ReLMCodec's preserve-control-refine design yields a single-codebook speech codec that improves the predictability-reconstruction trade-off at 650 and 800 bps, with gains in downstream TTS.
NadavHar-Tuv,OrTal,andYossiAdi
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.AS 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
ReLMCodec: Designing Predictable Speech Tokens from Pre-Quantization Phoneme Structure
ReLMCodec's preserve-control-refine design yields a single-codebook speech codec that improves the predictability-reconstruction trade-off at 650 and 800 bps, with gains in downstream TTS.