Title :
Address-vector quantisation applied to speech coding
Author :
Srinonchat, J. ; Danaher, S. ; Murray, A.
Author_Institution :
Sch. of Eng. & Technol., Northumbria Univ., Newcastle, UK
Abstract :
The use of address vector quantisation (VQ) in the compression of linear predictive coded (LPC) and line spectral pairs (LSP) speech parameters in a speaker dependent system are examined. Four speakers are investigated; two male and two female. The speech waveform is coded to LPC and LSP parameters using LPC techniques and is vector quantised using an unsupervised neural network, a Kohonen self organising feature map (KSOFM), to create a codebook of 128 entries. Address VQ is applied to the codebook and the data examined for recurring sequences to exploit redundancy. Preliminary results indicate that approximately 46% additional compression is achievable using this method. As Address VQ is a loss-less compression scheme, this reduction is achieved without any further reduction in speech quality.
Keywords :
linear predictive coding; self-organising feature maps; speech coding; vector quantisation; Kohonen self organising feature map; address vector quantisation; line spectral pairs speech parameter; linear predictive coded speech parameter; loss-less compression scheme; neural network; speaker dependent system; speech coding; Bit rate; Clustering algorithms; Image coding; Lakes; Linear predictive coding; Neural networks; Speech analysis; Speech coding; Tail; Vector quantization;
Conference_Titel :
Signal Processing and Information Technology, 2003. ISSPIT 2003. Proceedings of the 3rd IEEE International Symposium on
Print_ISBN :
0-7803-8292-7
DOI :
10.1109/ISSPIT.2003.1341228
