The Observation of Actors’ Vocal Emotion Exercises with Deep Learning and Spectral Analysis-Reference-Cited by-同舟云学术

The Observation of Actors’ Vocal Emotion Exercises with Deep Learning and Spectral Analysis

Published:2024-03-01 Issue: Volume:21 Page:153-159
ISSN:2224-3402
Container-title:WSEAS TRANSACTIONS ON INFORMATION SCIENCE AND APPLICATIONS
language:en
Short-container-title:

Author:

Bratan Costin Andrei¹,Tocila-Matasel Claudia²,Andrei Alexandra-Georgiana¹,Tebeanu Ana Voichita³,Franti Eduard⁴,Dascalu Monica¹,Ionescu Bogdan¹,Iana Gheorghe²,Bobeș Gabriela⁵,Morosanu Bogdan¹,Oproiu Ana-Maria⁶,Iorgulescu Gabriela⁶

Affiliation:

1. Faculty of Electronics, Telecommunications and Informational Technology, National University of Science and Technology Politehnica, Splaiul Independenței 313, Bucharest 060042, ROMANIA

2. MEDIMA Health, Odăii 42, Otopeni 075100, ROMANIA

3. Departamentul Pentru Pregătirea Personalului Didactic, National University of Science and Technology Politehnica, Splaiul Independenței 313, Bucharest 060042, ROMANIA

4. Romanian Academy Research Institute for Artificial Intelligence, Calea Victoriei 125, Bucharest 010071, ROMANIA

5. OKaua Theater Company and Pink Stil SRL, Bucharest, ROMANIA

6. Faculty of Medicine, University of Medicine and Pharmacy “Carol Davila”, Bulevardul Eroii Sanitari 8, Bucharest 050474, ROMANIA

Abstract

This paper presents two distinct methods that demonstrate the increased intensity of a specific emotion when the induced emotion is trained daily for 30 days. For this study, four actors participated in a 30-day exercise trial and were recorded each day using high-level audio equipment. The first method supporting our hypothesis is a deep learning approach. A convolutional neural network pre-trained on Mel-frequency cepstral coefficients analyzed the actors' recordings and delivered the intensity of the detected emotion. The CNN tested 3,561 segments of 0.2-second length, and the results showed a higher level of intensity on the final day of training for each participant. The second method is spectral analysis. The spectrograms generated on the first and final days of the experiment showed that the spectral composition on the final day had a wider range of frequencies than on the first day, further supporting our hypothesis.

Publisher

World Scientific and Engineering Academy and Society (WSEAS)

Reference27 articles.

1. Csikszentmihályi M., FLOW: The Psychology of Optimal Experience. Harper and Row, 1990. ISBN: 978-0-06-016253-5.

2. Nakamura J., Csikszentmihályi M., "Flow Theory and Research". In Snyder CR, Lopez SJ (eds.). Handbook of Positive Psychology. Oxford University Press. pp. 195–206, 20 December 2001. ISBN: 978-0-19-803094-2.

3. Csikszentmihályi M., "The flow experience and its significance for human psychology". Optimal experience: psychological studies of flow in consciousness. Cambridge, UK: Cambridge University Press. pp. 15–35, 1988. ISBN: 978-0-521-43809-4.E.

4. Wrigley W. J., Emmerson S. B., "The experience of the flow state in live music performance". Psychology of Music., 41 (3): 292–305, May 2013. doi:10.1177/0305735611425903. S2CID 144877389.

5. O'Neill S., "Flow Theory and the Development of Musical Performance Skills". Bulletin of the Council for Research in Music Education. 141 (141): 129–134. JSTOR 40318998 – via University of Illinois Press, 1999.