A Lightweight Multi-Scale Model for Speech Emotion Recognition

• Published in: IEEE access Vol. 12; pp. 130228 - 130240
• Main Authors: Li, Haoming, Zhao, Daqi, Wang, Jingwen, Wang, Deqiang
• Format: Journal Article
• Language: English
• Published: IEEE 2024
• Subjects: attention mechanism; Attention mechanisms; center loss; Computational modeling; Convolutional neural networks; Emotion recognition; Feature extraction; Long short term memory; Mel frequency cepstral coefficient; MFCC; Spectrogram; Speech emotion recognition

Recognizing emotional states from speech is essential for human-computer interaction. It is challenging to realize effective speech emotion recognition (SER) on platforms with limited memory capacity and computing power. In this paper, we propose a lightweight multi-scale deep neural network archite...