Multimodal explainable artificial intelligence: A comprehensive review of methodological advances and future research directions

N Rodis, C Sardianos, P Radoglou-Grammatikis… - IEEE …, 2024 - ieeexplore.ieee.org
Despite the fact that Artificial Intelligence (AI) has boosted the achievement of remarkable
results across numerous data analysis tasks, however, this is typically accompanied by a …

EEG-based multimodal emotion recognition: a machine learning perspective

H Liu, T Lou, Y Zhang, Y Wu, Y Xiao… - IEEE Transactions …, 2024 - ieeexplore.ieee.org
Emotion, a fundamental trait of human beings, plays a pivotal role in shaping aspects of our
lives, including our cognitive and perceptual abilities. Hence, emotion recognition also is …

Unsupervised discovery of interpretable visual concepts

CM Rodrigues, N Boutry, L Najman - Information Sciences, 2024 - Elsevier
Providing interpretability of deep-learning models to non-experts, while fundamental for a
responsible real-world usage, is challenging. Attribution maps from xAI techniques, such as …

Concept-based techniques for" musicologist-friendly" explanations in a deep music classifier

F Foscarin, K Hoedt, V Praher, A Flexer… - arXiv preprint arXiv …, 2022 - arxiv.org
Current approaches for explaining deep learning systems applied to musical data provide
results in a low-level feature space, eg, by highlighting potentially relevant time-frequency …

[PDF][PDF] Hybrid fusion based interpretable multimodal emotion recognition with insufficient labelled data

P Kumar, S Malik, B Raman - arXiv preprint arXiv:2208.11450, 2022 - academia.edu
The multimedia data has overgrown in the last few years, leading multimodal emotion
analysis to emerging as an important research trend [2]. Research in this direction aims to …

Towards interpretability in audio and visual affective machine learning: A review

DS Johnson, O Hakobyan, H Drimalla - arXiv preprint arXiv:2306.08933, 2023 - arxiv.org
Machine learning is frequently used in affective computing, but presents challenges due the
opacity of state-of-the-art machine learning methods. Because of the impact affective …

Learning unsupervised hierarchies of audio concepts

D Afchar, R Hennequin, V Guigue - arXiv preprint arXiv:2207.11231, 2022 - arxiv.org
Music signals are difficult to interpret from their low-level features, perhaps even more than
images: eg highlighting part of a spectrogram or an image is often insufficient to convey high …

A Framework for Counterfactual Explanation of Predictive Uncertainty in Multimodal Models

T Qiu, Q Li - IEEE Transactions on Neural Networks and …, 2024 - ieeexplore.ieee.org
Both predictive uncertainty estimation and visual explanation are crucial elements in helping
humans understand the artificial intelligence (AI) decision-making process and in building …

[HTML][HTML] Optimizing Speech Emotion Recognition with Machine Learning Based Advanced Audio Cue Analysis

N Pallewela, D Alahakoon, A Adikari, JE Pierce… - Technologies, 2024 - mdpi.com
In today's fast-paced and interconnected world, where human–computer interaction is an
integral component of daily life, the ability to recognize and understand human emotions has …

[PDF][PDF] Interpretabilty of Speech Emotion Recognition modelled using Self-Supervised Speech and Text Pre-Trained Embeddings.

KVV Girish, S Konjeti, J Vepa, O AI - Interspeech, 2022 - isca-archive.org
Speech emotion recognition (SER) is useful in many applications and is approached using
signal processing techniques in the past and deep learning techniques recently. Human …