MPO improves TTS alignment by constructing multi-dimensional preference pairs and adding cross-entropy regularization to DPO, yielding better intelligibility, speaker similarity, and prosody.
LM-based TTS systems convert speech waveforms into sequences of discrete tokens using neural audio codecs [1, 2, 3, 4, 5] and operate in a discrete space [6, 7]
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.