Luca Della Libera
lucadellalib
AI & ML interests
Speech processing, Audio tokenization, ASR, Continual learning, Reinforcement learning
Recent Activity
authored
a paper
about 6 hours ago
Beyond Fixed Frames: Dynamic Character-Aligned Speech Tokenization
authored
a paper
4 days ago
Autoregressive Speech Enhancement via Acoustic Tokens
upvoted
a
paper
4 days ago
Beyond Fixed Frames: Dynamic Character-Aligned Speech Tokenization
Organizations
models
7
lucadellalib/focalcodec_12_5hz
Audio-to-Audio
•
Updated
•
275
•
2
lucadellalib/focalcodec_25hz
Audio-to-Audio
•
Updated
•
166
•
1
lucadellalib/focalcodec_50hz
Audio-to-Audio
•
Updated
•
1.2k
•
1
lucadellalib/focalcodec_50hz_65k_causal
Audio-to-Audio
•
Updated
•
56
lucadellalib/focalcodec_50hz_4k_causal
Audio-to-Audio
•
Updated
•
82
lucadellalib/focalcodec_50hz_2k_causal
Audio-to-Audio
•
Updated
•
271
lucadellalib/discrete-wavlm-codec
Updated
datasets
0
None public yet