LightCodec: A High Fidelity Neural Audio Codec with Low Computation Complexity

The audio codec is one of the core modules in audio communication for real-time transmission. With the development of neural networks, end-to-end audio codecs have emerged and demonstrated effects beyond conventional codecs. However, current neural network-based codecs have the weakness of high comp...

Full description

Saved in:
Bibliographic Details
Published in:Proceedings of the ... IEEE International Conference on Acoustics, Speech and Signal Processing (1998) pp. 586 - 590
Main Authors: Xu, Liang, Wang, Jing, Zhang, Jianqian, Xie, Xiang
Format: Conference Proceeding
Language:English
Published: IEEE 14.04.2024
Subjects:
Audio codec
Codecs
Computational modeling
Frequency conversion
Low complexity
Neural networks
Quantization (signal)
Real-time systems
Speech coding
Vector quantization
ISSN:2379-190X
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The audio codec is one of the core modules in audio communication for real-time transmission. With the development of neural networks, end-to-end audio codecs have emerged and demonstrated effects beyond conventional codecs. However, current neural network-based codecs have the weakness of high computational complexity, and the performance of these methods decreases rapidly after decreasing the complexity, which is not conducive to deployment under low computational resources. In this paper, a low-complexity audio codec is proposed. To realize the low complexity of the model with high quality, a structure based on frequency band division is designed, which is implemented using a within bandacross band interaction (WBABI) module to learn the features across and within the subband. Further, we propose a new quantization-compensation module, which reduces the quantization error by 90%. The experimental results show that for audio with a sample rate of 24kHz, the model shows excellent performance at 3~6kbps compared to other codecs, and the complexity is only 0.8 Giga Multiply-Add Operations per Second(GMACs).
ISSN:2379-190X
DOI:10.1109/ICASSP48485.2024.10447532