Combined Speaker Recognition and Compression for Secured Speech Transmission
No Thumbnail Available
Date
2014
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
The continued advancement and growth in the network processing ability have
improved the competence and scope of speech communication in the network.
Therefore the secure speech communication and security of communication
information are required now a days. To provide more security for the speech
signal, the Multiple Huffman Table (MHT) is enhanced in this paper, by
incorporating an optimization procedure as a preprocessing step before
compression. So before performing compression the MHT splits the speech
signal into Most Significant Signal (MSS) and Least Significant Signal (LSS).
MSS is considered to be the significant signal, so the MHT considers only the
MSS for compression. From the compressed output, the coefficients are
selected and protected using cryptographic cipher Advanced Encryption
Standard (AES), because it will be difficult for attackers to recover any
information from these coefficients. Finally the results were evaluated using
Compression ratio (CR), Peak Signal-to-Noise Ratio (PSNR) and Normalized
Root-Mean Square Error (NRMSE). From the results it can be seen that the
Enhanced MHT with Encryption method provides better result.