MPO improves TTS alignment by constructing multi-dimensional preference pairs and adding cross-entropy regularization to DPO, yielding better intelligibility, speaker similarity, and prosody.
Dynamic time warping is employed to align the generated and reference speech features of different sequential lengths, following the evaluation script in ESPnet [29]
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
method 1
citation-polarity summary
fields
eess.AS 1years
2025 1verdicts
CONDITIONAL 1roles
method 1polarities
use method 1representative citing papers
citing papers explorer
-
MPO: Multidimensional Preference Optimization for Language Model-based Text-to-Speech
MPO improves TTS alignment by constructing multi-dimensional preference pairs and adding cross-entropy regularization to DPO, yielding better intelligibility, speaker similarity, and prosody.