Low Complexity, Low Delay and Scalable Audio Coding Scheme Based on a Novel Statistical Perceptual Quantization Procedure

In this paper we present Fast Perceptual Quantization (FPQ), a novel procedure to quantize and code audio signals. It employs the same psychoacoustics principles used in the popular MPEG/Audio coders, but substantially simplifies the complexity and computational needs of the encoding process. FPQ is based on defining a hierarchy of privileged quantization values so that the masking threshold calculated through a psychoacoustic model is leveraged to quantize the real values to the privileged ones when possible. The computational cost of this process is very low compared to MP3’s or AAC’s quantization/coding loops. Experimental results show that it is possible to achieve nearly transparent coding using as few as approximately 100 quantization values. This leads to very efficient bit compaction using Huffman or arithmetic coding so that nearly state-of-the-art performance can be achieved in terms of quality/bit-rate trade-off. Since quantization and codification (bit compaction) procedures are completely independent here, efficient scalable decoding can be achieved either by parsing and entropy re-encoding the original quantized values or by coding the bit-planes independently and sorting them in order of perceptual significance. Very low delay performance is also possible to achieve, which makes the proposed coding scheme suitable for real-time applications.