Metraipolis › archive › dc_55cb2d4e833f

AKDQ: Adaptive Key-Delta Quantization for Low-Bitrate RVQ-based Neural Speech Codecs — arXiv:2610.39885

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.39885
License (as archived): CC0-1.0
Archived: 2026-11-01T03:01:10.708Z
SHA-256 of the archived text: 4f6571de736880e79188ea9afb2b158a39318f625679a3d492e90d3032bd7cd7
Stable URL of this page: https://metraipolis.com/documento/dc_55cb2d4e833f

How to cite

AKDQ: Adaptive Key-Delta Quantization for Low-Bitrate RVQ-based Neural Speech Codecs — arXiv:2610.39885 — arXiv (en), https://arxiv.org/abs/2610.39885 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_55cb2d4e833f (Metraipolis archive dc_55cb2d4e833f, sha256 4f6571de736880e79188ea9afb2b158a39318f625679a3d492e90d3032bd7cd7)

BibTeX

@misc{dc55cb2d4e833f,
  title = {AKDQ: Adaptive Key-Delta Quantization for Low-Bitrate RVQ-based Neural Speech Codecs — arXiv:2610.39885},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.39885},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_55cb2d4e833f; sha256 4f6571de736880e79188ea9afb2b158a39318f625679a3d492e90d3032bd7cd7},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.39885. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Low-bitrate speech coding is essential for bandwidth-constrained channels and on-device applications, but conventional residual vector quantization (RVQ)-based codecs employ a fixed number of codebooks per frame regardless of content. Adjacent speech frames often exhibit strong similarity, and quantizing them independently with the same scheme results in redundant encoding, thereby wasting bitrate. Therefore, we propose Adaptive Key-Delta Quantization (AKDQ), which replaces the fixed per-frame VQ allocation of RVQ with an adaptive frame-wise key-or-delta policy. AKDQ is a plug-in strategy that requires no modification to the codec's encoder-decoder backbone. Specifically, in AKDQ, each frame is classified as either a key-frame (K-frame) quantized with all VQs, or a delta-frame (D-frame) quantized with only a few VQs on a delta correction from the previous reconstruction, thereby reducing bitrate. The K/D decision is made by a budget-aware causal scheduler through a bit-bank mechanism, keeping the system streamable with no additional lookahead. Experiments on both causal and non-causal codec families demonstrate that AKDQ effectively reduces bitrate redundancy. For instance, on DAC, using AKDQ at 1.5 kbps achieves reconstruction quality comparable to using the baseline RVQ at 2.0 kbps, saving 25% of the bitrate.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv eess.AS, nuovi lavori del giorno).
Categorie arXiv: Audio and Speech Processing (eess.AS).
Pagina del lavoro: https://arxiv.org/abs/2610.39885 — 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 2026-11-01T02:26:00.573Z dalla pagina https://arxiv.org/list/eess.AS/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).