Voice Input Voice Output Laboratory

The Vivolab research group, recognized by the Government of Aragon as a reference group (T36_20R), focuses its activity around three main lines of action: the processing of audiovisual information, technologies for human-machine interaction and technologies for the analysis, indexing and recovery of multimedia content (text, audio and video). The common thread of these lines of research are the technologies of speech, language and machine learning.

The group has an eminently applied vocation, which is why it also presents a line of action focused on the development of applications such as subtitling in various modalities, with transfer to both the Aragonese Radio and Television Corporation (CARTV) as to RTVE, biometric security systems, with transfer to the company AGNITIO/NUANCE, documentation of large audiovisual repositories (CÁTEDRA RTVE-UZ) or the use of speech technologies for e-inclusion where it has collaborated with the Aragonese Portal for Augmentative and Alternative Communication (ARASAAC) and the Alborada special education college.


Exchanges for SPEech ReseArch aNd TechnOlogies

Developing the next generation of AI in the field of rare languages, robotics or education
logo UE