Print ISSN: 1681-6900

Online ISSN: 2412-0758

Keywords : Wavelet Transform


Speaker Identification Using Wavelet Transform and Artificial Neural Network

Manal Hadi Jaber

Engineering and Technology Journal, 2011, Volume 29, Issue 15, Pages 3242-3255

This paper presents an effective method for improving the performance of
speaker identification system based on schemes combines the multi
resolution properly of the wavelet transform and radial basis function neural net works (RBFNN), evaluated its performance by comparing the results with other method. The input speech signal is decomposed into L sub band. To capture the characteristic of the vocal tract, the liner prediction code of each (including the linear predictive code (LPC) for full band) are calculated. The radial basis function neural network (RBFNN) approach is used for matching purpose. Experimental results shows that the speaker identification using the methods
achieve (combines the wavelet and RBFNN) give (100%) identification rate
and higher identification rate compared with multi band liner predictive
code, in this paper used Matlab program to prove the results.

Information Hiding Based on Discrete Time Wavelet Transform and Huffman Coding

Ammar Abdul-Amer Rashed

Engineering and Technology Journal, 2011, Volume 29, Issue 2, Pages 295-304

The approach of This paper presentation a companied technique for hiding
secret messages (text) based on wavelet transform applying in cover image (a gray
level image 8bit) then Huffman encoding is also executed on the secret
messages,to increase the robustness of hiding system by inserting the embedded
secret messages in the low frequency components of the cover image after
applying wavelet transform followed by a sorting process and the coefficients of
secret messages after applying Huffman encoding and using binary to multilevel
to reading the string of message reducing by multiplying in attenuation factor
before adding them with those of the cover image.
The experimental results show that the algorithm has a high capacity and a good
invisibility, Moreover PSNR of stego image shows the better results the PSNR
above 40 dB, the proposal system was activated according to attacker noise is
addition and JPEG compression application are used with out detection the secret
message.

Content-Based Authentication Using Digital Speech Data

Hana; a M. Salman

Engineering and Technology Journal, 2008, Volume 26, Issue 2, Pages 228-239

A watermarking technique for speech content and speaker authentication
scheme, which is based on using abstracts of speech features relevant to semantic
meaning and combined with an ID for the speaker is proposed in this paper. The ID
which, represents the watermark for the speaker, is embedded using spread spectrum
technique. While the extracted abstracts of speech features are used to represents the
watermark for the speech, is embedded in the original speech file using secret key.
The abstracts speech feature is implemented using B-spline curve interpolation. The
paper provides a background knowledge for the concept of speaker watermarking
and content-fragile watermarking based on digital speech data. Then, the suggested
feature based authentication scheme is develop and the results from the evaluation
are presented. It shows that the suggested scheme is successful for combining
speech and speaker watermark authentication.

A Content-Based Authentication Using Digital Speech Data

Hana; a M. Salman

Engineering and Technology Journal, 2007, Volume 25, Issue 10, Pages 1162-1170

A watermarking technique for speech content and speaker authentication
scheme, which is based on using abstracts of speech features relevant to
semantic meaning and combined with an ID for the speaker is proposed in
this paper. The ID which represents the watermark for the speaker, is
embedded using spread spectrum technique while the extracted abstracts of
speech features are used to represent the watermark for the speech, embedded
in the original speech file using secret key. The abstracts speech feature is
implemented using B-spline curve interpolation. The paper provides a
background knowledge for the concept of speaker watermarking and contentfragile
watermarking based on digital speech data. Then, the suggested
feature based authentication scheme is developed and the results from the
evaluation are presented. Show that the suggested scheme is successful in
combining speech and speaker watermark authentication.