A token-based accent normalization pipeline using HuBERT discrete tokens, TTS-synthesized targets, and flow matching improves accent conversion over a frame-to-frame baseline.
62401377), Shenzhen Science and Technology Program (Shenzhen Key Laboratory, Grant No
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
-
Accent Normalization Using Self-Supervised Discrete Tokens with Non-Parallel Data
A token-based accent normalization pipeline using HuBERT discrete tokens, TTS-synthesized targets, and flow matching improves accent conversion over a frame-to-frame baseline.