Feature selection enhancement and feature space visualization for speech-based emotion recognition

<p dir="ltr">Robust speech emotion recognition relies on the quality of the speech features. We present speech features enhancement strategy that improves speech emotion recognition. We used the INTERSPEECH 2010 challenge feature-set. We identified subsets from the features set and a...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Sofia Kanwal (12256565) (author)
مؤلفون آخرون: Sohail Asghar (11017743) (author), Hazrat Ali (421019) (author)
منشور في: 2022
الموضوعات:
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1864513516849856512
author Sofia Kanwal (12256565)
author2 Sohail Asghar (11017743)
Hazrat Ali (421019)
author2_role author
author
author_facet Sofia Kanwal (12256565)
Sohail Asghar (11017743)
Hazrat Ali (421019)
author_role author
dc.creator.none.fl_str_mv Sofia Kanwal (12256565)
Sohail Asghar (11017743)
Hazrat Ali (421019)
dc.date.none.fl_str_mv 2022-11-04T03:00:00Z
dc.identifier.none.fl_str_mv 10.7717/peerj-cs.1091
dc.relation.none.fl_str_mv https://figshare.com/articles/journal_contribution/Feature_selection_enhancement_and_feature_space_visualization_for_speech-based_emotion_recognition/25539598
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Information and computing sciences
Data management and data science
Human-centred computing
Machine learning
Feature selection
Feature space visualization
t-SNE graphs
SVM
Speech emotion recognition
Machine learning
Speaker-independent emotion recognition
dc.title.none.fl_str_mv Feature selection enhancement and feature space visualization for speech-based emotion recognition
dc.type.none.fl_str_mv Text
Journal contribution
info:eu-repo/semantics/publishedVersion
text
contribution to journal
description <p dir="ltr">Robust speech emotion recognition relies on the quality of the speech features. We present speech features enhancement strategy that improves speech emotion recognition. We used the INTERSPEECH 2010 challenge feature-set. We identified subsets from the features set and applied principle component analysis to the subsets. Finally, the features are fused horizontally. The resulting feature set is analyzed using t-distributed neighbour embeddings (t-SNE) before the application of features for emotion recognition. The method is compared with the state-of-the-art methods used in the literature. The empirical evidence is drawn using two well-known datasets: Berlin Emotional Speech Dataset (EMO-DB) and Ryerson Audio-Visual Database of Emotional Speech and Song (RAVDESS) for two languages, German and English, respectively. Our method achieved an average recognition gain of 11.5% for six out of seven emotions for the EMO-DB dataset, and 13.8% for seven out of eight emotions for the RAVDESS dataset as compared to the baseline study.</p><h2>Other Information</h2><p dir="ltr">Published in: PeerJ Computer Science<br>License: <a href="https://creativecommons.org/licenses/by/4.0/" target="_blank">https://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.7717/peerj-cs.1091" target="_blank">https://dx.doi.org/10.7717/peerj-cs.1091</a></p>
eu_rights_str_mv openAccess
id Manara2_e95052248950c6856fa1caec445da0c1
identifier_str_mv 10.7717/peerj-cs.1091
network_acronym_str Manara2
network_name_str Manara2
oai_identifier_str oai:figshare.com:article/25539598
publishDate 2022
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling Feature selection enhancement and feature space visualization for speech-based emotion recognitionSofia Kanwal (12256565)Sohail Asghar (11017743)Hazrat Ali (421019)Information and computing sciencesData management and data scienceHuman-centred computingMachine learningFeature selectionFeature space visualizationt-SNE graphsSVMSpeech emotion recognitionMachine learningSpeaker-independent emotion recognition<p dir="ltr">Robust speech emotion recognition relies on the quality of the speech features. We present speech features enhancement strategy that improves speech emotion recognition. We used the INTERSPEECH 2010 challenge feature-set. We identified subsets from the features set and applied principle component analysis to the subsets. Finally, the features are fused horizontally. The resulting feature set is analyzed using t-distributed neighbour embeddings (t-SNE) before the application of features for emotion recognition. The method is compared with the state-of-the-art methods used in the literature. The empirical evidence is drawn using two well-known datasets: Berlin Emotional Speech Dataset (EMO-DB) and Ryerson Audio-Visual Database of Emotional Speech and Song (RAVDESS) for two languages, German and English, respectively. Our method achieved an average recognition gain of 11.5% for six out of seven emotions for the EMO-DB dataset, and 13.8% for seven out of eight emotions for the RAVDESS dataset as compared to the baseline study.</p><h2>Other Information</h2><p dir="ltr">Published in: PeerJ Computer Science<br>License: <a href="https://creativecommons.org/licenses/by/4.0/" target="_blank">https://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.7717/peerj-cs.1091" target="_blank">https://dx.doi.org/10.7717/peerj-cs.1091</a></p>2022-11-04T03:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.7717/peerj-cs.1091https://figshare.com/articles/journal_contribution/Feature_selection_enhancement_and_feature_space_visualization_for_speech-based_emotion_recognition/25539598CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/255395982022-11-04T03:00:00Z
spellingShingle Feature selection enhancement and feature space visualization for speech-based emotion recognition
Sofia Kanwal (12256565)
Information and computing sciences
Data management and data science
Human-centred computing
Machine learning
Feature selection
Feature space visualization
t-SNE graphs
SVM
Speech emotion recognition
Machine learning
Speaker-independent emotion recognition
status_str publishedVersion
title Feature selection enhancement and feature space visualization for speech-based emotion recognition
title_full Feature selection enhancement and feature space visualization for speech-based emotion recognition
title_fullStr Feature selection enhancement and feature space visualization for speech-based emotion recognition
title_full_unstemmed Feature selection enhancement and feature space visualization for speech-based emotion recognition
title_short Feature selection enhancement and feature space visualization for speech-based emotion recognition
title_sort Feature selection enhancement and feature space visualization for speech-based emotion recognition
topic Information and computing sciences
Data management and data science
Human-centred computing
Machine learning
Feature selection
Feature space visualization
t-SNE graphs
SVM
Speech emotion recognition
Machine learning
Speaker-independent emotion recognition