Search results

Crédit: RTS.ch, la première, émission CQFD, 5 octobre 2012

Revisiting autoencoders for speech representation learning

“The deep artificial neural networks are inspired from the hierarchical structure of the human brain. Therefore, questioning the neural networks to learn ...

Roxanne Bi-Annual Newsletter: First and Second Edition

Edition: April 2020 and September 2020

SDialog : la boîte à outils en libre accès de l’Idiap pour une IA reproductible

Construire des systèmes d’intelligence artificielle conversationnelle fiables — comme des chabots ou des assistant virtuels tel que Siri ou Alexa — est plus ...

SDialog: Idiap's Open-Source Toolkit for Reproducible Conversational AI

Building reliable conversational AI systems—such as chatbots or virtual assistants like Siri or Alexa—is more challenging than it may initially appear. ...

SIIP - Speaker Identification Integrated Project passes final field test

LYON, France – In its final field test, the Speaker Identification Integrated Project (SiiP) successfully demonstrated the system’s innovative capabilities as ...

The first Roxanne field test took place

Roxanne is a EU-funded project that leverages text, speech and video in real-time in order to build tools for combating organized crime.

The next Idiap Speaker Series will take place at Idiap on June 2nd 2017, room 106

The Prof. Marelie Davel will give the talk entitled: Multilingual speech recognition in under-resourced environments

The security of sensitive information: Prof. Hervé Bourlard interviewed for RTS’ radio show “CQFD”

How is it possible for people with bad intentions to get access to data from our smartphone or our GPS?

Un chercheur de l’Idiap décroche une subvention BRIDGE « Proof of Concept » pour la création d’un détecteur de deepfakes audio

Ajinkya Kulkarni, chercheur postdoctoral à l’Idiap, a obtenu une subvention SNSF Bridge « Proof of Concept » pour lutter contre une menace croissante en ...