Cluster-based voice activity detection for mobile devices
A voice activity detection in mobile environments is not performed well due to arbitrary noises. In this paper, a robust voice activity detection framework for mobile devices is proposed. The unsupervised clustering and discriminative weight training of each cluster is employed to model various characteristics of arbitrary noises.
- Issue Date
- 2016-01
- Language
- English
- Citation
IEEE International Conference on Consumer Electronics, ICCE 2016, pp.149 - 150
- Appears in Collection
- EE-Conference Papers(학술회의논문)
- Files in This Item
- There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.