DiffSoundStream uses a latent diffusion decoder conditioned on WavLM semantic tokens and coarse SoundStream acoustic tokens to match 100-token-per-second quality at 50 tokens per second.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.AS 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
DiffSoundStream: Efficient Speech Tokenization via Diffusion Decoding
DiffSoundStream uses a latent diffusion decoder conditioned on WavLM semantic tokens and coarse SoundStream acoustic tokens to match 100-token-per-second quality at 50 tokens per second.