Search results

Idiap at ICASSP 2021

Idiap's speech group will be presenting six papers at ICASSP 2021. Our papers address a variety of research problems in pathological and physiological speech ...

Learning to transcribe Swiss German dialects

Improving Swiss German speech recognition for Swisscom TV Box Voice Assistant

Adjustable Deterministic Pseudonymization of Speech

Obfuscating Voice Identity

Prof. Hervé Bourlard to receive the Prestigious IEEE 2022 James L. Flanagan Speech and Audio Processing Award

Director of the Idiap Research Institute and Professor at EPFL, Hervé Bourlard is recognized for his major contributions to neural networks for statistical ...

How to adapt your pretrained models for ASR?

Understanding the impact of self-supervised pretraining approaches on low resource speech recognition.

Idiap at INTERSPEECH 2021

(August 30 - September 3, 2021, Brno, Czech Republic)

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 ...

Controllability and Interpretability in Affective Speech Synthesis

In his research work, Idiap student, Bastian Schnell believes that affective TTS can be enabled with models which generalise better to the variability in ...

Prix Idiap 2022

Chaque année, l’Institut nomme deux étudiants pour ses prix internes. En 2022, le prix de la publication scientifique est allé à Alexandre Bittar et celui de ...

Un système d’analyse de la parole inspiré par le cerveau humain

Les chercheurs de l’Idiap ont publié un papier décrivant une approche de l’analyse de la parole basée sur les propriétés du cerveau humain. Leur méthode s’est ...