Metraipolis › archive › dc_dec3096b59cb

Normalise or condition? Noise-floor front-ends for on-board keyword spotting under UAV rotor ego-noise — arXiv:2609.31699

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.31699
License (as archived): CC0-1.0
Archived: 2026-10-07T23:54:59.662Z
SHA-256 of the archived text: a86fd2affbb8d7e1133966b6004f070b62e4538890d899572c114d3cbe49229a
Stable URL of this page: https://metraipolis.com/documento/dc_dec3096b59cb

How to cite

Normalise or condition? Noise-floor front-ends for on-board keyword spotting under UAV rotor ego-noise — arXiv:2609.31699 — arXiv (en), https://arxiv.org/abs/2609.31699 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_dec3096b59cb (Metraipolis archive dc_dec3096b59cb, sha256 a86fd2affbb8d7e1133966b6004f070b62e4538890d899572c114d3cbe49229a)

BibTeX

@misc{dcdec3096b59cb,
  title = {Normalise or condition? Noise-floor front-ends for on-board keyword spotting under UAV rotor ego-noise — arXiv:2609.31699},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.31699},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_dec3096b59cb; sha256 a86fd2affbb8d7e1133966b6004f070b62e4538890d899572c114d3cbe49229a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.31699. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

A microphone on the airframe of a small multi-rotor UAV is dominated by rotor ego-noise, so spoken flight commands arrive at negative signal-to-noise ratio (SNR). We study small-footprint keyword spotting (KWS) for a ten-word command vocabulary under real ego-noise, training on one quadrotor and testing on another. Besides per-clip accuracy we measure the streaming false-alarm rate on 4.4 h of continuous rotor noise. We compare classical noise-robust front-ends (CMN, PCEN, spectral subtraction), test-time adaptation, and two front-ends that track the per-band ego-noise floor over the two seconds preceding the decision window and either subtract it (normalisation) or feed it to the network as a second input channel (conditioning). Per clip, all front-ends look alike: +2-3 points on average, up to +14 at -15 dB. On continuous rotor noise they differ sharply. Normalising front-ends fire about ten times more often than plain log-mel at the same threshold and end up below it at a budget of one false alarm per hour (-9 points at 0 dB). Conditioning keeps the baseline's false-alarm rate and turns its gain into detections (+8 points at -10 dB over three seeds); on top of PCEN it gives the best per-clip accuracy and false-alarm rate, and a level-anchored variant is also invariant to the microphone gain. Real drone+interferer recordings expose the remaining failure mode, environmental sounds and bystander speech, which training negatives halve. A single script reproduces all on-device numbers on the NVIDIA Jetson Orin NX flight computer, where the complete pipeline costs 3 ms per 100 ms hop on the CPU.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-29 in cs.CV).
Categorie arXiv: Sound (cs.SD) ; Computer Vision and Pattern Recognition (cs.CV); Audio and Speech Processing (eess.AS).
Pagina del lavoro: https://arxiv.org/abs/2609.31699 — 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 2026-10-07T23:29:27.642Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).