Frequency estimator improves tone detection across noisy environments
Frequency Estimation Based on SNR-adaptive Frequency Estimator Under Wide SNR Range
SoundArtificial Intelligence
Summary
Estimating frequencies from signals with lots of background noise is challenging because weak tones get lost in the noise. To fix this, the authors designed a system called SAFE that adjusts how it estimates frequencies based on how noisy the signal is. SAFE uses a neural network to boost weak tones when the noise is high and then chooses the best estimation method depending on the signal quality. Their results showed that SAFE finds true frequencies more accurately and misses fewer than previous methods, working well even with real-world noisy data. This approach helps in applications where precise frequency detection is needed despite noise.
Frequency estimationSignal-to-noise ratio (SNR)Multi-tone sinusoidal signalsNeural networkTime-frequency analysisLow SNR robustnessSuper-resolution frequency estimatorFalse Negative RateRoot Mean Squared ErrorSignal processing
Authors
Hee-Yang Jung, Dong-Hee Paek, Woo-Jin Jung, Seung-Hyun Kong
Abstract
Frequency estimation is the problem of estimating individual tone frequencies from noisy multi-tone sinusoidal signals. Existing frequency estimation methods have difficulty accurately estimating both the number of tone frequencies and the individual tone frequencies in low signal-to-noise ratio (SNR) environments, because weak tone frequency components are buried in noise. In addition, existing methods generally exhibit a trade-off between robustness at low SNR and frequency estimation precision at high SNR, making it difficult to achieve consistently superior frequency estimation performance over a wide SNR range. To overcome these limitations, this paper proposes an SNR-adaptive frequency estimator (SAFE). SAFE consists of a time-frequency image neural network (TFINet), which enhances weak tone frequency components at low SNR, and an SNR-based frequency selector (SFS), which selects an appropriate frequency estimator according to the SNR of the estimated tone frequencies. TFINet enhances tone frequency components even in the low-SNR range, while SFS estimates the SNR of each tone frequency and selects either a robust frequency estimator or a super-resolution frequency estimator according to the estimated SNR. This enables SAFE to achieve robustness at low SNR while preserving high precision at high SNR. Simulation results show that SAFE achieves an False Negative Rate (FNR) of 13.00% over the SNR range from -10 dB to 0 dB, corresponding to an 13.04% improvement over the state-of-the-art method. In addition, SAFE reduces the Nearest Neighbor-Root Mean Squared Error (NN-RMSE) by 56.67% compared with the state-of-the-art method, demonstrating that SAFE performs more accurate frequency estimation. Furthermore, experiments using real-world data demonstrate that SAFE provides robust frequency estimation performance even in practical environments with clutter.