MDCTCodec：面向高采样率与低比特率场景的轻量级基于MDCT的神经音频编解码器
MDCTCodec: A Lightweight MDCT-based Neural Audio Codec towards High Sampling Rate and Low Bitrate Scenarios
AI总结：
该研究提出基于MDCT的轻量级神经音频编解码器MDCTCodec，搭配新型多分辨率MDCT判别器做对抗训练，在高采样率低比特率场景下相较基线实现了音质、效率与模型尺寸的综合提升，在VCTK数据集48kHz/6kbps条件下ViSQOL达4.18。
摘要：
本文提出了MDCTCodec，这是一种基于改进离散余弦变换（MDCT）的高效轻量级端到端神经音频编解码器。编码器以音频的MDCT频谱为输入，将其编码为连续潜码，再通过残差矢量量化器（RVQ）对潜码进行离散化处理。随后，解码器从量化后的潜码中解码出MDCT频谱，并通过逆MDCT重建音频。在训练阶段，采用一种新型的多分辨率基于MDCT的判别器（MR-MDCTD）来判别自然MDCT频谱与解码后的MDCT频谱，以此实现对抗训练。实验结果证实，在高采样率、低比特率场景下，与基线编解码器相比，MDCTCodec具备更高的解码音频质量、更优的训练与生成效率，且模型尺寸更紧凑。具体而言，在公开VCTK语料库上，采样率为48 kHz、比特率为6 kbps的条件下，MDCTCodec取得了4.18的ViSQOL分数。
英文摘要：
In this paper, we propose MDCTCodec, an efficient lightweight end-to-end neural audio codec based on the modified discrete cosine transform (MDCT). The encoder takes the MDCT spectrum of audio as input, encoding it into a continuous latent code which is then discretized by a residual vector quantizer (RVQ). Subsequently, the decoder decodes the MDCT spectrum from the quantized latent code and reconstructs audio via inverse MDCT. During the training phase, a novel multi-resolution MDCT-based discriminator (MR-MDCTD) is adopted to discriminate the natural or decoded MDCT spectrum for adversarial training. Experimental results confirm that, in scenarios with high sampling rates and low bitrates, the MDCTCodec exhibited high decoded audio quality, improved training and generation efficiency, and compact model size compared to baseline codecs. Specifically, the MDCTCodec achieved a ViSQOL score of 4.18 at a sampling rate of 48 kHz and a bitrate of 6 kbps on the public VCTK corpus.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
