Luca Della Libera's picture

Luca Della Libera

lucadellalib

·

https://github.com/lucadellalib

AI & ML interests

Speech processing, Audio tokenization, ASR, Continual learning, Reinforcement learning

Recent Activity

upvoted a collection 19 days ago

updated a collection 19 days ago

authored a paper about 2 months ago

WavSLM: Single-Stream Speech Language Modeling via WavLM Distillation

View all activity

Organizations

upvoted a collection 19 days ago

focalcodec

11 items • Updated 19 days ago • 4

upvoted 2 papers 3 months ago

Beyond Fixed Frames: Dynamic Character-Aligned Speech Tokenization

Paper • 2601.23174 • Published Jan 30 • 3

UniAudio 2.0: A Unified Audio Language Model with Text-Aligned Factorized Audio Tokenization

Paper • 2602.04683 • Published Feb 4 • 3

upvoted a paper about 1 year ago

FocalCodec: Low-Bitrate Speech Coding via Focal Modulation Networks

Paper • 2502.04465 • Published Feb 6, 2025 • 3