Vector quantization system and method based on deep neural network

Abstract

The invention provides a depth neural network based vector quantization system and method, comprising a normalization preprocessing module for normalizing original data through normalized data and outputting preprocessed data after normalization; a vector quantization and coding module for receiving the preprocessed data and the codebook and carrying out vector quantization coding to the preprocessed data through the codebook and outputting the coded data; a neural network inverse quantization module for performing the decoding of the inverse quantization to the coded data through a depth neural network and outputting the decoded data; a processing module after inverse normalization for performing an inverse normalization process to the decoded data through the normalized data and outputting the restored original data after the inverse normalization; and a neural network training module for carrying out trainings to the neural network through the pre-processed training data and coded training data after normalization processing and outputting the neural network to the neural network inverse quantization module. The system and the method of the invention can effectively solve the problem that the quantization error is large in high dimension signal vector quantization.

Description

technical field [0001] The present invention relates to the technical field of information and signal processing, such as multimedia codec technology, and in particular to a vector quantization system and method based on a deep neural network. Background technique [0002] Vector quantization is a data compression method widely used in speech and image codec algorithms. This method can effectively use the correlation between the components of the vector to eliminate the redundancy in the data, thereby realizing the compression of multi-dimensional signals. From the perspective of data quantization, vector quantization can be regarded as an extension of scalar quantization in dimension. Scalar quantization uses linear dependence and probability density function to eliminate redundancy, while vector quantization also uses nonlinear dependence and data dimension to eliminate redundancy. [0003] In the traditional vector quantization system, both the encoding end and the deco...

AI Technical Summary

Problems solved by technology

[0004] The technical problem to be solved by the present invention is to provide a vector quantization system and method based on a deep neural network, which can effectively solve the problem of large quantization errors in vector quantization of high-dimensional signals

Images