Rethinking Depth in Speech Encoder
Tuesday 21 April 2026
Starts 13:00 PM
Finishes 14:00 PM
Organized by Priberam
Venue: Instituto Superior Técnico, Anfiteatro PA2
Address: 1 Avenida Rovisco Pais
1049-001 Lisboa
About this event
Priberam Machine Learning Lunch Seminar
Abstract:
Nowadays, speech encoders are becoming increasingly powerful, but also larger and more complex. However, we observe significant redundancy within these models, which motivates a rethinking of how depth should be designed. In this talk, I will present a parameter-efficient alternative based on shared weights with recursive (looped) application of encoder layers, where a smaller set of parameters is reused across multiple iterations instead of stacking many distinct layers. This approach aims to preserve strong representational capacity while reducing model size.
Bio:
Thomas Rolland is a Postdoctoral Researcher at INESC-ID in Lisbon, focusing on building robust speech systems for low-resource, noisy, and domain-shifted settings. His work centers on parameter-efficient architectures, synthetic data augmentation, and post-training strategies to improve adaptability and fairness across diverse speech scenarios.
www.priberam.com
This page last updated Wednesday 8 April 2026 at 10:56.
Problems? Report an error or inappropriate listing here.
Information is provided in good faith but we are not responsible for the content of event listings. Sometimes events can be cancelled or changed at short notice. Please check with the venue or organizer before you travel.