Speech Processing
Language Technologies
From voice to action: intelligent audio comprehension and generation We develop solutions that enable interaction with spoken language even in difficult conditions (noise, accents, imperfect recordings).
- Automatic transcription and subtitling: Real-time voice-to-text conversion, adapted to different acoustic environments and with speaker recognition.
- Voice synthesis and conversion: Creation of high-quality, natural-sounding artificial voices using advanced tools for voice synthesis and conversion.
- Detection of fake audio (deepfakes): Identification of manipulated or artificially generated audio, a crucial technology for security and fraud prevention.
- Speaker verification: Identity authentication using vocal biometric fingerprinting to enhance security in access and communications.
- Voice biomarkers: Processing of pathological speech and analysis of vocal patterns to detect health indicators or to aid in rehabilitation treatments.
- Avatar animation: Extraction of vocal characteristics to animate avatars expressively with real and synthetic audio.
- Emotion analysis: Detection of emotional state in the voice, useful for call centres or monitoring the customer experience.
- Noteworthy Projects
- Related News
05.06.2025
IKUN, a project developing large multimodal models for quality assurance and operator support in Smart Industry
IKUN aims to adapt advances in Artificial Intelligence to industrial environments, overcoming key barriers through the use of Large Multimodal Models.
24.04.2024
End of STREAMS, a platform that deploys connected AI services for transcription, translation and speech synthesis in multiple languages for the generation of multiple applications
The project, in collaboration with a consortium of seven companies and with Vicomtech as scientific-technological coordinator, has as its main objective the construction of a platform with multilingual and connectable AI services for transcription, translation, speech synthesis and audio description that allow the construction of various applications for batch processing and streaming of multimedia content.
18.12.2023
Vicomtech leads ADAPT-IA, a project aimed at the research and development of Artificial Intelligence applied to Language Technologies in Basque
Together with entities such as UPV/EHU, MAFEX, INVEMA, Artificial Intelligence Center, AIC-Automotive Intelligence Center or UZEI, the project develops a prototype per member and sector that integrates the R&D activities, with the aim of boosting and naturalising its integration in the industrial processes of different Basque sectors.
25.04.2022
Nerea and Mikel, the synthetic voices generated from Vicomtech with Artificial Intelligence for Eusko Jaurlaritza - Basque Government
The Basque Government presented last December 3rd the synthetic voice of Nerea during the commemorative event of the International Day of the Basque Language.
Looking for support for your next project? Contact us, we are looking forward to helping you.
