MULTIPATH TREE-STRUCTURED VECTOR
|
Abstract:
Tree-structured vector quantization (TSVQ) is a popular mean of avoiding the exponential complexity of fullsearch vector quantizers. We present two new design algorithms for TSVQ in which more than one path can be chosen at each internal node. The two algorithms dier on the way the paths are chosen. In the rst algorithm the number of paths is xed and the encoding is similar to the M-algorithm for delayed decision coders. In the second algorithm, the paths are chosen adaptively at each node, according to a (1+ ) nearest neighbor rule. We show the performances of the two algorithms on an AR(1) gaussian process, and observe that the adaptive method is the best one. Those methods allow near fullsearch performances at a fraction of the complexity cost.
Citations
| 804 | An algorithm for vector quantizer design – Linde, Buzo, et al. - 1980 |
| 49 | Speech coding based upon vector quantization,”IEEE – Buzo, Gray, et al. - 1980 |
| 12 | Instrumentable tree encoding of information sources – Jelinek, Anderson - 1971 |
| 11 | Variable-rate treestructured vector quantizers – Balakrishnan, Pearlman, et al. - 1995 |
| 2 | Practical multi-resolution source coding: TSVQ revisited – Eros - 1998 |
| 1 | Image sequence coding using adaptive tree-structured vector quantization with multipath searching – F, Wang - 1991 |
