I3A - Instituto de Investigación en Ingeniería de Aragón

About Us
About of us
About us
About us
About us
ViVoLabVoice Input Voice Output Laboratory
ViVoLab is a research laboratory on Speech Technologies. VivoLab has been recognized as “Grupo Consolidado de Investigación” (Quality Research Group) by the Regional Government of Aragón.
 
The primary goal of the lab is to become a national and international reference in the area of speech technologies. The research is focused around three main lines of action: the processing of acoustic information, technologies for human-machine interaction and technologies for indexing and retrieval of multimedia content.
 
ViVoLab is active in the following technologies among others:
 
  • Audio Segmentation
  • Speech Enhancement
  • Acoustic Modeling
  • Speaker Recognition and Identification
  • Speech Recognition
  • Large-Vocabulary Automatic Speech Recognition
  • Real-Time Live Broadcast News Subtitling
  • Tools for Computer-Aided Speech Therapy in Spanish Language
  •  
ViVoLab is heavily involved in the transfer of technology and knowledge with industries and the collaboration with national and international research groups. At the present, the group is composed by 6 doctors, 4 PhD students and 1 technician.

Research Lines

Information and Communication Technologies

Acoustic processing
  • Acoustic event detection and classification
  • Speaker Clustering and Diarization
  • Speaker Verification and Identification
  • Language Identification
  • Speech...
  • Acoustic event detection and classification
  • Speaker Clustering and Diarization
  • Speaker Verification and Identification
  • Language Identification
  • Speech Pathologies Detection and Identification
Speech technolgies for natural user interaction
  • Robust Speech Processing and Modeling
  • Automatic Speech Recognition
  • Text-to-Speech Conversion
  • Spoken Dialogue Systems
  • Personalization
  • Robust Speech Processing and Modeling
  • Automatic Speech Recognition
  • Text-to-Speech Conversion
  • Spoken Dialogue Systems
  • Personalization
Technologies for multimedia indexation and transcription
  • Audiovisual Document Segmentation and Classification
  • Audiovisual Recognition of Persons and Events
  • Audiovisual Content Indexing and Retrieval
  • Audiovisual Document Segmentation and Classification
  • Audiovisual Recognition of Persons and Events
  • Audiovisual Content Indexing and Retrieval
Speech Technologies Applications
  • Subtitling
  • Biometric Security Systems
  • Audiovisual Archives Documentation
  • Speech Technologies for e-inclusion
  • Subtitling
  • Biometric Security Systems
  • Audiovisual Archives Documentation
  • Speech Technologies for e-inclusion

Key Projects

Information and Communication Technologies

IRIS: Towards Natural Interaction and Communication.
Funded by: FP7- Marie Curie- IAPP

Grant agreement no.: 610986

Partners: Microsoft Portugal, UZ, UAveiro, FIMOporto, METU-...

Funded by: FP7- Marie Curie- IAPP

Grant agreement no.: 610986

Partners: Microsoft Portugal, UZ, UAveiro, FIMOporto, METU-Turquía.

Description: The overall goal of IRIS is to provide a natural interaction communication platform accessible and adapted for all users, particularly for people with speech impairments and elderly in indoor scenarios.

Human-Computer interaction with this platform will adopt the principles of universal design and natural user interfaces such as speech, silent speech, gestures, tactile and haptic devices, pictograms, animated characters and personalized synthetic voices.

The platform will provide a set of services that allow easy access to social networks, friends and remote family members, fighting social-exclusion of people with special needs or impairments. Application of these features will be performed in the context of serious games, virtual reality environments and assisted living scenarios. We will also explore the use of personalized avatars (that resemble with the user) in asynchronous human-human and human-machine communications, in situations where the user has lost his/her voice and in scenarios where it is not possible to have a video signal transmission due to low bandwidth or privacy reasons.

Biometrics will complement the platform, in the sense that authentication and authorization are fundamental aspects for assuring access security to personal information in a natural way.
 

MULAN: Audio, speech and language processing for multimedia analytics.
Partners: UZ, UPV, UPM, UPV/EHU, CICYT TIN2014-54288-C4-2-R.
 
Description: The main goal of this project is to explore the maturity...
Partners: UZ, UPV, UPM, UPV/EHU, CICYT TIN2014-54288-C4-2-R.
 
Description: The main goal of this project is to explore the maturity of diverse technologies, progress or develop them when necessary as well as use them to deal with multimedia document retrieval and analysis, focusing on the information provided by audio and speech. We thus contribute to multimedia information retrieval and other use cases such as the building of automatic market and reputation analysis from social media sources. In this context our two main strategic objectives are:
  • Developing audio, speech and language technologies devoted to
  1. Speech and audio information retrieval
  2. Multimedia information analytics
  3. Automatic output generation.
  • Transferring the acquired knowledge to the society trough dissemination and technology transfer actions.
BATVOX: The next generation of technology for speaker recognition in forensic environments
INNPACTO IPT-2011-1696-390000.
 
Partners: Agnitio, UZ
 
Description: The main objective of the project is...
INNPACTO IPT-2011-1696-390000.
 
Partners: Agnitio, UZ
 
Description: The main objective of the project is about research on speech technologies in order to achieve a prototype device with appropriate functionalities so that this new development, can industrialize and commercialize, a posteriori, in the market sector that includes the forensic field, in relation to security forces and law
© 2017 Instituto Universitario de Investigación en Ingeniería de Aragón - Universidad de Zaragoza | Policy