A5091315707- Speech Recognition and Synthesis
- Speech and Audio Processing
- Environmental Toxicology and Ecotoxicology
- Digital Mental Health Interventions
- Anomaly Detection Techniques and Applications
- Usability and User Interface Design
- Speech and dialogue systems
- Mercury impact and mitigation studies
- Phonetics and Phonology Research
- Pharmaceutical and Antibiotic Environmental Impacts
- Digital Media Forensic Detection
- Innovative Human-Technology Interaction
- Impact of Technology on Adolescents
- Hearing Loss and Rehabilitation
- Toxic Organic Pollutants Impact
- Social Robot Interaction and HRI
- Industrial Vision Systems and Defect Detection
- Pesticide and Herbicide Environmental Studies
University of Aveiro
2020-2025
National Institute of Science and Technology for Software Engineering
2021
Speech is our most natural and efficient form of communication offers a strong potential to improve how we interact with machines. However, speech can sometimes be limited by environmental (e.g., ambient noise), contextual need for privacy), or health conditions laryngectomy), preventing the consideration audible speech. In this regard, silent interfaces (SSI) have been proposed as an alternative, considering technologies that do not require production acoustic signals electromyography...
Data-driven methods—particularly machine learning techniques—are expected to play a key role in the headway of Industry 4.0. One increasingly popular application this context is when anomaly detection employed test manufactured goods assembly lines. In work, we compare supervised, semi/weakly-supervised, and unsupervised strategies detect anomalous sequences video samples which may be indicative defective televisions assembled factory. We 3D autoencoders, convolutional neural networks,...