-
WavSLM: Single-Stream Speech Language Modeling via WavLM Distillation
Paper • 2603.05299 • Published -
Beyond Fixed Frames: Dynamic Character-Aligned Speech Tokenization
Paper • 2601.23174 • Published • 3 -
FocalCodec-Stream: Streaming Low-Bitrate Speech Coding via Causal Distillation
Paper • 2509.16195 • Published • 1 -
FocalCodec: Low-Bitrate Speech Coding via Focal Modulation Networks
Paper • 2502.04465 • Published • 3
Luca Della Libera
lucadellalib
AI & ML interests
Speech processing, Audio tokenization, ASR, Continual learning, Reinforcement learning
Recent Activity
upvoted a collection 4 days ago
focalcodec updated a collection 4 days ago
focalcodec authored a paper about 1 month ago
WavSLM: Single-Stream Speech Language Modeling via WavLM DistillationOrganizations
-
WavSLM: Single-Stream Speech Language Modeling via WavLM Distillation
Paper • 2603.05299 • Published -
Beyond Fixed Frames: Dynamic Character-Aligned Speech Tokenization
Paper • 2601.23174 • Published • 3 -
FocalCodec-Stream: Streaming Low-Bitrate Speech Coding via Causal Distillation
Paper • 2509.16195 • Published • 1 -
FocalCodec: Low-Bitrate Speech Coding via Focal Modulation Networks
Paper • 2502.04465 • Published • 3
models 8
lucadellalib/dycast
Audio-to-Audio • Updated • 92 • 4
lucadellalib/focalcodec_12_5hz
Audio-to-Audio • Updated • 2.14k • 2
lucadellalib/focalcodec_25hz
Audio-to-Audio • Updated • 122 • 1
lucadellalib/focalcodec_50hz
Audio-to-Audio • Updated • 2.7k • 2
lucadellalib/focalcodec_50hz_65k_causal
Audio-to-Audio • Updated • 51
lucadellalib/focalcodec_50hz_4k_causal
Audio-to-Audio • Updated • 158
lucadellalib/focalcodec_50hz_2k_causal
Audio-to-Audio • Updated • 260
lucadellalib/discrete-wavlm-codec
Updated
datasets 0
None public yet