Metraipolis › archive › dc_6c04a57cc65e
AS$^2$D: Accelerating On-Demand Audio Understanding on Mobile Devices — arXiv:2609.37617
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.37617
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T16:27:28.810Z
- SHA-256 of the archived text
95a46a9217657a85c72dc41d66f99ceb8e5ef7c2e1f47a3ba24b3a75fe48cb3f- Stable URL of this page
https://metraipolis.com/documento/dc_6c04a57cc65e
How to cite
AS$^2$D: Accelerating On-Demand Audio Understanding on Mobile Devices — arXiv:2609.37617 — arXiv (en), https://arxiv.org/abs/2609.37617 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6c04a57cc65e (Metraipolis archive dc_6c04a57cc65e, sha256 95a46a9217657a85c72dc41d66f99ceb8e5ef7c2e1f47a3ba24b3a75fe48cb3f)
BibTeX
@misc{dc6c04a57cc65e,
title = {AS$^2$D: Accelerating On-Demand Audio Understanding on Mobile Devices — arXiv:2609.37617},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.37617},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6c04a57cc65e; sha256 95a46a9217657a85c72dc41d66f99ceb8e5ef7c2e1f47a3ba24b3a75fe48cb3f},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.37617. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Speculative decoding accelerates autoregressive generation by using a smaller drafter to propose tokens for batched verification by a larger target. However, conventional speculative decoding couples drafting to the target's evolving verified prefix, serializing drafting and verification. We ask whether this dependency is necessary for source-conditioned generation. Our key observation is that, for audio language models, the input audio and user request can provide useful speculative candidates without following the target's evolving text prefix. We propose AS$^2$D (Audio Speculative Speculative Decoding), which enables target-decoupled drafting: an audio-conditioned drafter follows its own generation history while the target independently verifies and corrects ready candidates. Without usable candidates, the target advances alone. Thus, target feedback determines which candidates are committed but no longer determines when the drafter can make progress, enabling drafting and verification to proceed concurrently while retaining target-side verification and correction. We implement AS$^2$D in MNN for Android and evaluate two target models across four phones, seven datasets, and three tasks covering 12.2 hours of audio. Across four phones, AS$^2$D improves pooled ASR throughput by 42-76% over target-only decoding, while only 5.7% of evaluation windows are slower than target-only, compared with 58.1-63.0% for speculative baselines. For ASR, AS$^2$D reaches 97.33-98.20% of a hindsight per-window oracle's pooled throughput over the evaluated drafter/budget catalog. Native on-demand execution with a 7B target achieves up to 78% higher throughput than target-only. These results show that source-conditioned audio generation can relax the conventional dependence of speculative drafting on the target's evolving output prefix, exposing substantial parallelism for efficient inference. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-30 in cs.AI). Categorie arXiv: Sound (cs.SD) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.37617 — 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 2026-10-07T15:54:54.002Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).