GS-Codec: A Gaussian-Splatting Bottleneck for Neural Audio Coding
Neural audio codecs compress waveforms into compact discrete tokens that underpin speech language models, real-time communication, and large-scale audio storage. Almost every dominant design, including residual vector quantization, finite scalar quantization, and single-codebook variants, follows the VQ-VAE template by partitioning the encoder latent through a learned codebook or a fixed scalar…
We haven't written up this one. arXiv cs.AI has the full story — the link below goes straight to it.
