Metraipolis › archive › dc_c81ac8ee2e4a
Low-Latency State Space Voice Activity Detection with Robust Onset Time Evaluation — arXiv:2609.11110
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.11110
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T07:17:39.243Z
- SHA-256 of the archived text
628eaf6febf33cc93f8ec44c96db9204ab025c7282704ed9f8b384e656ceafc5- Stable URL of this page
https://metraipolis.com/documento/dc_c81ac8ee2e4a
How to cite
Low-Latency State Space Voice Activity Detection with Robust Onset Time Evaluation — arXiv:2609.11110 — arXiv (en), https://arxiv.org/abs/2609.11110 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c81ac8ee2e4a (Metraipolis archive dc_c81ac8ee2e4a, sha256 628eaf6febf33cc93f8ec44c96db9204ab025c7282704ed9f8b384e656ceafc5)
BibTeX
@misc{dcc81ac8ee2e4a,
title = {Low-Latency State Space Voice Activity Detection with Robust Onset Time Evaluation — arXiv:2609.11110},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.11110},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c81ac8ee2e4a; sha256 628eaf6febf33cc93f8ec44c96db9204ab025c7282704ed9f8b384e656ceafc5},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.11110. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Voice Activity Detection (VAD) systems are commonly evaluated using metrics such as the area under the receiver operating characteristic curve (AUROC), but these metrics do not account for temporal responsiveness. For low-latency applications, however, accurately measuring speech onset delay is essential. This is particularly challenging because onset latency evaluation is affected by noise and systematic misalignment in annotation timestamps. In this work, we introduce a probabilistic framework for evaluating VAD onset time under noisy temporal labels. We model annotated onset times as noisy observations of latent acoustic onsets and estimate the resulting discrepancy distribution from data. We show that this approach provides a more stable and robust estimate of algorithmic latency. In addition, we introduce S4VAD, the first state-space-model-based (SSM-based) VAD architecture. S4VAD supports efficient streaming inference while directly controlling the decay of past acoustic evidence, enabling fast and responsive speech-onset detection. We evaluate VAD onset latency across several low-latency architectures, including CNN, Transformer, and RNN models. Our proposed VAD achieves the lowest latency while maintaining a competitive AUROC. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-11 in eess.AS). Categorie arXiv: Audio and Speech Processing (eess.AS). Pagina del lavoro: https://arxiv.org/abs/2609.11110 — 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 2026-10-16T06:59:25.290Z dalla pagina https://arxiv.org/catchup/eess.AS/2026-09-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).