Introduction to statistical pattern recognition (2nd ed.)
Introduction to statistical pattern recognition (2nd ed.)
Multiresolution Signal Decomposition: Transforms, Subbands, and Wavelets
Multiresolution Signal Decomposition: Transforms, Subbands, and Wavelets
A novel method to represent speech signals
Signal Processing - Content-based image and video retrieval
Hi-index | 0.00 |
A novel systematic procedure referred to as "SYMPES" to model speech signals is introduced. The structure of SYMPES is based on the creation of the so-called predefined "signature S = {SR(n)} and envelope E = {EK(n)}" sets. These sets are speaker and language independent. Once the speech signals are divided into frames with selected lengths, then each frame sequence Xi(n) is reconstructed by means of the mathematical form Xi(n) = CiEK (n)SR(n). In this representation, Ci is called the gain factor, SR(n) and EK(n) are properly assigned from the predefined signature and envelope sets, respectively. Examples are given to exhibit the implementation of SYMPES. It is shown that for the same compression ratio or better, SYMPES yields considerably better speech quality over the commercially available coders such as G.726 (ADPCM) at 16 kbps and voice excited LPC-10E(FS1015) at 2.4 kbps.