Method and system for encoding and decoding lattice vector quantization audio

Abstract

The invention provides a method for encoding and decoding lattice vector quantization audio. The method comprises the following steps: dividing a frequency domain coefficient of an audio signal which is subjected to modified discrete cosine transform (MDCT) conversion into a plurality of encoding sub-bands, and quantizing and encoding amplitude enveloping value of each encoding sub-band to acquire encoding bit of amplitude envelope; performing bit distribution on each encoding sub-band, normalizing, quantizing and encoding vectors in low-bit encoding sub-bands and high-bit encoding sub-bands by using a tower lattice vector quantizing method and a spherical lattice vector quantizing method to acquire encoding bit of the frequency domain coefficient respectively; and complexly packaging theencoding bit of the amplitude envelope and the encoding bit of the frequency domain coefficient of each encoding sub-band, and transmitting the package to a decoding end. The method and the system for encoding and decoding the lattice vector quantizing audio can acquire better voice source encoding effect.

Description

Technical field [0001] The invention relates to an audio coding and decoding technology, in particular to a lattice vector quantization audio coding and decoding method and system. Background technique [0002] Audio coding technology is the core of multimedia application technologies such as digital audio broadcasting, Internet music and audio communications. These applications will greatly benefit from the improvement of audio encoder compression performance. Perceptual audio encoder, as a kind of lossy transform domain encoding, is a modern mainstream audio encoder. Existing audio codecs such as MPEG 4AAC use non-uniform scalar quantization to perform transform domain audio codec, which has high computational complexity and low compression capabilities; based on traditional statistical vector quantizers (such as vector quantizers designed with LBG algorithms) Quantizer) has strong compression capabilities, so it has been widely used in the field of audio and video compression...

AI Technical Summary

Problems solved by technology

However, the existing audio codecs based on lattice vector quantization (such as G.719, etc.) use spherical grids in codebook selection, and their codebook truncation methods are only suitable for uniformly distributed and Gaussian distributed signals. source, and the coding effect is not good for the source of the Laplace distribution of speech; meanwhile, the bit step size of the existing lattice vector quantizer (such as G.719) in the coding process is an integer number of bits ( Such as one bit), the step size of the low bit allocation is too long, causing the bit allocation to be too concentrated and cannot use the limited bits more effectively; in addition, the grid codebook of a single bit of the codec takes up too much storage space

Images