No AI summary available for this article.
Why It Matters
Emotion-conditioned text-to-speech (TTS) models may fail to express the requested emotion reliably, and improving controllability by additional training is costly in both computation and emotion-labeled speech training data.
Provenance
Discovered via ArXiv and published by ArXiv.
Key Claims
Original description
Emotion-conditioned text-to-speech (TTS) models may fail to express the requested emotion reliably, and improving controllability by additional training is costly in both computation and emotion-labeled speech training data. We therefore study vector steering, a training-free approach that modifies the internal representations of a frozen model. CoCoEmo, a conventional vector steering method for emotion TTS, treats each emotion vector as an indivisible direction controlled by a single global strength, limiting adherence to the requested emotion. In this work, we first discover that an emotion...
Discovered via ArXiv
Research papers and preprints from arXiv.
Publisher: arxiv.org
ID: http://arxiv.org/abs/2609.38157v1 · Indexed about 1 hour ago