Emotional prosody in LM-TTS localizes to the x-vector by elimination, where centroid arithmetic on speaker embeddings yields training-free cross-lingual gains of +0.29 emotion2vec cosine on English and +0.09 on Brazilian Portuguese while preserving identity.
Dataset, version 1.0.0
1 Pith paper cite this work, alongside 3 external citations. Polarity classification is still indexing.
1
Pith paper citing it
3
external citations · OpenAlex
fields
cs.SD 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Task-Vector Arithmetic for Emotional Expressivity Control in Language-Model-Based Text-to-Speech
Emotional prosody in LM-TTS localizes to the x-vector by elimination, where centroid arithmetic on speaker embeddings yields training-free cross-lingual gains of +0.29 emotion2vec cosine on English and +0.09 on Brazilian Portuguese while preserving identity.