Metraipolis › archive › dc_ffe7be9d1ef4

GS-Codec: A Gaussian-Splatting Bottleneck for Neural Audio Coding — arXiv:2610.04651

Source
arXiv
Original
https://arxiv.org/abs/2610.04651
License (as archived)
CC0-1.0
Archived
2026-10-06T05:26:21.767Z
SHA-256 of the archived text
95cd655b022e43a69cb4dd1fb5df3d9e0fdc1905028aa64e29e50378ff9ed4ca
Stable URL of this page
https://metraipolis.com/documento/dc_ffe7be9d1ef4

How to cite

GS-Codec: A Gaussian-Splatting Bottleneck for Neural Audio Coding — arXiv:2610.04651 — arXiv, https://arxiv.org/abs/2610.04651 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ffe7be9d1ef4 (Metraipolis archive dc_ffe7be9d1ef4, sha256 95cd655b022e43a69cb4dd1fb5df3d9e0fdc1905028aa64e29e50378ff9ed4ca)
BibTeX
@misc{dcffe7be9d1ef4,
  title = {GS-Codec: A Gaussian-Splatting Bottleneck for Neural Audio Coding — arXiv:2610.04651},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.04651},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ffe7be9d1ef4; sha256 95cd655b022e43a69cb4dd1fb5df3d9e0fdc1905028aa64e29e50378ff9ed4ca},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.04651. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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 grid. We ask whether this partition is necessary. We introduce GS-Codec, a neural speech codec whose bottleneck is a parametric signal decomposition rather than a quantizer. We adapt Gaussian splatting from 3D scene reconstruction to one-dimensional latents. An inner optimization loop fits each encoder segment as a weighted sum of 1D Gaussian primitives. The decoder then reconstructs the waveform from the rendered sum. To avoid the cost of this iterative inner loop at inference time, we additionally train a lightweight GS Predictor Net that regresses the primitive parameters in a single forward pass. The encoder and decoder are trained end-to-end through the inner loop, with no quantizer anywhere in the training pipeline: the bottleneck is the decomposition itself, and scalar quantization is applied only post-training to the fitted parameters. Rather than relying on discrete codebook stages for bitrate control, our representation exposes a fine-grained rate-quality tradeoff: a single trained checkpoint supports post-training bitrate control by varying the number of primitives and the per-parameter bit depth, with no retraining required. GS-Codec matches or exceeds well-established open-source codecs such as EnCodec and DAC on speaker similarity (SIM), intelligibility (STOI), and perceptual quality (UTMOS) at comparable bitrates, while achieving comparable semantic performance (WER). Code and audio samples are available at this https URL

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Sound (cs.SD) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Audio and Speech Processing (eess.AS); Signal Processing (eess.SP).
Pagina del lavoro: https://arxiv.org/abs/2610.04651 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-06T05:24:05.896Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).