CrossAccent-TTS adds an Accent Intensity Controller to disentangled representations for controllable accent strength in cross-lingual TTS on Indic and L2 datasets.
Fi- nite scalar quantization enables redundant and transmission- robust neural audio compression at low bit-rates,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.AS 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
CrossAccent-TTS: Cross-Lingual Accent-Intensity Controllable Text-to-Speech via Disentangled Speaker and Accent Representations
CrossAccent-TTS adds an Accent Intensity Controller to disentangled representations for controllable accent strength in cross-lingual TTS on Indic and L2 datasets.