No abstract

In speech coding area, several vector quantization (VQ) methods for the LPC (linear predictive coding) parameters have been developed. Because LPC parameters are too dynamic to quantize directly, the LSFs (line spectrum frequencies) are used instead. In this study, we propose the linked split-vector quantizer (LSVQ) where the lower and the upper codebook are selected according to the preselected middle codevector. Using the ordering property of LSFs, LSVQ links three codebooks for the efficient use of the codebook space. Compared with the conventional split-vector quantizer (SVQ), LSVQ increases the usage of codebook space by 10.84%, and shows lower spectral distortion at 23 bitdframe than the SVQ at 24 bitdframe.