Luca Della Libera
lucadellalib
AI & ML interests
Speech processing, Audio tokenization, ASR, Continual learning, Reinforcement learning
Recent Activity
upvoted
a
paper
about 8 hours ago
Beyond Fixed Frames: Dynamic Character-Aligned Speech Tokenization
upvoted
a
paper
about 8 hours ago
UniAudio 2.0: A Unified Audio Language Model with Text-Aligned Factorized Audio Tokenization
submitted
a paper
about 8 hours ago
Beyond Fixed Frames: Dynamic Character-Aligned Speech Tokenization
Organizations
models
7
lucadellalib/focalcodec_12_5hz
Audio-to-Audio
•
Updated
•
311
•
2
lucadellalib/focalcodec_25hz
Audio-to-Audio
•
Updated
•
231
•
1
lucadellalib/focalcodec_50hz
Audio-to-Audio
•
Updated
•
1.27k
•
1
lucadellalib/focalcodec_50hz_65k_causal
Audio-to-Audio
•
Updated
•
54
lucadellalib/focalcodec_50hz_4k_causal
Audio-to-Audio
•
Updated
•
73
lucadellalib/focalcodec_50hz_2k_causal
Audio-to-Audio
•
Updated
•
299
lucadellalib/discrete-wavlm-codec
Updated
datasets
0
None public yet