APCodec+: A Spectrum-Coding-Based High-Fidelity and High-Compression-Rate Neural Audio Codec with Staged Training Paradigm
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917823418204160 |
|---|---|
| author | Du, Hui-Peng Ai, Yang Zheng, Rui-Chen Ling, Zhen-Hua |
| author_facet | Du, Hui-Peng Ai, Yang Zheng, Rui-Chen Ling, Zhen-Hua |
| contents | This paper proposes a novel neural audio codec, named APCodec+, which is an improved version of APCodec. The APCodec+ takes the audio amplitude and phase spectra as the coding object, and employs an adversarial training strategy. Innovatively, we propose a two-stage joint-individual training paradigm for APCodec+. In the joint training stage, the encoder, quantizer, decoder and discriminator are jointly trained with complete spectral loss, quantization loss, and adversarial loss. In the individual training stage, the encoder and quantizer fix their parameters and provide high-quality training data for the decoder and discriminator. The decoder and discriminator are individually trained from scratch without the quantization loss. The purpose of introducing individual training is to reduce the learning difficulty of the decoder, thereby further improving the fidelity of the decoded audio. Experimental results confirm that our proposed APCodec+ at low bitrates achieves comparable performance with baseline codecs at higher bitrates, thanks to the proposed staged training paradigm. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_22807 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | APCodec+: A Spectrum-Coding-Based High-Fidelity and High-Compression-Rate Neural Audio Codec with Staged Training Paradigm Du, Hui-Peng Ai, Yang Zheng, Rui-Chen Ling, Zhen-Hua Audio and Speech Processing Sound This paper proposes a novel neural audio codec, named APCodec+, which is an improved version of APCodec. The APCodec+ takes the audio amplitude and phase spectra as the coding object, and employs an adversarial training strategy. Innovatively, we propose a two-stage joint-individual training paradigm for APCodec+. In the joint training stage, the encoder, quantizer, decoder and discriminator are jointly trained with complete spectral loss, quantization loss, and adversarial loss. In the individual training stage, the encoder and quantizer fix their parameters and provide high-quality training data for the decoder and discriminator. The decoder and discriminator are individually trained from scratch without the quantization loss. The purpose of introducing individual training is to reduce the learning difficulty of the decoder, thereby further improving the fidelity of the decoded audio. Experimental results confirm that our proposed APCodec+ at low bitrates achieves comparable performance with baseline codecs at higher bitrates, thanks to the proposed staged training paradigm. |
| title | APCodec+: A Spectrum-Coding-Based High-Fidelity and High-Compression-Rate Neural Audio Codec with Staged Training Paradigm |
| topic | Audio and Speech Processing Sound |
| url | https://arxiv.org/abs/2410.22807 |