{"id":"https://openalex.org/W4401597829","doi":"https://doi.org/10.1109/icasspw62465.2024.10626164","title":"Cochceps-Augment: A Novel Self-Supervised Contrastive Learning Using Cochlear Cepstrum-Based Masking for Speech Emotion Recognition","display_name":"Cochceps-Augment: A Novel Self-Supervised Contrastive Learning Using Cochlear Cepstrum-Based Masking for Speech Emotion Recognition","publication_year":2024,"publication_date":"2024-04-14","ids":{"openalex":"https://openalex.org/W4401597829","doi":"https://doi.org/10.1109/icasspw62465.2024.10626164"},"language":"en","primary_location":{"id":"doi:10.1109/icasspw62465.2024.10626164","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icasspw62465.2024.10626164","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","raw_type":"proceedings-article"},"type":"article","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/A5088657402","display_name":"Ioannis Ziogas","orcid":"https://orcid.org/0000-0003-0615-322X"},"institutions":[{"id":"https://openalex.org/I176601375","display_name":"Khalifa University of Science and Technology","ror":"https://ror.org/05hffr360","country_code":"AE","type":"education","lineage":["https://openalex.org/I176601375"]}],"countries":["AE"],"is_corresponding":true,"raw_author_name":"Ioannis Ziogas","raw_affiliation_strings":["Khalifa University of Science and Technology,Department of Biomedical Engineering,Abu Dhabi,UAE"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Khalifa University of Science and Technology,Department of Biomedical Engineering,Abu Dhabi,UAE","institution_ids":["https://openalex.org/I176601375"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053893033","display_name":"Hessa Alfalahi","orcid":"https://orcid.org/0000-0002-2576-7000"},"institutions":[{"id":"https://openalex.org/I176601375","display_name":"Khalifa University of Science and Technology","ror":"https://ror.org/05hffr360","country_code":"AE","type":"education","lineage":["https://openalex.org/I176601375"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Hessa Alfalahi","raw_affiliation_strings":["Khalifa University of Science and Technology,Department of Biomedical Engineering,Abu Dhabi,UAE"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Khalifa University of Science and Technology,Department of Biomedical Engineering,Abu Dhabi,UAE","institution_ids":["https://openalex.org/I176601375"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053525471","display_name":"Ahsan H. Khandoker","orcid":"https://orcid.org/0000-0002-0636-1646"},"institutions":[{"id":"https://openalex.org/I176601375","display_name":"Khalifa University of Science and Technology","ror":"https://ror.org/05hffr360","country_code":"AE","type":"education","lineage":["https://openalex.org/I176601375"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Ahsan H. Khandoker","raw_affiliation_strings":["Khalifa University of Science and Technology,Department of Biomedical Engineering,Abu Dhabi,UAE"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Khalifa University of Science and Technology,Department of Biomedical Engineering,Abu Dhabi,UAE","institution_ids":["https://openalex.org/I176601375"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072772953","display_name":"Leontios J. Hadjileontiadis","orcid":"https://orcid.org/0000-0002-9932-9302"},"institutions":[{"id":"https://openalex.org/I176601375","display_name":"Khalifa University of Science and Technology","ror":"https://ror.org/05hffr360","country_code":"AE","type":"education","lineage":["https://openalex.org/I176601375"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Leontios J. Hadjileontiadis","raw_affiliation_strings":["Khalifa University of Science and Technology,Department of Biomedical Engineering,Abu Dhabi,UAE"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Khalifa University of Science and Technology,Department of Biomedical Engineering,Abu Dhabi,UAE","institution_ids":["https://openalex.org/I176601375"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5088657402"],"corresponding_institution_ids":["https://openalex.org/I176601375"],"apc_list":null,"apc_paid":null,"fwci":1.2892,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.79794011,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":"1","issue":null,"first_page":"700","last_page":"704"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9908999800682068,"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":0.9908999800682068,"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":0.7341092824935913},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.7212486267089844},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7085939645767212},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.6863751411437988},{"id":"https://openalex.org/keywords/augment","display_name":"Augment","score":0.652596116065979},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49569451808929443},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3413708508014679},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.05942091345787048}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7341092824935913},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.7212486267089844},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7085939645767212},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.6863751411437988},{"id":"https://openalex.org/C2779070825","wikidata":"https://www.wikidata.org/wiki/Q760434","display_name":"Augment","level":2,"score":0.652596116065979},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49569451808929443},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3413708508014679},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.05942091345787048},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"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/icasspw62465.2024.10626164","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icasspw62465.2024.10626164","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.4099999964237213}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1978274651","https://openalex.org/W2032254851","https://openalex.org/W2038385925","https://openalex.org/W2134707158","https://openalex.org/W2139155691","https://openalex.org/W2168609109","https://openalex.org/W2757910899","https://openalex.org/W2936774411","https://openalex.org/W3003875258","https://openalex.org/W3005680577","https://openalex.org/W3021080764","https://openalex.org/W3036601975","https://openalex.org/W3103291722","https://openalex.org/W3167533889","https://openalex.org/W3192216513","https://openalex.org/W3209059054","https://openalex.org/W4200192679","https://openalex.org/W4221162872","https://openalex.org/W4254446689","https://openalex.org/W4293363567","https://openalex.org/W4313156423","https://openalex.org/W4367000428","https://openalex.org/W4372259942","https://openalex.org/W4372266023","https://openalex.org/W4375869095","https://openalex.org/W4375869340","https://openalex.org/W4392902532","https://openalex.org/W6687483927","https://openalex.org/W6726497184","https://openalex.org/W6744513255","https://openalex.org/W6755207826","https://openalex.org/W6774314701","https://openalex.org/W6780218876","https://openalex.org/W6851949647","https://openalex.org/W6855788430"],"related_works":["https://openalex.org/W2943769328","https://openalex.org/W894828327","https://openalex.org/W2136559180","https://openalex.org/W2216505304","https://openalex.org/W2188424442","https://openalex.org/W2381350675","https://openalex.org/W1614028504","https://openalex.org/W2548243992","https://openalex.org/W1996938627","https://openalex.org/W1994396704"],"abstract_inverted_index":{"Self-supervised":[0],"learning":[1,90,120],"(SSL)":[2],"for":[3,87,153,196,200],"automated":[4],"speech":[5,39,92,179],"recognition":[6,149,181],"in":[7,178],"terms":[8],"of":[9,24,33,91,109,130,135,187],"its":[10,136],"emotional":[11],"content,":[12],"can":[13],"be":[14,204],"heavily":[15],"degraded":[16],"by":[17,78],"the":[18,22,26,66,97,147,154,184],"presence":[19],"noise,":[20],"affecting":[21],"efficiency":[23],"modeling":[25],"intricate":[27],"temporal":[28,51],"and":[29,52,138,144,166],"spectral":[30],"informative":[31,193],"structures":[32],"speech.":[34],"Recently,":[35],"SSL":[36,46],"on":[37,146],"large":[38],"datasets,":[40],"as":[41,43,174,191],"well":[42],"new":[44],"audio-specific":[45],"proxy":[47],"tasks,":[48],"such":[49],"as,":[50],"frequency":[53],"masking,":[54],"have":[55],"emerged,":[56],"yielding":[57],"superior":[58],"performance":[59],"compared":[60],"to":[61,104,126,172],"classic":[62],"approaches":[63],"drawn":[64],"from":[65],"image":[67],"augmentation":[68,85,194],"domain.":[69],"Our":[70,141,168,198],"proposed":[71],"contribution":[72],"builds":[73],"upon":[74],"this":[75],"successful":[76],"paradigm":[77],"introducing":[79],"CochCeps-Augment,":[80],"a":[81,118,131,158,175],"novel":[82],"bio-inspired":[83,100,189],"masking":[84,134,190],"task":[86,195],"self-supervised":[88,119],"contrastive":[89,128],"representations.":[93],"Specifically,":[94],"we":[95],"utilize":[96],"newly":[98],"introduced":[99],"cochlear":[101],"cepstrogram":[102],"(CC-GRAM)":[103],"derive":[105],"noise":[106],"robust":[107],"representations":[108],"input":[110],"speech,":[111],"that":[112],"are":[113],"then":[114],"further":[115],"refined":[116],"through":[117,133],"scheme.":[121],"The":[122],"latter":[123],"employs":[124],"SimCLR":[125],"generate":[127],"views":[129],"CC-GRAM":[132],"angle":[137],"quefrency":[139],"dimensions.":[140],"experimental":[142],"approach":[143],"validations":[145],"emotion":[148,180],"K-EmoCon":[150],"benchmark":[151],"dataset,":[152],"first":[155],"time":[156],"via":[157],"speaker-independent":[159],"approach,":[160],"features":[161],"unsupervised":[162],"pre-training,":[163],"linear":[164],"probing":[165],"fine-tuning.":[167],"results":[169],"potentiate":[170],"CochCeps-Augment":[171,202],"serve":[173],"standard":[176],"tool":[177],"analysis,":[182],"showing":[183],"added":[185],"value":[186],"incorporating":[188],"an":[192],"self-supervision.":[197],"code":[199],"implementing":[201],"will":[203],"made":[205],"available":[206],"at:":[207],"https://github.com/GiannisZgs/CochCepsAugment.":[208]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2}],"updated_date":"2026-05-07T13:39:58.223016","created_date":"2025-10-10T00:00:00"}