Research lines

Audiovisual Information Processing
  • Speaker/Face Verification and identification
  • Language identification
  • Speaker/Face Diarization
  • Acoustic event detection & classification
  • Speech enhancement and audio quality assessment
Technologies for human-machine interaction
  • Robust voice modeling and processing
  • Automatic speech recognition
  • Natural language processing


Multimedia content retrieval & indexing
  • Classification and segmentation of audiovisual documents
  • Analysis and retrieval of audiovisual content
  • Multimodal person and event recognition
  • Multimedia content summarization
Aumentative and alternative communication & paralinguistics
  • Automatic assessment of pathological speech
  • Pictograms
  • Training assistant

PhD Thesis

Our group holds a large experience forming researchers in audio and speech processing, with several PhD Thesis succesfully presented in the last 20 years.

After finishing their PhD studies, former ViVoLab members have succesfully transitioned to senior researcher roles in both academia and industry.

In progress
Completed

Academic partners

Ir arriba