collaborators
Showing eess.ASShow all

5 papers · 1 filter

eess.AS2026

OneVoice: One Model, Triple Scenarios-Towards Unified Zero-shot Voice Conversion

Zhichao Wang, Tao Li, Wenshuo Ge +3

Recent progress of voice conversion~(VC) has achieved a new milestone in speaker cloning and linguistic preservation. But the field remains fragmented, relying on specialized model…

eess.AS2026

B-GRPO: Unsupervised Speech Emotion Recognition based on Batched-Group Relative Policy Optimization

Yingying Gao, Shilei Zhang, Runyan Yang +2

Unsupervised speech emotion recognition (SER) focuses on addressing the problem of data sparsity and annotation bias of emotional speech. Reinforcement learning (RL) is a promising…

eess.AS2024

On Calibration of Speech Classification Models: Insights from Energy-Based Model Investigations

Yaqian Hao, Chenguang Hu, Yingying Gao +2

For speech classification tasks, deep learning models often achieve high accuracy but exhibit shortcomings in calibration, manifesting as classifiers exhibiting overconfidence. The…

eess.AS2024

MFSN: Multi-perspective Fusion Search Network For Pre-training Knowledge in Speech Emotion Recognition

Haiyang Sun, Fulin Zhang, Yingying Gao +3

Speech Emotion Recognition (SER) is an important research topic in human-computer interaction. Many recent works focus on directly extracting emotional cues through pre-trained kno…

eess.AS2024

CEC: A Noisy Label Detection Method for Speaker Recognition

Yao Shen, Yingying Gao, Yaqian Hao +4

Noisy labels are inevitable, even in well-annotated datasets. The detection of noisy labels is of significant importance to enhance the robustness of speaker recognition models. In…