← Back to all news
arXiv Machine Learning By Siyi Wang, Shihong Tan, Siyi Liu, Hong Jia, Gongping Huang, James Bailey, Ting Dang

CoCoEmo: Composable and Controllable Human-Like Emotional TTS via Activation Steering

Read the original on arXiv Machine Learning →

arXiv:2602. 03420v2 Announce Type: replace-cross Abstract: Emotional expression in human speech is nuanced and compositional, often involving multiple, sometimes conflicting, affective cues that may diverge from linguistic content.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv AI
Aug 26

EmoTra-TTS: Smooth Intra-Utterance Emotion Transitions for Speech Synthesis

EmoTra‑TTS introduces a method for smooth intra‑utterance emotion transitions in speech synthesis. It uses a multi‑pass flow blending pipeline, dual‑stage VAD conditioning, and direction‑magnitude decoupled injection to generate frame‑aligned emotional prosody. The system adds only 0.43% more parameters, incurs no latency, and outperforms four state‑of‑the‑art baselines and two commercial systems in emotion transition quality and overall preference tests.

By Tianchi Liu, Zeyang Song, Tianrui Wang, Zhipeng Li, Chenglin Xu, Yiwen Guo
llmsragmultimodalbenchmarks
More like this →
arXiv Computation and Language
Aug 27

Controllable Affective Generation via Latent Vector Steering

The paper introduces EmoVec, a lightweight framework that enables controllable affective generation in large language models by steering latent vectors. EmoVec identifies emotion-specific directions from paired neutral and emotion-conditioned responses using contrastive activation addition, then refines these directions through task-specific debiasing and principal subspace removal. During inference, the refined vectors are injected into the final residual stream with static or scenario-adaptive scaling, allowing continuous control over emotional intensity without updating model weights, and experiments across three LLMs and eight emotions demonstrate improved emotional salience while preserving semantic content, fluency, and coherence.

By Xixian Yong, Siyuan Chang, Yingying Zhang, Xian Wu, Xiao Zhou
llmsbenchmarkssafety
More like this →