Speech Emotion Recognition by Conventional Machine Learning andDeep Learning
- Lope, Javier de 1
- Enrique Hernández 1
- Vanessa Vargas 1
- Manuel Graña 2
-
1
Universidad Politécnica de Madrid
info
-
2
Universidad del País Vasco/Euskal Herriko Unibertsitatea
info
Universidad del País Vasco/Euskal Herriko Unibertsitatea
Lejona, España
- Hugo Sanjurjo González (coord.)
- Iker Pastor López (coord.)
- Pablo García Bringas (coord.)
- Héctor Quintián (coord.)
- Emilio Corchado (coord.)
Editorial: Springer International Publishing AG
ISBN: 978-3-030-86271-8, 978-3-030-86270-1
Año de publicación: 2021
Páginas: 319-330
Congreso: Hybrid Artificial Intelligent Systems (HAIS) (16. 2021. Bilbao)
Tipo: Aportación congreso
Resumen
This paper reports experimental results of speech emotion recognition by conventional machine learning methods and deep learning techniques. We use a selection of mel frequency cepstral coefficients (MFCCs) as features for the conventional machine learning classifiers. The convolutional neural network uses as features the mel spectrograms treated as images. We test both approaches over a state of the art free database that provides samples of 8 emotions recorded by 24 professional actors. We report and comment the accuracy achieved by each classifier in cross validation experiments. Results of our proposal are competitive with recent studies.