Data-driven subvector clustering using the Cross-Entropy method

Automatic Speech Recognition(ASR) systems are limited in the computational power and memory resources, especially in low-memory/low-power environments such as personal digital assistants. The parameter quantization is the one of the ways to achieve these conditions. In this work, we compare various subvector clustering procedures for the parameter quantization in the ASR system and propose a data-driven subvector clustering technique based on the entropy minimization. The Cross-Entropy(CE) method is a good choice for the combinatorial optimization problems. We compare the ASR performance on Resource Management(RM) speech recognition task and show that the proposed technique produces better performance than previous heuristic techniques.