{"id":"https://openalex.org/W2707551695","doi":"https://doi.org/10.1109/icassp.2017.7953131","title":"A first look into a Convolutional Neural Network for speech emotion detection","display_name":"A first look into a Convolutional Neural Network for speech emotion detection","publication_year":2017,"publication_date":"2017-03-01","ids":{"openalex":"https://openalex.org/W2707551695","doi":"https://doi.org/10.1109/icassp.2017.7953131","mag":"2707551695"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2017.7953131","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7953131","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 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/A5052137623","display_name":"Dario Bertero","orcid":"https://orcid.org/0000-0003-0065-0751"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Dario Bertero","raw_affiliation_strings":["Department of Electronic and Computer Engineering, Hong Kong University of Science and Technology Clear Water Bay, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic and Computer Engineering, Hong Kong University of Science and Technology Clear Water Bay, Hong Kong","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065856469","display_name":"Pascale Fung","orcid":"https://orcid.org/0000-0002-0628-7132"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Pascale Fung","raw_affiliation_strings":["Department of Electronic and Computer Engineering, Hong Kong University of Science and Technology Clear Water Bay, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic and Computer Engineering, Hong Kong University of Science and Technology Clear Water Bay, Hong Kong","institution_ids":["https://openalex.org/I200769079"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I200769079"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":112,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5115","last_page":"5119"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9937000274658203,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9937000274658203,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9918000102043152,"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"}},{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.9817000031471252,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7596957683563232},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7377809286117554},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6594162583351135},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4359554648399353},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.41177091002464294},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37001973390579224},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.31555819511413574}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7596957683563232},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7377809286117554},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6594162583351135},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4359554648399353},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.41177091002464294},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37001973390579224},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.31555819511413574}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2017.7953131","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7953131","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-86089","is_oa":false,"landing_page_url":"http://lbdiscover.ust.hk/uresolver?url_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rfr_id=info:sid/HKUST:SPI&rft.genre=article&rft.issn=1520-6149&rft.volume=&rft.issue=&rft.date=2017&rft.spage=5115&rft.aulast=Bertero&rft.aufirst=D.%7C015122&rft.atitle=A+first+look+into+a+Convolutional+Neural+Network+for+speech+emotion+detection&rft.title=ICASSP%2C+IEEE+International+Conference+on+Acoustics%2C+Speech+and+Signal+Processing+-+Proceedings","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"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":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1501669607","https://openalex.org/W1666984270","https://openalex.org/W1849277567","https://openalex.org/W1973378890","https://openalex.org/W2087618018","https://openalex.org/W2094274886","https://openalex.org/W2102298245","https://openalex.org/W2132037657","https://openalex.org/W2154611638","https://openalex.org/W2231315629","https://openalex.org/W2251321385","https://openalex.org/W2295001676","https://openalex.org/W2354968889","https://openalex.org/W2399733683","https://openalex.org/W2401869809","https://openalex.org/W2465954854","https://openalex.org/W2565875961","https://openalex.org/W2610859066","https://openalex.org/W2963382311","https://openalex.org/W2964159778","https://openalex.org/W6630073874","https://openalex.org/W6637061625","https://openalex.org/W6639204139","https://openalex.org/W6691770337","https://openalex.org/W6706141880","https://openalex.org/W6713197546"],"related_works":["https://openalex.org/W191108438","https://openalex.org/W3135230428","https://openalex.org/W2904739811","https://openalex.org/W249088392","https://openalex.org/W2152158029","https://openalex.org/W2012540220","https://openalex.org/W2559837139","https://openalex.org/W2131711534","https://openalex.org/W2559040841","https://openalex.org/W114661351"],"abstract_inverted_index":{"We":[0,60,69],"propose":[1],"a":[2,20,48],"real-time":[3],"Convolutional":[4],"Neural":[5],"Network":[6],"model":[7,13,65],"for":[8,151],"speech":[9,26,79],"emotion":[10,32,148],"detection.":[11],"Our":[12,140],"is":[14],"trained":[15],"from":[16],"raw":[17],"audio":[18],"on":[19],"small":[21],"dataset":[22],"of":[23,43,56,81,85,136],"TED":[24],"talks":[25],"data,":[27],"manually":[28],"annotated":[29],"into":[30],"three":[31],"classes:":[33],"\u201cAngry\u201d,":[34],"\u201cHappy\u201d":[35],"and":[36,67,145,156],"\u201cSad\u201d.":[37],"It":[38],"achieves":[39],"an":[40,53,63],"average":[41,115],"accuracy":[42],"66.1%,":[44],"5%":[45],"higher":[46,111],"than":[47],"feature-based":[49],"SVM":[50],"baseline,":[51],"with":[52,110],"evaluation":[54],"time":[55],"few":[57],"hundred":[58],"milliseconds.":[59],"also":[61,124],"provide":[62],"in-depth":[64],"visualization":[66],"analysis.":[68],"show":[70],"how":[71],"our":[72],"neural":[73],"network":[74],"effectively":[75],"activates":[76,125],"during":[77],"the":[78,82,86,89,98,101,107,114,133],"sections":[80],"waveform":[83],"regardless":[84],"emotion,":[87],"ignoring":[88],"silence":[90],"parts":[91],"which":[92],"do":[93],"not":[94],"contain":[95],"information.":[96],"On":[97],"frequency":[99,128],"domain":[100],"CNN":[102],"filters":[103],"distribute":[104],"throughout":[105],"all":[106],"spectrum":[108],"range,":[109],"concentration":[112],"around":[113],"pitch":[116],"range":[117],"related":[118,158],"to":[119,132],"that":[120],"emotion.":[121],"Each":[122],"filter":[123],"at":[126],"multiple":[127],"intervals,":[129],"presumably":[130],"due":[131],"additional":[134],"contribution":[135],"amplitude-related":[137],"feature":[138],"learning.":[139],"work":[141],"will":[142],"allow":[143],"faster":[144],"more":[146],"accurate":[147],"detection":[149],"modules":[150],"human-machine":[152],"empathetic":[153],"dialog":[154],"systems":[155],"other":[157],"applications.":[159]},"counts_by_year":[{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":19},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":12},{"year":2021,"cited_by_count":22},{"year":2020,"cited_by_count":11},{"year":2019,"cited_by_count":16},{"year":2018,"cited_by_count":9},{"year":2017,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}