Subband-based blind signal separationfor noisy speech recognition
- 11 November 1999
- journal article
- Published by Institution of Engineering and Technology (IET) in Electronics Letters
- Vol. 35 (23) , 2011-2012
- https://doi.org/10.1049/el:19991358
Abstract
A method for directly extracting clean speech features from noisy speech is proposed. This process is based on independent component analysis (ICA) and a new feature analysis technique for reducing the computational complexity of the frequency-domain ICA. For noisy speech signals recorded in real environments, this method yielded a considerable performance improvement.Keywords
This publication has 2 references indexed in Scilit:
- Blind source separation of real world signalsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- An Information-Maximization Approach to Blind Separation and Blind DeconvolutionNeural Computation, 1995