arXiv Machine Learning July 2, 2026 By Siyi Wang, James Bailey, Ting Dang

A Geometric Perspective on Composable Emotion Steering in Text-to-Speech Models

Read the original on arXiv Machine Learning →

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.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

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.

By Siyi Wang, Shihong Tan, Siyi Liu, Hong Jia, Gongping Huang, James Bailey, Ting Dang

multimodal

arXiv AI

Jun 16

An Empirical Study on Learning Latent Representations for Emotional Speech Synthesis

arXiv:2606. 14922v1 Announce Type: cross Abstract: For the last couple of years, the field of speech synthesis has improved dramatically thanks to deep learning.

By Vinh Dang Quang, Huy Ngo Quang

rag

arXiv AI

Jul 20

AuEmoChat: Authentic Emotion Understanding and Rendering for Conversational Speech Synthesis

arXiv:2607. 15755v1 Announce Type: cross Abstract: Conversational Speech Synthesis (CSS) aims to synthesize speech with human-like emotional expression and contextual consistency in user-agent interactions.

By Zhenqi Jia, Yuan Zhao, Aruukhan, Rui Liu, Haizhou Li

agents diffusion efficiency multimodal benchmarks

arXiv AI

Jul 2

Enhancing Flow Matching with A Unified Guidance Framework for Efficient and Robust Speech Synthesis

arXiv:2607. 00363v1 Announce Type: cross Abstract: Flow Matching (FM) has emerged as a powerful paradigm for speech generation but remains constrained by high inference latency and timbre leakage.

By Zuda Yu, Qianhui Xu, Ting Chen, Junhui Zhang, Tao Fu, Hongjiang Yu, Qiangqing Wang, Yang Song

diffusion efficiency benchmarks

arXiv Machine Learning

Jun 2

Sympatheia: Emotionally Adaptive Voice Assistant with Continuous Affect Conditioning

arXiv:2606. 00851v1 Announce Type: cross Abstract: Empathetic spoken dialogue systems must infer a user's emotional state to respond appropriately, yet everyday speech often carries weak, neutral, or ambiguous affective cues.

By Sukru Samet Dindar, Riki Shimizu, Xilin Jiang, Nima Mesgarani

multimodal safety

arXiv Machine Learning

Jun 8

TargetSEC: Plug-and-Play In-the-Wild Speech Emotion Conversion via Arousal-Conditioned Latent Style Diffusion

arXiv:2606. 07293v1 Announce Type: cross Abstract: Speech Emotion Conversion (SEC) aims to transform the emotion of a source utterance into a target emotion while preserving content and speaker identity.

By Constantin Alexander Auga

rag diffusion

Related stories

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

An Empirical Study on Learning Latent Representations for Emotional Speech Synthesis

AuEmoChat: Authentic Emotion Understanding and Rendering for Conversational Speech Synthesis

Enhancing Flow Matching with A Unified Guidance Framework for Efficient and Robust Speech Synthesis

Sympatheia: Emotionally Adaptive Voice Assistant with Continuous Affect Conditioning

TargetSEC: Plug-and-Play In-the-Wild Speech Emotion Conversion via Arousal-Conditioned Latent Style Diffusion