Recently, neural networks have proven to be effective in performing speech coding task at low bitrates. However, under-utilization of intra-frame correlations and the error of quantizer specifically degrade the reconstructed audio quality. To improve the coding quality, we present an end-to-end neural speech codec, namely CBRC (Convolutional and Bidirectional Recurrent neural Codec). An interleaved structure using 1D-CNN and Intra-BRNN is designed to exploit the intra-frame correlations more efficiently. Furthermore, Group-wise and Beam-search Residual Vector Quantizer (GB-RVQ) is used to reduce the quantization noise. CBRC encodes audio every 20ms with no additional latency, which is suitable for real-time communication. Experimental results demonstrate the superiority of the proposed codec when comparing CBRC at 3kbps with Opus at 12kbps.

翻译：近年来，神经网络在低比特率语音编码任务中表现出有效性。然而，帧内相关性的欠利用以及量化器的误差会显著降低重构音频质量。为提升编码质量，我们提出一种端到端神经语音编解码器——CBRC（卷积双向递归神经编解码器）。通过设计一维卷积与内部双向循环神经网络（Intra-BRNN）的交错结构，可更高效地挖掘帧内相关性；同时，采用分组波束搜索残差矢量量化器（GB-RVQ）降低量化噪声。CBRC以20毫秒为间隔对音频进行编码，无额外延迟，适用于实时通信。实验结果表明，当3kbps码率的CBRC与12kbps码率的Opus对比时，本编解码器展现了显著优势。