3 papers
cs.SD2025
Speaker Disentanglement of Speech Pre-trained Model Based on Interpretability
Xiaoxu Zhu, Junhua Li, Aaron J. Li +2
Self-supervised speech models learn representations that capture both content and speaker information. Yet this entanglement creates problems: content tasks suffer from speaker bia…
cs.SD2023
GNCformer Enhanced Self-attention for Automatic Speech Recognition
J. Li, Z. Duan, S. Li +2
In this paper,an Enhanced Self-Attention (ESA) mechanism has been put forward for robust feature extraction.The proposed ESA is integrated with the recursive gated convolution and…
cs.SD2023
Sim-T: Simplify the Transformer Network by Multiplexing Technique for Speech Recognition
Guangyong Wei, Zhikui Duan, Shiren Li +3
In recent years, a great deal of attention has been paid to the Transformer network for speech recognition tasks due to its excellent model performance. However, the Transformer ne…