Background: Enhancement of real-world speech signals is still a challenging task to eliminate noises namely reverberation, background, street, and babble noises. Recently learned methods like dictionary learning have become increasingly popular and showed promising results in speech enhancement. Among many sparse representation algorithms, the K-means Singular Value Decomposition (KSVD) algorithm is best suited for dictionary learning, and the orthogonal matching pursuit (OMP) based algorithm used towards signal recovery is giving the best enhancement results. On the other hand, FPGAs and ASICs are widely used in accelerating applications that require speech enhancement. FPGAs are commonly used in healthcare and consumer applications where speech enhancement also plays a crucial role. Method: In this paper, a modified KSVD algorithm is proposed that can easily be implemented onto hardware platforms like FPGAs and ASICS. Instead of using the double-precision arithmetic for the singular value decomposition part of the KSVD algorithm, we proposed to use CORDIC (Coordinate Rotation Digital Computer) based QR decomposition, and QR-based singular value decomposition in the dictionary learning. Result: The proposed KSVD algorithm is optimal with the usage of the CORDIC algorithm that can reduce by 7-8 times of processing time. Conclusion: The finding indicates that the proposed work is best suited on FPGA or ASIC platforms.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.