Gustavo Assunção

Dr. Gustavo Assunção

orcid

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
16 March 2022 in IEEE Transactions on Artificial Intelligence
Verified
Journal Article
Closed access
Gustavo AssunçãoGustavo Assunção
Gustavo Assunção
BPBruno Patrão
Bruno Patrão
Miguel Castelo-BrancoMiguel Castelo-Branco
Miguel Castelo-Branco
PMPaulo Menezes
Paulo Menezes
The field of Artificial Intelligence (AI) has gained immense traction over the past decade, producing increasingly successful applications as research strives to understand and exploit neural processing specifics. Nonetheless emotion, despite its demonstrated significance to reinforcement, social integration and general development, remains a largely stigmatized and consequently disregarded topic by most engineers and computer scientists. In this paper we endorse emotion's value for the advancement of artificial cognitive processing, as well as explore real-world use cases of emotion-augmented AI. A schematization is provided on the psychological-neurophysiologic basics of emotion in order to bridge the interdisciplinary gap preventing emulation and integration in AI methodology, as well as exploitation by current systems. In addition we overview three major subdomains of AI greatly benefiting from emotion, and produce a systematic survey of meaningful yet recent contributions to each area. To conclude, we address crucial challenges and promising research paths for the future of emotion in AI with the hope that more researchers will develop an interest for the topic and find it easier to develop their own contributions.

8 April 2020 in International Journal of Online and Biomedical Engineering (iJOE)
Verified
Journal Article
Open access
PDF file
Gustavo AssunçãoGustavo Assunção
Gustavo Assunção
PMPaulo Menezes
Paulo Menezes
FPFernando Perdigão
Fernando Perdigão
The idea of recognizing human emotion through speech (SER) has recently received considerable attention from the research community, mostly due to the current machine learning trend. Nevertheless, even the most successful methods are still rather lacking in terms of adaptation to specific speakers and scenarios, evidently reducing their performance when compared to humans. In this paper, we evaluate a largescale machine learning model for classification of emotional states. This model has been trained for speaker iden- tification but is instead used here as a front-end for extracting robust features from emotional speech. We aim to verify that SER improves when some speak- er’s emotional prosody cues are considered. Experiments using various state-of- the-art classifiers are carried out, using the Weka software, so as to evaluate the robustness of the extracted features. Considerable improvement is observed when comparing our results with other SER state-of-the-art techniques.

1 July 2020
Verified
Conference Paper
Closed access
Gustavo AssunçãoGustavo Assunção
Gustavo Assunção
PMPaulo Menezes
Paulo Menezes
Affective systems are getting increasingly more attention from researchers and high-tech companies in order to enable the acknowledgment or adaptation to a user’s mood. Emotion classification is typically a hard problem due to the number of subtle cues which are present in human facial and body expressions, or in voiced utterances. Another critical factor is that typically used models tend to map emotions into all-or-nothing regions with artificially sharp divisions among them, a view which is rather unsupported in the field of psychology and human behavioral analysis. In this paper we propose the inclusion of an intermediary fuzzy layer in a VGGVox-based NN, whose aim is to deal with the inherently foggy transitions between emotional states. This neuro-fuzzy model was trained and evaluated against four emotional speech databases and has shown improvements in the classification performance over a non-fuzzy counterpart. Observed performances were also on-par or above those of other current state-of-the-art techniques.

10 April 2021 in Applied Sciences
Verified
Journal Article
Open access
PDF file
Gustavo AssunçãoGustavo Assunção
Gustavo Assunção
Nuno GonçalvesNuno Gonçalves
Nuno Gonçalves
PMPaulo Menezes
Paulo Menezes
Human beings have developed fantastic abilities to integrate information from various sensory sources exploring their inherent complementarity. Perceptual capabilities are therefore heightened, enabling, for instance, the well-known "cocktail party" and McGurk effects, i.e., speech disambiguation from a panoply of sound signals. This fusion ability is also key in refining the perception of sound source location, as in distinguishing whose voice is being heard in a group conversation. Furthermore, neuroscience has successfully identified the superior colliculus region in the brain as the one responsible for this modality fusion, with a handful of biological models having been proposed to approach its underlying neurophysiological process. Deriving inspiration from one of these models, this paper presents a methodology for effectively fusing correlated auditory and visual information for active speaker detection. Such an ability can have a wide range of applications, from teleconferencing systems to social robotics. The detection approach initially routes auditory and visual information through two specialized neural network structures. The resulting embeddings are fused via a novel layer based on the superior colliculus, whose topological structure emulates spatial neuron cross-mapping of unimodal perceptual fields. The validation process employed two publicly available datasets, with achieved results confirming and greatly surpassing initial expectations.

1 June 2019
Verified
Conference Paper
Closed access
Gustavo AssunçãoGustavo Assunção
Gustavo Assunção
PMPaulo Menezes
Paulo Menezes
FPFernando Perdigao
Fernando Perdigao
The recognition of emotions is an inherent ability possessed by humans, which has long intrigued many researchers. Primarily due to the possibility of its successful emulation and integration in independent systems. Further, speech, being a mixture of utterances conveying a state of mind, proves to be a suitable candidate from which emotionality can be inferred, due to its many feature variations. This is corroborated by human beings themselves using this modality for extraction of emotionality clues. Another important aspect has to do with communicational register adaptation and the skill to discern different emotions in different speakers. Sure enough, the same emotional utterance may be interpreted divergently for two different people, meaning emotionality specific information is present in a speaker’s personal register. As a demo, we propose a real-time automatic emotion recognition system from speech, based on the use of the well established VGG-like convolutional neural network speaker recognition model VGGVox, trained with over 100,000 utterances from the VoxCeleb1 dataset on speaker recognition, for emotional feature extraction and feeding to state-of-the-art classifiers for accurate recognition of emotional states. Positive supporting results have been captivating enough to spark interest in the technique.

9 September 2025 in AI
Verified
Journal Article
Open access
PDF file
Gustavo AssunçãoGustavo Assunção
Gustavo Assunção
Miguel Castelo-BrancoMiguel Castelo-Branco
Miguel Castelo-Branco
PMPaulo Menezes
Paulo Menezes
Background: Exploration of the physical environment is an indispensable precursor to information acquisition and knowledge consolidation for living organisms. Yet, current artificial intelligence models lack these autonomy capabilities during training, hindering their adaptability. This work proposes a learning framework for artificial agents to obtain an intrinsic exploratory drive, based on epistemic and achievement emotions triggered during data observation. Methods: This study proposes a dual-module reinforcement framework, where data analysis scores dictate pride or surprise, in accordance with psychological studies on humans. A correlation between these states and exploration is then optimized for agents to meet their learning goals. Results: Causal relationships between states and exploration are demonstrated by the majority of agents. A 15.4% mean increase is noted for surprise, with a 2.8% mean decrease for pride. Resulting correlations of ρsurprise=0.461 and ρpride=−0.237 are obtained, mirroring previously reported human behavior. Conclusions: These findings lead to the conclusion that bio-inspiration for AI development can be of great use. This can incur benefits typically found in living beings, such as autonomy. Further, it empirically shows how AI methodologies can corroborate human behavioral findings, showcasing major interdisciplinary importance. Ramifications are discussed.