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

Yida Lin; Bing Xue; Mengjie Zhang; Sam Schofield; Richard Green

cs.SDSep 19, 2026

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

Authors: Yida Lin, Bing Xue, Mengjie Zhang, Sam Schofield, Richard Green

Organizations: Victoria University of Wellington Wellington, New Zealand · University of Canterbury Christchurch, New Zealand

Abstract

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.

Figures & tables

Panel of Figure 1 — Figure 1: On-board pipeline. Every 100 ms the last second of log-mel frames is combined with the noise-floor profile $N_{f}$ tracked over the preceding two seconds (blue blocks are the proposed front-end) and classified; smoothed posteriors drive the flight controller over MAVLink.

Front-end	Train	$-15$	$-10$	$-5$	0	5	10	20	clean	mean	FAR
log-mel	–	15.8	23.3	38.9	61.2	73.2	80.0	85.6	98.0	54.0	100.0
log-mel	G	29.9	53.3	71.6	82.6	87.2	89.8	91.4	96.0	72.3	43.1
NFN	G	44.5	65.7	78.3	85.2	88.2	89.6	90.7	96.6	77.5	53.8
NPC	G	41.8	64.2	78.8	86.8	90.3	91.9	93.1	96.3	78.1	30.3
log-mel	E	42.8	69.9	83.5	89.6	92.8	94.6	95.7	96.7	81.2 $\pm$ 0.2	3.6 $\pm$ 2.1
CMN	E	55.3	73.2	84.0	89.6	92.6	94.2	95.3	97.0	83.5	7.3

Table 1: BC-ResNet-8 on the 12-class UAV command task, test words mixed with unseen-drone ego-noise: accuracy (%) per SNR, mean over the seven noisy SNRs, and false-alarm rate FAR (%) on noise-only input. Train noise: E = drone2 ego-noise, G = GSC noise, – = clean;

\pm

= std over three seeds; bold = best in the E block.

Figure 2: Streaming operation (BC-ResNet-8, deployed decision logic): hit rate of commands embedded every 3 s in unseen-drone rotor noise vs. false alarms per hour on 4.4 h of speech-free rotor noise; one marker per threshold $\tau\in[0.5,0.95]$ (“0”: none in 4.4 h), curves for seed 0, error bars: std over three seeds at 1 FA/h. Open markers: normalising.

Figure 3: Stress tests (BC-ResNet-8 unless noted). (a) Accuracy at 0 dB SNR with the test input scaled by $-20$ to $+20$ dB. (b) Accuracy lost when the floor context comes from the other throttle level of the same drone (mean over both directions).

	acc.	hit ${}_{0\,\mathrm{dB}}$	FA/h @0.7			unk.
Front-end	mean	1 FA/h	rotor	non-sp.	speech	/100
log-mel	81.3	82.8	1.1	27	143	3.8
log-mel + neg.	81.6	88.7	0.0	15	66	6.2
NFN	83.0	75.4	9.8	40	124	5.2
NFN + neg.	82.8	60.7	12.5	24	93	6.2
NPC-a	84.0	86.1	0.9	42	132	4.5

Table 2: Beyond rotor noise (BC-ResNet-8 unless noted, unseen drone,

\tau{=}0.7

): per-clip mean accuracy; streaming hit rate at 0 dB under 1 FA/h; false alarms per hour on rotor noise, on real drone+non-speech-interferer and drone+bystander-speech recordings; firings per 100 non-command words. “+ neg.”: ESC-50 events and overlapping non-command words as negatives.

Stage / model	Params	PC	Jetson	Jetson
		CPU	CPU	TensorRT
Front-end (log-mel $+$ $N_{f}$ )	–	0.10	0.57	n/a
BC-ResNet-3 + NPC-a	57 k	1.07	2.64	1.32
BC-ResNet-8 + NPC-a	349 k	2.09	8.01	1.45
BC-ResNet-8 + PCEN+NPC-a	349 k	2.02	8.10	1.44
KWT-1 + NFN	558 k	1.56	6.61	0.75

Table 3: Per-hop (100 ms) processing time in ms, batch 1, median over 300–500 runs. PC: Intel i5-14600K, ONNX Runtime CPU, 2 threads. Jetson: Orin NX 16 GB, JetPack 6.2.1, MAXN; ONNX Runtime 1.24 CPU (2 threads) or TensorRT execution provider (FP16). The front-end always runs in NumPy on the CPU.

Keyword Spotting

Keyword spotting detects specified words or wake phrases in continuous audio, often on-device under tight latency, power, and false-alarm limits.

See all 24 papers

Personalized Keyword Spotting for User-Defined Keywords Leveraging Text-Independent Speaker Verification
Jun 18, 2026Ming-Hsiang Hu, Kuan-Tang Huang, Chien-Chun Wang +2Zero-Shot Learning Keyword Spotting
Dept. Computer Science and Information Engineering, National Taiwan Normal University, Taiwan · E.SUN Financial Holding Co., Ltd., Taiwan · United Link Co., Ltd., Taiwan
EchoHawk: A Reproducible Acoustic Pipeline for Drone Detection, Classification, and Direction-Finding, with a Cautionary Study of Session-Level Data Leakage
Jun 28, 2026David ShulmanData Leakage Direction-of-Arrival Estimation
DRONEAUDIONET: Noise Suppression for Drone Audition-based Search and Rescue
Aug 1, 2026Chitralekha Gupta, Soundarya Ramesh, Yifei Luo +1
School of Computing, National University of Singapore

Jun 18, 2026J/K move · Enter open · S save

Personalized Keyword Spotting for User-Defined Keywords Leveraging Text-Independent Speaker Verification

Ming-Hsiang Hu, Kuan-Tang Huang, Chien-Chun Wang, Hung-Shin Lee+1

Dept. Computer Science and Information Engineering, National Taiwan Normal University, Taiwan · E.SUN Financial Holding Co., Ltd., Taiwan · United Link Co., Ltd., Taiwan

Zero-Shot Learning Keyword Spotting

Open paper AskPDF arXiv

User-defined keyword spotting (UD-KWS) enables zero-shot wake-word detection from text, but existing systems learn speaker-invariant representations that cannot reject impostors uttering the correct keyword. We address this dual zero-shot setting -- unseen keywords and unseen speakers -- with ZP-KWS, a lightweight framework combining a phoneme-supervised audio encoder with a GE2E-pretrained compact speaker encoder (about 0.9M parameters). Multiplicative late fusion at inference grants each branch independent veto power, supporting modes from conventional detection to strict speaker-gated activation without retraining. On LibriPhrase, Google Speech Commands, and Qualcomm datasets, ZP-KWS reduces target-only FRR at 1% FAR by up to 60% relative to the strongest baseline while maintaining competitive keyword detection, all within a 1.55M parameter budget for edge deployment.

Abstract

Keyword Spotting

Explore similar work

Personalized Keyword Spotting for User-Defined Keywords Leveraging Text-Independent Speaker Verification

EchoHawk: A Reproducible Acoustic Pipeline for Drone Detection, Classification, and Direction-Finding, with a Cautionary Study of Session-Level Data Leakage

DRONEAUDIONET: Noise Suppression for Drone Audition-based Search and Rescue