EmoRES-TTS: Residual-Enhanced Vector Steering for Emotional Speech Generation
cs.SD, cs.CL, eess.AS
Submitted: 2026-09-29
Updated: 2026-09-29
Code: https://github.com/facebookresearch/EmoRES-TTS
Terminology
Sources
- Task-Vector Arithmetic for Emotional Expressivity Control in Language-Model-Based Text-to-Speech
- CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models
- Adaptive Multi-Subspace Representation Steering for Attribute Alignment in Large Language Models
- Steering Language Models With Activation Engineering
- A Geometric Perspective on Composable Emotion Steering in Text-to-Speech Models
- EmoSteer-TTS: Fine-Grained and Training-Free Emotion-Controllable Text-to-Speech via Activation Steering
- Qwen3-Omni Technical Report
- Representation Engineering: A Top-Down Approach to AI Transparency
Related papers
- Few-Shot Open-Set Audio Classification via Transductive Prototype Refinement and Class Logit Enhancement
- Spectral Masking and Interpolation Attack (SMIA): A Black-box Adversarial Attack against Voice Authentication and Anti-Spoofing Systems
- AVMeme Exam: A Multimodal Multilingual Multicultural Benchmark for LLMs' Contextual and Cultural Knowledge and Thinking
- SoundWeaver: Compositional Warm-Starting for Text-to-Audio Diffusion Serving
- WASIL: In-the-Wild Arabic Spoken Interactions with LLMs
- Efficient Audiovisual Speech Processing via MUTUD: Multimodal Training and Unimodal Deployment