293823},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.5488161444664001},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.4694601595401764},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4467947781085968},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.41986513137817383},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.39267635345458984},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33833029866218567},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08889728784561157},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747914","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747914","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2025768430","https://openalex.org/W2083595270","https://openalex.org/W2099471712","https://openalex.org/W2100495367","https://openalex.org/W2152790380","https://openalex.org/W2557579533","https://openalex.org/W2743406877","https://openalex.org/W2752796333","https://openalex.org/W2787636496","https://openalex.org/W2810914326","https://openalex.org/W2842511635","https://openalex.org/W2935711438","https://openalex.org/W2962159375","https://openalex.org/W2962839285","https://openalex.org/W2963226019","https://openalex.org/W2963762683","https://openalex.org/W2963799213","https://openalex.org/W2982602185","https://openalex.org/W3100270690","https://openalex.org/W3125709657","https://openalex.org/W3160576174","https://openalex.org/W4293469690","https://openalex.org/W4297808394","https://openalex.org/W4320013936","https://openalex.org/W6682948231","https://openalex.org/W6713634518","https://openalex.org/W6718140377","https://openalex.org/W6729906282","https://openalex.org/W6748775516","https://openalex.org/W6753049143"],"related_works":["https://openalex.org/W2496295964","https://openalex.org/W1546240199","https://openalex.org/W1976952689","https://openalex.org/W2336887028","https://openalex.org/W1984921740","https://openalex.org/W193702574","https://openalex.org/W2070982348","https://openalex.org/W2365485488","https://openalex.org/W642007152","https://openalex.org/W2056066842"],"abstract_inverted_index":{"We":[0],"propose":[1],"an":[2,78,116],"approach":[3],"for":[4,149],"cognitive":[5],"coding":[6],"of":[7,12,19,40,63,94,112,127,156],"speech":[8,43,119,151],"by":[9,69],"unsupervised":[10],"extraction":[11],"contextual":[13],"representations":[14],"in":[15,36,59,97,118,121],"two":[16],"hierarchical":[17],"levels":[18],"abstraction.":[20,64],"Speech":[21],"attributes":[22,44,152],"such":[23,45],"as":[24,46],"phoneme":[25],"identity":[26,48],"that":[27,51,155],"last":[28],"one":[29,55],"hundred":[30],"milliseconds":[31],"or":[32],"less":[33],"are":[34,57,88],"captured":[35,58],"the":[37,60,92,95,109,113,125,135,142],"lower":[38,76],"level":[39,62],"abstraction,":[41],"while":[42],"speaker":[47],"and":[49,77,130,144,148],"emotion":[50],"persist":[52],"up":[53],"to":[54,90],"second":[56],"higher":[61],"This":[65],"decomposition":[66],"is":[67],"achieved":[68],"a":[70,75],"two-stage":[71],"neural":[72],"net-work,":[73],"with":[74],"upper":[79],"stage":[80],"operating":[81],"at":[82],"different":[83],"time":[84],"scales.":[85],"Both":[86],"stages":[87,106],"trained":[89],"predict":[91],"content":[93],"signal":[96],"their":[98],"respective":[99],"latent":[100],"spaces.":[101],"A":[102],"top-down":[103],"path-way":[104],"between":[105],"further":[107],"improves":[108],"predictive":[110],"capability":[111],"network.":[114],"With":[115],"application":[117],"compression":[120],"mind,":[122],"we":[123],"investigate":[124],"effect":[126],"dimensionality":[128],"reduction":[129],"low":[131],"bitrate":[132],"quantization":[133],"on":[134,141],"extracted":[136],"representations.":[137],"The":[138],"performance":[139],"measured":[140],"LibriSpeech":[143],"EmoV-DB":[145],"datasets":[146],"reaches,":[147],"some":[150],"even":[153],"exceeds,":[154],"state-of-the-art":[157],"approaches.":[158]},"counts_by_year":[{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}