LDCodec: A high quality neural audio codec with low-complexity decoder
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909852595388416 |
|---|---|
| author | Jiang, Jiawei Xu, Linping Zhang, Dejun Huang, Qingbo Xia, Xianjun Xiao, Yijian |
| author_facet | Jiang, Jiawei Xu, Linping Zhang, Dejun Huang, Qingbo Xia, Xianjun Xiao, Yijian |
| contents | Neural audio coding has been shown to outperform classical audio coding at extremely low bitrates. However, the practical application of neural audio codecs is still limited by their elevated complexity. To address this challenge, we have developed a high-quality neural audio codec with a low-complexity decoder, named LDCodec (Low-complexity Decoder Neural Audio Codec), specifically designed for on-demand streaming media clients, such as smartphones. Specifically, we introduced a novel residual unit combined with Long-term and Short-term Residual Vector Quantization (LSRVQ), subband-fullband frequency discriminators, and perceptual loss functions. This combination results in high-quality audio reconstruction with lower complexity. Both our subjective and objective tests demonstrated that our proposed LDCodec at 6kbps outperforms Opus at 12kbps. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_15364 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LDCodec: A high quality neural audio codec with low-complexity decoder Jiang, Jiawei Xu, Linping Zhang, Dejun Huang, Qingbo Xia, Xianjun Xiao, Yijian Audio and Speech Processing Neural audio coding has been shown to outperform classical audio coding at extremely low bitrates. However, the practical application of neural audio codecs is still limited by their elevated complexity. To address this challenge, we have developed a high-quality neural audio codec with a low-complexity decoder, named LDCodec (Low-complexity Decoder Neural Audio Codec), specifically designed for on-demand streaming media clients, such as smartphones. Specifically, we introduced a novel residual unit combined with Long-term and Short-term Residual Vector Quantization (LSRVQ), subband-fullband frequency discriminators, and perceptual loss functions. This combination results in high-quality audio reconstruction with lower complexity. Both our subjective and objective tests demonstrated that our proposed LDCodec at 6kbps outperforms Opus at 12kbps. |
| title | LDCodec: A high quality neural audio codec with low-complexity decoder |
| topic | Audio and Speech Processing |
| url | https://arxiv.org/abs/2510.15364 |