Metraipolis › archive › dc_c6bb173f2092
GIVE-KWS: Gated Injection of Visual Evidence for Noise-Robust Query-by-Example Keyword Spotting — arXiv:2610.07046
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.07046
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T11:23:34.565Z
- SHA-256 of the archived text
98dc68c8f395d5dc31229033d15df70cf3ad096fb91d4c797dfca5c266ad927f- Stable URL of this page
https://metraipolis.com/documento/dc_c6bb173f2092
How to cite
GIVE-KWS: Gated Injection of Visual Evidence for Noise-Robust Query-by-Example Keyword Spotting — arXiv:2610.07046 — arXiv (en), https://arxiv.org/abs/2610.07046 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c6bb173f2092 (Metraipolis archive dc_c6bb173f2092, sha256 98dc68c8f395d5dc31229033d15df70cf3ad096fb91d4c797dfca5c266ad927f)
BibTeX
@misc{dcc6bb173f2092,
title = {GIVE-KWS: Gated Injection of Visual Evidence for Noise-Robust Query-by-Example Keyword Spotting — arXiv:2610.07046},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.07046},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c6bb173f2092; sha256 98dc68c8f395d5dc31229033d15df70cf3ad096fb91d4c797dfca5c266ad927f},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.07046. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Visual speech promises noise-robust keyword spotting, yet a visual stream is not necessarily used. On a tri-modal query-by-example keyword spotting (QbyE-KWS) benchmark, we find that a system with a task-trained visual encoder comes within 2 percentage points of a text-and-audio system in equal error rate (EER) at -10 dB, and link this gap to the encoder's lack of phonemic information. We present GIVE-KWS, whose fusion stage, GIVE (Gated Injection of Visual Evidence), conditions query audio on lip motion through gated cross-attention. We show that visual robustness depends on two interacting conditions: a phoneme-bearing visual representation, and fusion that injects visual evidence rather than rescaling audio features. Under a phoneme-bearing encoder, injection yields an effective SNR gain of 4.0-9.3 dB over masking at -10 dB, whereas under a phoneme-poor one it nearly vanishes. Relative to the benchmark system, GIVE-KWS reduces unseen-keyword EER by 72.9% at -10 dB and 62.8% on average. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno). Categorie arXiv: Audio and Speech Processing (eess.AS) ; Computation and Language (cs.CL); Multimedia (cs.MM); Sound (cs.SD). Pagina del lavoro: https://arxiv.org/abs/2610.07046 — 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 2026-10-07T11:15:39.473Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).