-
Idiap at ICASSP 2021
by admin
—
published
Apr 21, 2021
—
filed under:
Speech Processing
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 ...
Located in
Research
/
Speech & Audio Processing
/
Speech and Audio Processing Group News
-
Learning to transcribe Swiss German dialects
by admin
—
published
Apr 21, 2021
—
filed under:
Speech Processing
Improving Swiss German speech recognition for Swisscom TV Box Voice Assistant
Located in
Research
/
Speech & Audio Processing
/
Speech and Audio Processing Group News
-
Adjustable Deterministic Pseudonymization of Speech
by admin
—
published
Apr 21, 2021
—
filed under:
Speech Processing
Obfuscating Voice Identity
Located in
Research
/
Speech & Audio Processing
/
Speech and Audio Processing Group News
-
Prof. Hervé Bourlard to receive the Prestigious IEEE 2022 James L. Flanagan Speech and Audio Processing Award
by nicolas-filippov
—
published
Jul 06, 2021
—
last modified
Jul 07, 2021 08:49 AM
—
filed under:
Speech Processing
Director of the Idiap Research Institute and Professor at EPFL, Hervé Bourlard is recognized for his major contributions to neural networks for statistical ...
Located in
Research
/
Speech & Audio Processing
/
Speech and Audio Processing Group News
-
How to adapt your pretrained models for ASR?
by admin
—
published
Jul 07, 2021
—
last modified
Jul 07, 2021 03:28 PM
—
filed under:
Speech Processing
Understanding the impact of self-supervised pretraining approaches on low resource speech recognition.
Located in
Research
/
Speech & Audio Processing
/
Speech and Audio Processing Group News
-
Idiap at INTERSPEECH 2021
by admin
—
published
Jul 14, 2021
—
last modified
Jul 14, 2021 02:07 PM
—
filed under:
Speech Processing
(August 30 - September 3, 2021, Brno, Czech Republic)
Located in
Research
/
Speech & Audio Processing
/
Speech and Audio Processing Group News
-
Revisiting autoencoders for speech representation learning
by admin
—
published
Jul 16, 2021
—
filed under:
Speech Processing
“The deep artificial neural networks are inspired from the hierarchical structure of the human brain. Therefore, questioning the neural networks to learn ...
Located in
Research
/
Speech & Audio Processing
/
Speech and Audio Processing Group News
-
Controllability and Interpretability in Affective Speech Synthesis
by Maxime Bourlard
—
published
Mar 14, 2022
—
last modified
Mar 14, 2022 04:26 PM
—
filed under:
Speech Processing
In his research work, Idiap student, Bastian Schnell believes that affective TTS can be enabled with models which generalise better to the variability in ...
Located in
Research
/
Speech & Audio Processing
/
Speech and Audio Processing Group News