Enhancing Speech Emotion Recognition Using Dual Feature Extraction Encoders
Sensors · 2023
DOI: 10.3390/s23146640 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, 2023. Verfasst von Ilkhomjon Pulatov und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Engineering, Gachon University, Seongnam 13120, Republic of Korea. Hauptthemen laut MEDLINE: Speech, Speech Perception. Die Arbeit wurde bisher 25-mal zitiert (Crossref) und nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: ministry of science and ICT, Korea Agency for Technology and Standards in 2022, Ministry of Oceans and Fisheries.
Abstract (Originalsprache)
Understanding and identifying emotional cues in human speech is a crucial aspect of human–computer communication. The application of computer technology in dissecting and deciphering emotions, along with the extraction of relevant emotional characteristics from speech, forms a significant part of this process. The objective of this study was to architect an innovative framework for speech emotion recognition predicated on spectrograms and semantic feature transcribers, aiming to bolster performance precision by acknowledging the conspicuous inadequacies in extant methodologies and rectifying them. To procure invaluable attributes for speech detection, this investigation leveraged two divergent strategies. Primarily, a wholly convolutional neural network model was engaged to transcribe speech spectrograms. Subsequently, a cutting-edge Mel-frequency cepstral coefficient feature abstraction approach was adopted and integrated with Speech2Vec for semantic feature encoding. These dual forms of attributes underwent individual processing before they were channeled into a long short-term memory network and a comprehensive connected layer for supplementary representation. By doing so, we aimed to bolster the sophistication and efficacy of our speech emotion detection model, thereby enhancing its potential to accurately recognize and interpret emotion from human speech. The proposed mechanism underwent a rigorous evaluation process employing two distinct databases: RAVDESS and EMO-DB. The outcome displayed a predominant performance when juxtaposed with established models, registering an impressive accuracy of 94.8% on the RAVDESS dataset and a commendable 94.0% on the EMO-DB dataset. This superior performance underscores the efficacy of our innovative system in the realm of speech emotion recognition, as it outperforms current frameworks in accuracy metrics.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Computer Engineering, Gachon University, Seongnam 13120, Republic of Korea.
- Department of Telecommunication Engineering, Nukus Branch of Tashkent University of Information Technologies Named after Muhammad Al-Khwarizmi, Nukus 230100, Uzbekistan.
ORCID-Profile: Fazliddin Makhmudov, Young-Im Cho
Förderung
- ministry of science and ICT
- Korea Agency for Technology and Standards in 2022
- Ministry of Oceans and Fisheries
Zitieren
APA
Pulatov, I., Oteniyazov, R., Makhmudov, F., & Cho, Y. I. (2023). Enhancing Speech Emotion Recognition Using Dual Feature Extraction Encoders. Sensors. https://doi.org/10.3390/s23146640
Vancouver
Pulatov I, Oteniyazov R, Makhmudov F, Cho YI. Enhancing Speech Emotion Recognition Using Dual Feature Extraction Encoders. Sensors. 2023. doi:10.3390/s23146640
BibTeX
@article{Pulatov2023,
author = {Pulatov, Ilkhomjon and Oteniyazov, Rashid and Makhmudov, Fazliddin and Cho, Young-Im},
title = {Enhancing Speech Emotion Recognition Using Dual Feature Extraction Encoders},
journal = {Sensors},
year = {2023},
doi = {10.3390/s23146640}
}
EUVIMED