低复杂度解码器实现6kbps高音质音频，超越12kbps的Opus。
LDCodec: A high quality neural audio codec with low-complexity decoder
- 用新型残差单元与长短时向量量化，降低解码复杂度。
- 6kbps下主观和客观评测均优于12kbps的Opus。
- 适合手机等终端设备的按需流媒体场景使用。
神经音频编码在极低比特率下已超越传统编码方法，但其应用受限于较高计算复杂度。为解决此问题，我们提出一种高保真、低复杂度解码器的神经音频编码器LDCodec（Low-complexity Decoder Neural Audio Codec），专为智能手机等按需流媒体客户端设计。通过引入新型残差单元与长短时残差向量量化（LSRVQ）、子带-全频段频率判别器及感知损失函数，实现高质量音频重建且计算开销更低。主观与客观测试表明，LDCodec在6kbps下的表现优于Opus在12kbps的表现。
原文摘要 · Abstract (English)
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.
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。