Search results

Statistical and neural machine translation systems (in short, SMT and NMT) have reached significant quality and speed levels. Such systems use large amounts of ...

Eyeware creates natural and intuitive human-machine interaction experiences using eye-gaze tracking. We propose to design a novel, robust gaze estimation ...

Building, testing and adapting bespoke speaker identification models to be used in IDIAP's 'Bob.Spear' speaker recognition software

The work of John Antonakis and colleagues at UNIL has identified markers in the transcripts of speeches that are indicative of charisma. Charisma in turn has ...

Our ASR approaches have always used neural networks, Idiap researchers having pioneered the hybrid approach to ASR based on posterior probabilities. The work ...

Standard machine learning systems require massive data and huge processing infrastructures, but the main limitation to their spreading comes from the need of ...

There are an increasing number of people across Europe with debilitating speech pathologies (e.g., due to stroke, Alzeheimer's, Parkinson's, etc). These groups ...

Le but du présent projet est d’industrialiser la solution de transcription vocale développée par l’Idiap et la SUVA lors du projet RecoMed 313-13. Ce projet ...

The impact that migration has on individuals, notably with regard to maintaining their language, and with that the intrinsically linked issue of identity ...