Shengyu Peng

According to our database, Shengyu Peng authored at least 7 papers between 2024 and 2025.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of five.

2025

A Study of Multi-Scale Feature Learning From Pre-Trained Models on Speaker Verification.

Shengyu Peng, Wu Guo, Jie Zhang, Zuoliang Li, Yu Guan, Bin Gu, Yang Ai

Proceedings of the 2025 IEEE International Conference on Acoustics, 2025

Aligning Noisy-Clean Speech Pairs at Feature and Embedding Levels for Learning Noise-Invariant Speaker Representations.

Zuoliang Li, Yang Ai, Jie Zhang, Shengyu Peng, Yu Guan, Bin Gu, Wu Guo

Proceedings of the 2025 IEEE International Conference on Acoustics, 2025

Recursive Feature Learning from Pre-Trained Models for Spoofing Speech Detection.

Yu Guan, Yang Ai, Zuoliang Li, Shengyu Peng, Wu Guo

Proceedings of the 2025 IEEE International Conference on Acoustics, 2025

2024

Spoofing Speech Detection by Modeling Local Spectro-Temporal and Long-term Dependency.

Haochen Wu, Wu Guo, Zhentao Zhang, Wenting Zhao, Shengyu Peng, Jie Zhang

Proceedings of the 25th Annual Conference of the International Speech Communication Association, 2024

Adapter Learning from Pre-trained Model for Robust Spoof Speech Detection.

Haochen Wu, Wu Guo, Shengyu Peng, Zhuhai Li, Jie Zhang

Proceedings of the 25th Annual Conference of the International Speech Communication Association, 2024

Fine-tune Pre-Trained Models with Multi-Level Feature Fusion for Speaker Verification.

Shengyu Peng, Wu Guo, Haochen Wu, Zuoliang Li, Jie Zhang

Proceedings of the 25th Annual Conference of the International Speech Communication Association, 2024

Contrastive Learning and Inter-Speaker Distribution Alignment Based Unsupervised Domain Adaptation for Robust Speaker Verification.

Zuoliang Li, Wu Guo, Bin Gu, Shengyu Peng, Jie Zhang

Proceedings of the 25th Annual Conference of the International Speech Communication Association, 2024