Light-SERNet: A lightweight fully convolutional neural network for speech emotion recognition

Abstract

Detecting emotions directly from a speech signal plays an important role in effective human-computer interactions. Existing speech emotion recognition models require massive computational and storage resources, making them hard to implement concurrently with other machine-interactive tasks in embedded systems. In this paper, we propose an efficient and lightweight fully convolutional neural network for speech emotion recognition in systems with limited hardware resources. In the proposed FCNN model, various feature maps are extracted via three parallel paths with different filter sizes. This helps deep convolution blocks to extract high-level features, while ensuring sufficient separability. The extracted features are used to classify the emotion of the input speech segment. While our model has a smaller size than that of the state-of-the-art models, it achieves a higher performance on the IEMOCAP and EMO-DB datasets. The source code is available https: //github.com/AryaAftab/LIGHT-SERNET

The Emotion Probe: On the Universality of Cross-Linguistic and Cross-Gender Speech Emotion Recognition via Machine Learning

“…The most common algorithmic framework for automatic SER involves the extraction of features from audio data, in turn used to train classifiers. Despite various issues, including the scarcity of datasets or the presence of inter-individual differences, most studies involve either “traditional” ML classifiers (Support Vector Machines (SVM)) [ 18 , 19 , 20 , 21 , 22 , 23 ], neural networks (Multi-Layer Perceptrons (MLP)) [ 24 ], Long Short Term Memory (LSTM) networks, Deep Belief Networks (DBN) [ 22 ] or Convolutional Neural Networks (CNN) [ 25 , 26 , 27 ], and probabilistic models (Hidden Markov Models (HMM)) [ 6 , 28 ]. Table 1 outlines an overview of some representative works in the field of SER, along with the datasets and emotions used and classification accuracy, showing the prevalence of neural networks and SVM, often favored in other speech-based ML tasks as well [ 29 ].…”

Artificial Intelligence-Based Voice Assessment of Patients with Parkinson’s Disease Off and On Treatment: Machine vs. Deep-Learning Comparison

“…Other than being a reliable means to non-empirically quantify voice impairment in diseases that affect phonatory production, voice analysis is also a completely non-invasive, low-cost and pseudo-real-time solution for deploying telemedicine assessments. Voice-based AI solutions have been successfully experimentally investigated and employed in other medical fields such as dysphonia [ 31 , 32 , 33 ], COVID-19 and pulmonary diseases [ 20 , 22 , 34 , 35 ], and even emotion and stress recognition [ 24 , 36 ].…”