arXiv Machine Learning
Steerspeech: Activation Steering For Emotion Control In Generated Speech
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv Computation and Language
Sep 30
EmoRES-TTS: Residual-Enhanced Vector Steering for Emotional Speech Generation
arXiv:2609.38157v1 Announce Type: cross Abstract: Emotion-conditioned text-to-speech (TTS) models may fail to express the requested emotion reliably, and improving controllability by additional train...
arXiv Machine Learning
Jun 17
CoCoEmo: Composable and Controllable Human-Like Emotional TTS via Activation Steering
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.
arXiv Computation and Language
Sep 1
Sequential Trajectories and Simultaneous Blending: Multi-Emotion Modeling for Instruction-Following TTS
arXiv:2608.30325v1 Announce Type: new Abstract: Natural-language instructions enable flexible control of synthesized speech, yet emotional TTS systems primarily model a single utterance-level affect,...
arXiv Computation and Language
6d ago
Steering Follows Geometry, Not Labels: Emotion Directions in a Full-Duplex Speech Model
The paper investigates emotion steering in Moshi, a fully open‑source full‑duplex speech language model, across four emotions. Using mean‑difference activation steering—just a few vector additions per frame and no retraining—the authors find that emotion can be linearly decoded from Moshi’s residual stream, but steering is only partially achievable and uneven: happy, angry and surprise steer toward a shared direction while sad is distinctly steerable. They also demonstrate that the shared component across the three emotions cannot simply be projected away from all emotions equally.
arXiv Machine Learning
Jul 2
A Geometric Perspective on Composable Emotion Steering in Text-to-Speech Models
arXiv:2607. 00946v1 Announce Type: cross Abstract: While prior work has explored emotion control in hybrid text-to-speech systems, the geometric properties of these modules, and their implications for steerability, remain poorly understood.
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.