Better Spanish Emotion Recognition In-the-wild: Bringing Attention to Deep Spectrum Voice Analysis

TL;DR

This paper improves Spanish emotion recognition in real-world settings by introducing an attention-based deep spectrum voice analysis model that outperforms existing state-of-the-art methods on two datasets.

Contribution

It proposes a novel attention mechanism-based classifier for DeepSpectrum features, enhancing emotion recognition accuracy in Spanish in-the-wild datasets.

Findings

The DS-AM model outperforms state-of-the-art models on both datasets.

Attention mechanisms improve classification accuracy.

Cross-dataset testing reveals model bias and generalization capabilities.

Abstract

Within the context of creating new Socially Assistive Robots, emotion recognition has become a key development factor, as it allows the robot to adapt to the user's emotional state in the wild. In this work, we focused on the analysis of two voice recording Spanish datasets: ELRA-S0329 and EmoMatchSpanishDB. Specifically, we centered our work in the paralanguage, e.~g. the vocal characteristics that go along with the message and clarifies the meaning. We proposed the use of the DeepSpectrum method, which consists of extracting a visual representation of the audio tracks and feeding them to a pretrained CNN model. For the classification task, DeepSpectrum is often paired with a Support Vector Classifier --DS-SVC--, or a Fully-Connected deep-learning classifier --DS-FC--. We compared the results of the DS-SVC and DS-FC architectures with the state-of-the-art (SOTA) for ELRA-S0329 and EmoMatchSpanishDB. Moreover, we proposed our own classifier based upon Attention Mechanisms, namely DS-AM. We trained all models against both datasets, and we found that our DS-AM model outperforms the SOTA models for the datasets and the SOTA DeepSpectrum architectures. Finally, we trained our DS-AM model in one dataset and tested it in the other, to simulate real-world conditions on how biased is the model to the dataset.