TY - GEN
T1 - An Entropy-Based Computational Classifier for Positive and Negative Emotions in Voice Signals
AU - Herrera-Ortiz, A. D.
AU - Yáñez-Casas, G. A.
AU - Hernández-Gómez, J. J.
AU - Orozco-del-Castillo, M. G.
AU - Mata-Rivera, M. F.
AU - de la Rosa-Rábago, R.
N1 - Publisher Copyright:
© 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.
PY - 2022
Y1 - 2022
N2 - The detection, classification and analysis of emotions has been an intense research area in the last years. Most of the techniques applied for emotion recognition are those comprised by Artificial Intelligence, such as neural networks, machine learning and deep learning, which are focused on the training and learning of models. In this work, we propose a rather different approach to the problem of detection and classification of emotion within voice speech, regarding sound files as information sources in the context of Shannon’s information theory. By computing the entropy content of each audio, we find that emotion in speech can be classified into two subsets: positive and negative. To be able to perform the entropy computation, we first compute the Fourier transform to digital audio recordings, bearing in mind that the voice signal has a bandwidth 100 Hz and 4 kHz. The discrete Fourier spectrum is then used to set the alphabet and then the occurrence probabilities of each symbol (frequency) is used to compute the entropy for non-hysterical information sources. A dataset consisting of 1,440 voice audios performed by professional voice actors was analysed through this methodology, showing that in most cases, this simple approach is capable of performing the positive/negative emotion classification.
AB - The detection, classification and analysis of emotions has been an intense research area in the last years. Most of the techniques applied for emotion recognition are those comprised by Artificial Intelligence, such as neural networks, machine learning and deep learning, which are focused on the training and learning of models. In this work, we propose a rather different approach to the problem of detection and classification of emotion within voice speech, regarding sound files as information sources in the context of Shannon’s information theory. By computing the entropy content of each audio, we find that emotion in speech can be classified into two subsets: positive and negative. To be able to perform the entropy computation, we first compute the Fourier transform to digital audio recordings, bearing in mind that the voice signal has a bandwidth 100 Hz and 4 kHz. The discrete Fourier spectrum is then used to set the alphabet and then the occurrence probabilities of each symbol (frequency) is used to compute the entropy for non-hysterical information sources. A dataset consisting of 1,440 voice audios performed by professional voice actors was analysed through this methodology, showing that in most cases, this simple approach is capable of performing the positive/negative emotion classification.
KW - Computational entropy
KW - Emotion analysis
KW - Fourier transform
KW - Frequency alphabet
KW - Information source
KW - Information theory
KW - Pattern recognition
KW - Sound
KW - Speech
KW - Voice signals
UR - http://www.scopus.com/inward/record.url?scp=85142768169&partnerID=8YFLogxK
U2 - 10.1007/978-3-031-18082-8_7
DO - 10.1007/978-3-031-18082-8_7
M3 - Contribución a la conferencia
AN - SCOPUS:85142768169
SN - 9783031180811
T3 - Communications in Computer and Information Science
SP - 100
EP - 121
BT - Telematics and Computing - 11th International Congress, WITCOM 2022, Proceedings
A2 - Mata-Rivera, Miguel Félix
A2 - Zagal-Flores, Roberto
A2 - Barria-Huidobro, Cristian
PB - Springer Science and Business Media Deutschland GmbH
T2 - 11th International Congress of Telematics and Computing, WITCOM 2022
Y2 - 7 November 2022 through 11 November 2022
ER -