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.
We study the way to convert the non-native (L2) accented speech into a native (L1) accented one
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
eess.AS 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 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.