用分阶段训练提升音频压缩质量，低码率下媲美高码率传统方法。
APCodec+: A Spectrum-Coding-Based High-Fidelity and High-Compression-Rate Neural Audio Codec with Staged Training Paradigm
- 分两阶段训练：先联合优化，再单独精修解码器与判别器。
- 在低码率下音质接近更高码率基线模型，实现高保真与高压缩率。
- 适合关注音频编码效率与音质的工程师及研究者。
本文提出一种新型神经音频编解码器APCodec+，为APCodec的改进版本。该方法以音频幅度谱和相位谱为编码对象，采用对抗训练策略。创新性地设计了两阶段联合-独立训练范式：第一阶段联合训练编码器、量化器、解码器与判别器，使用完整的谱损失、量化损失与对抗损失；第二阶段固定编码器与量化器参数，为其生成高质量训练数据，解码器与判别器从头开始单独训练，且不包含量化损失。此设计旨在降低解码器学习难度，进一步提升还原音质。实验结果表明，在低码率下，所提APCodec+性能可媲美更高码率基线编解码器，得益于提出的分阶段训练机制。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。