Shao-Jung Chan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Shao-Jung Chan has a total of 3 co-authors. Here are the top co-authors by number of shared publications:
- Kuang-Yow Lian
National Taipei University of Technology
2 shared publications - Yeshanew Ale Wubet
Department of Electrical Engineering, National Taipei University of Technology, Taipei, Taiwan
1 shared publication Zong-En Wu
Department of Electrical Engineering, National Taipei University of Technology, Taipei, Taiwan
1 shared publication
Latest Publications
- Open Access
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- p. 1
Instant Response Keyword Spotting via Early Prediction in Streaming Speech
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- p. 1
Open AccessInstant Response Keyword Spotting via Early Prediction in Streaming Speech
- Open Access
- 29 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 23498-23507
DLiGRU-X: Efficient X-Vector-Based Embeddings for Small-Footprint Keyword Spotting System
Deployment of deep learning-based speech processing models for real-world applications on devices with limited processing capacity and memory constraints poses significant challenges. This paper introduces an enhanced deep learning model based on the X-vector architecture, named dilated light-gated recurrent unit in X-vector (DLiGRU-X) to address these challenges specifically for small-footprint keyword spotting (KWS) tasks. The DLiGRU-X model enhances temporal feature extraction with a LiGRU and reduces computational complexity through dilated convolution techniques. The proposed model efficiently learns speech signal characteristics, making it suitable for scenarios with limited hardware resources and can handle an expanded vocabulary size of keyword identification. The proposed model is validated on the Google Speech Command public dataset, and its performance is compared with other recently proposed deep learning models for KWS. The proposed model achieves an excellent trade-off between recognition accuracy and computational complexity, outperforming various advanced keyword spotting models. Notably, despite a reduction in model parameters, DLiGRU-X maintains an accuracy of 97% without significant decline. This model offers greater flexibility compared to previous models, allowing users to adjust and expand the set of targeted vocabulary according to their needs and deploy the model in resource-constrained environments.
- 29 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 23498-23507
Open AccessDLiGRU-X: Efficient X-Vector-Based Embeddings for Small-Footprint Keyword Spotting System
Deployment of deep learning-based speech processing models for real-world applications on devices with limited processing capacity and memory constraints poses significant challenges. This paper introduces an enhanced deep learning model based on the X-vector architecture, named dilated light-gated recurrent unit in X-vector (DLiGRU-X) to address these challenges specifically for small-footprint keyword spotting (KWS) tasks. The DLiGRU-X model enhances temporal feature extraction with a LiGRU and reduces computational complexity through dilated convolution techniques. The proposed model efficiently learns speech signal characteristics, making it suitable for scenarios with limited hardware resources and can handle an expanded vocabulary size of keyword identification. The proposed model is validated on the Google Speech Command public dataset, and its performance is compared with other recently proposed deep learning models for KWS. The proposed model achieves an excellent trade-off between recognition accuracy and computational complexity, outperforming various advanced keyword spotting models. Notably, despite a reduction in model parameters, DLiGRU-X maintains an accuracy of 97% without significant decline. This model offers greater flexibility compared to previous models, allowing users to adjust and expand the set of targeted vocabulary according to their needs and deploy the model in resource-constrained environments.