Speech Technology
We work on:
- Text-to-speech conversion
- Speech recognition
- Database collection
- Applications
Automatic Recognition of Sign Language
Goals:
- To build a progressively large dataset for Spanish SL and annotation tools
- To design and develop automatic sign recognition algorithms
- To serve of meeting point of stakeholders by organizing public events and disseminate the research results
Some dissemination results accessible in the Youtube channel:
- Presentations in different fora (spanish, english)
- Explanations of the web application created to recognize signs and cooperate with the project: Application SignaMed
Acoustics and Sound processing
Marine acoustics: we work on classifying underwater sounds using AI techniques, modelling and measuring underwater noise levels, analysing the effect of underwater noise on marine fauna, and cetacean bioacoustics.
- Marine Acoustics
Biometrics
We work on biometrics-based recognition of people with emphasis on Internet applications. The main issues addressed by our research are:
- Robustness of monomodal biometric systems (speaker and face recogntion).
- Multimodal biometric systems.
Advanced Speech and Image Processing Techniques for Detecting Neurological Disorders
We work on:
- Depression Detection
- Mild Cognitive Impairment Detection
- Database collection