2 papers
cs.SD2026
Where Does Timbre Hide? Localizing Speaker Information in Speech Signals
Yiquan Zhou, Yixuan Wang, Xiaozhe Qi +2
Timbre similarity is a key evaluation target for generative speech systems, including voice conversion, speaker-cloning text-to-speech, and zero-shot speech models. When the genera…
cs.LG2026
AMRD: Adaptive Multi-Teacher Relational Distillation for Lightweight Speech Emotion Recognition
Yuqi Li, Yi-Cheng Lin, Xianglong Wang +5
On-device speech emotion recognition (SER) is critical for real-time applications, yet large self-supervised models that excel at SER are too costly for edge devices. Multi-teacher…