9 papers
A Geometric Perspective on Composable Emotion Steering in Text-to-Speech Models
Siyi Wang, James Bailey, Ting Dang
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 un…
A Fusion-Aware Two-Stage Framework for Mispronunciation Detection and Diagnosis in Low-Resource Modern Standard Arabic
Jing Yang, Shuqing Zhang, Yongyi Deng +5
Accurate phoneme recognition is pivotal for mispronunciation detection and diagnosis (MDD) in modern standard Arabic (MSA), yet remains constrained by data scarcity and the synthet…
CoCoEmo: Composable and Controllable Human-Like Emotional TTS via Activation Steering
Siyi Wang, Shihong Tan, Siyi Liu +4
Emotional expression in human speech is nuanced and compositional, often involving multiple, sometimes conflicting, affective cues that may diverge from linguistic content. In cont…
Titans-as-a-Layer: Test-Time Memory for Conversational Speech Emotion Recognition
Daniel Chen, Qicong Hu, Yang Xiao +2
Speech emotion recognition (SER) is commonly formulated as utterance-level classification, although conversational emotion depends on a speaker's usual vocal range and the emotiona…
Adaptive Federated Fine-Tuning of Self-Supervised Speech Representations
Xin Guo, Chunrui Zhao, Hong Jia +4
Integrating Federated Learning (FL) with self-supervised learning (SSL) enables privacy-preserving fine-tuning for speech tasks. However, federated environments exhibit significant…
Emotion-Aware Quantization for Discrete Speech Representations: An Analysis of Emotion Preservation
Haoguang Zhou, Siyi Wang, Jingyao Wu +2
Modern speech systems increasingly use discretized self-supervised speech representations for compression and integration with token-based models, yet their impact on emotional inf…