5th European Conference on Speech Communication and Technology

Rhodes, Greece
September 22-25, 1997

Spectral Sensitivity of LSP Parameters and Their Transformed Coefficients

Hai Le Vu, Laszlo Lois

Department of Telecommunications, Technical University of Budapest, Hungary

In this paper, the optimal transformation and quantization of Line Spectrum Pair (LSP) are accomplished. Based upon the interframe and intraframe correlation properties of the LSPs, the Karhunen-Loeve (KL) transformation is adopted by Principal Component Analysis (PCA) neural network. The spectral sensitivity of the LSP and transformed coefficients are investigated in order to develop better scalar and vector quantizers for these coefficients. Using PCA network with spectral sensitivity guided quantizers we show that this new approach leads to as good as or better distortion compared to other methods for speech coding.

Full Paper

Bibliographic reference.  Vu, Hai Le / Lois, Laszlo (1997): "Spectral sensitivity of LSP parameters and their transformed coefficients", In EUROSPEECH-1997, 1251-1254.