{"id":"https://openalex.org/W2047337856","doi":"https://doi.org/10.1109/aspaa.2011.6082328","title":"Learning emotion-based acoustic features with deep belief networks","display_name":"Learning emotion-based acoustic features with deep belief networks","publication_year":2011,"publication_date":"2011-10-01","ids":{"openalex":"https://openalex.org/W2047337856","doi":"https://doi.org/10.1109/aspaa.2011.6082328","mag":"2047337856"},"language":"en","primary_location":{"id":"doi:10.1109/aspaa.2011.6082328","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aspaa.2011.6082328","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","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/A5111442475","display_name":"Erik M. Schmidt","orcid":"https://orcid.org/0000-0003-1549-8297"},"institutions":[{"id":"https://openalex.org/I72816309","display_name":"Drexel University","ror":"https://ror.org/04bdffz58","country_code":"US","type":"education","lineage":["https://openalex.org/I72816309"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Erik M. Schmidt","raw_affiliation_strings":["Music and Entertainment Technology Laboratory (MET-lab), Electrical and Computer Engineering, Drexel University, Philadelphia, PA, USA","Music and Entertainment Technology Laboratory (MET-lab), Electrical and Computer Engineering, Drexel University, Philadelphia, 19104, USA"],"affiliations":[{"raw_affiliation_string":"Music and Entertainment Technology Laboratory (MET-lab), Electrical and Computer Engineering, Drexel University, Philadelphia, PA, USA","institution_ids":["https://openalex.org/I72816309"]},{"raw_affiliation_string":"Music and Entertainment Technology Laboratory (MET-lab), Electrical and Computer Engineering, Drexel University, Philadelphia, 19104, USA","institution_ids":["https://openalex.org/I72816309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025175604","display_name":"Youngmoo E. Kim","orcid":"https://orcid.org/0009-0005-0922-1787"},"institutions":[{"id":"https://openalex.org/I72816309","display_name":"Drexel University","ror":"https://ror.org/04bdffz58","country_code":"US","type":"education","lineage":["https://openalex.org/I72816309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Youngmoo E. Kim","raw_affiliation_strings":["Music and Entertainment Technology Laboratory (MET-lab), Electrical and Computer Engineering, Drexel University, Philadelphia, PA, USA","Music and Entertainment Technology Laboratory (MET-lab), Electrical and Computer Engineering, Drexel University, Philadelphia, 19104, USA"],"affiliations":[{"raw_affiliation_string":"Music and Entertainment Technology Laboratory (MET-lab), Electrical and Computer Engineering, Drexel University, Philadelphia, PA, USA","institution_ids":["https://openalex.org/I72816309"]},{"raw_affiliation_string":"Music and Entertainment Technology Laboratory (MET-lab), Electrical and Computer Engineering, Drexel University, Philadelphia, 19104, USA","institution_ids":["https://openalex.org/I72816309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5111442475"],"corresponding_institution_ids":["https://openalex.org/I72816309"],"apc_list":null,"apc_paid":null,"fwci":5.3032,"has_fulltext":false,"cited_by_count":87,"citation_normalized_percentile":{"value":0.96265209,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"65","last_page":"68"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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/T10860","display_name":"Speech and Audio Processing","score":0.9984999895095825,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9955999851226807,"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/timbre","display_name":"Timbre","score":0.6365435123443604},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.6200472712516785},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6116592884063721},{"id":"https://openalex.org/keywords/loudness","display_name":"Loudness","score":0.6019217371940613},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.47101056575775146},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4676377773284912},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4491698741912842},{"id":"https://openalex.org/keywords/dimensionality-reduction","display_name":"Dimensionality reduction","score":0.4311577379703522},{"id":"https://openalex.org/keywords/emotion-classification","display_name":"Emotion classification","score":0.4260457158088684},{"id":"https://openalex.org/keywords/valence","display_name":"Valence (chemistry)","score":0.4247272312641144},{"id":"https://openalex.org/keywords/deep-belief-network","display_name":"Deep belief network","score":0.4244767427444458},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.41502296924591064},{"id":"https://openalex.org/keywords/affective-computing","display_name":"Affective computing","score":0.4149840474128723},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.28052783012390137},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.23157671093940735}],"concepts":[{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.6365435123443604},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.6200472712516785},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6116592884063721},{"id":"https://openalex.org/C79018884","wikidata":"https://www.wikidata.org/wiki/Q622324","display_name":"Loudness","level":2,"score":0.6019217371940613},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.47101056575775146},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4676377773284912},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4491698741912842},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.4311577379703522},{"id":"https://openalex.org/C206310091","wikidata":"https://www.wikidata.org/wiki/Q750859","display_name":"Emotion classification","level":2,"score":0.4260457158088684},{"id":"https://openalex.org/C168900304","wikidata":"https://www.wikidata.org/wiki/Q171407","display_name":"Valence (chemistry)","level":2,"score":0.4247272312641144},{"id":"https://openalex.org/C97385483","wikidata":"https://www.wikidata.org/wiki/Q16954980","display_name":"Deep belief network","level":3,"score":0.4244767427444458},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.41502296924591064},{"id":"https://openalex.org/C6438553","wikidata":"https://www.wikidata.org/wiki/Q1185804","display_name":"Affective computing","level":2,"score":0.4149840474128723},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.28052783012390137},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.23157671093940735},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"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/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","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/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/aspaa.2011.6082328","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aspaa.2011.6082328","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.457.8794","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.457.8794","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://music.ece.drexel.edu/files/Navigation/Publications/Schmidt2011.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.41999998688697815}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W79265767","https://openalex.org/W858155270","https://openalex.org/W2011853905","https://openalex.org/W2100495367","https://openalex.org/W2107789863","https://openalex.org/W2110798204","https://openalex.org/W2133285226","https://openalex.org/W2136922672","https://openalex.org/W2149628368","https://openalex.org/W2160929029","https://openalex.org/W2295991281","https://openalex.org/W2341090665","https://openalex.org/W6603211394","https://openalex.org/W6623798586","https://openalex.org/W6676071220","https://openalex.org/W6676481782","https://openalex.org/W6696901769","https://openalex.org/W6704344484"],"related_works":["https://openalex.org/W1107690805","https://openalex.org/W2097318409","https://openalex.org/W2739662815","https://openalex.org/W4360994129","https://openalex.org/W4313351211","https://openalex.org/W3125908420","https://openalex.org/W3038982524","https://openalex.org/W2138630609","https://openalex.org/W2800170478","https://openalex.org/W3031096864"],"abstract_inverted_index":{"The":[0],"medium":[1],"of":[2,10,23,62,72,111,123,194],"music":[3,20,55,105,126,195],"has":[4,58,142,154],"evolved":[5],"specifically":[6],"for":[7,16,35,54,120,148],"the":[8,63,70,73,77,83,107,159,186,191],"expression":[9],"emotions,":[11],"and":[12,47,89,163],"it":[13,38,198],"is":[14,31,69,188],"natural":[15,33],"us":[17],"to":[18,41,87,104,172,178,190,203],"organize":[19],"in":[21,65,106,125,145],"terms":[22],"its":[24],"emotional":[25,164],"associations.":[26,165],"But":[27],"while":[28],"such":[29,49],"organization":[30],"a":[32,43,114],"process":[34],"humans,":[36],"quantifying":[37],"empirically":[39],"proves":[40],"be":[42,200],"very":[44],"difficult":[45],"task,":[46],"as":[48,113],"no":[50],"dominant":[51],"feature":[52,133,207],"representation":[53,110],"emotion":[56,84,124,196],"recognition":[57],"yet":[59],"emerged.":[60],"Much":[61],"difficulty":[64],"developing":[66],"emotion-based":[67],"features":[68,180],"ambiguity":[71],"ground-truth.":[74],"Even":[75],"using":[76],"smallest":[78],"time":[79],"window,":[80],"opinions":[81],"on":[82],"are":[85],"bound":[86],"vary":[88],"reflect":[90],"some":[91],"disagreement":[92],"between":[93,161],"listeners.":[94],"In":[95,166],"previous":[96],"work,":[97],"we":[98,170],"have":[99],"modeled":[100],"human":[101],"response":[102],"labels":[103],"arousal-valence":[108],"(A-V)":[109],"affect":[112],"time-varying,":[115],"stochastic":[116],"distribution.":[117],"Current":[118],"methods":[119],"automatic":[121],"detection":[122],"seek":[127,171],"performance":[128,151],"increases":[129],"by":[130],"combining":[131],"several":[132],"domains":[134],"(e.g.":[135],"loudness,":[136],"timbre,":[137],"harmony,":[138],"rhythm).":[139],"Such":[140],"work":[141,169],"focused":[143],"largely":[144],"dimensionality":[146],"reduction":[147],"minor":[149],"classification":[150],"gains,":[152],"but":[153],"provided":[155],"little":[156],"insight":[157],"into":[158],"relationship":[160],"audio":[162,206],"this":[167],"new":[168],"employ":[173],"regression-based":[174,205],"deep":[175],"belief":[176],"networks":[177],"learn":[179],"directly":[181],"from":[182],"magnitude":[183],"spectra.":[184],"While":[185],"system":[187],"applied":[189,202],"specific":[192],"problem":[193],"recognition,":[197],"could":[199],"easily":[201],"any":[204],"learning":[208],"problem.":[209]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":13},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":8},{"year":2015,"cited_by_count":11},{"year":2014,"cited_by_count":9},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":5}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}