SmartSDR v4 – Noise Mitigation Quick Reference

Mike-VA3MW

https://helpdesk.flexradio.com/hc/en-us/articles/43315244661403-SmartSDR-v4-Noise-Mitigation-Quick-Reference

radioshopbob

When is FLEX radio going to give features we used to have back us??? I have asked this question ever since you folks started charging for your updated software and Version 4. I used to take care of my noisy environment here in the city, but now I can't. You guys took away the adjustment for the Noise Blanker and a few other noise mitigation tools. What are you thinking I now have SmartSDR Early Access and I still can't adjust anything. Come on FLEX. You just made my 6400M into a SWAN 500.

John Mikucki

Hey @Mike-VA3MW — thanks for the chart. Can you/Tim clarify one point for me? It says : "no user-adjustable parameters" — is that "we thought it was one-size-fits-all so we took out the sliders"? Or "no adjustment possible", as in, "there's nowhere in this new code for the user to provide hints to the NR"?

wb0z

I’ve also wondered why user adjustments to the noise reduction algorithms were removed. However, since multiple algorithms can be used together, giving each one its own adjustment slider would make the Maestro’s interface overwhelmingly large. On top of that, the number of possible combinations would be practically endless, meaning the time spent filtering through them would take far too long. Overall - I love some of the new filters, I just have to remeber that some of the new ones take 1 to 3 seconds to realy take effect.

lcyez

Using the new filter from SamrtSDR+ EarlyAcces

My primary use try to mitigate the noise for weak DX station

RNN for DX Station in noise, the signal disappear unusable for week signal in noise, the voice rx cutoff on-off-on-off sequence, lost the complete message, i cant use this, maybe if can adjust the level of the filter (now it is fixed), only work for reduce noise in signal S6+ for ragshew

NRS Reduce the noise a bit more than NR, the combination of the NR and NRS is the best approach for noise reduction but don’t enough

NRL for weak signal add watery noise

NRF add like eco to the weak signal

Mike-VA3MW

Here is the very approximate ranges:

🔹 General Rule of Thumb

Most digital noise reduction systems in SmartSDR (and SDRs in general) perform best when the SNR of the desired signal is between about 0 dB and +20 dB.
Below 0 dB, there’s too little structure for the algorithms to reliably distinguish signal from noise.
Above +20 dB, the noise is already low enough that filtering offers little benefit and may start to color the audio unnecessarily.

Filter-by-Filter SNR Guidelines

NRL – Noise Reduction Leaky

• Optimal SNR Range: ≈ 0 dB → +15 dB
  
  
• Why: NRL relies on correlation detection — it can track structured content like speech or CW as long as there’s at least a small margin above the noise floor.
  
  
• Below 0 dB: The filter struggles to lock onto the desired signal and may flatten or “wash out” speech.
  
  
• Above +15 dB: Little improvement; may add mild “watery” artifacts.
  
  

ANFL – Adaptive Notch Filter Leaky

• Optimal SNR Range: Any SNR (works even with negative SNR)
  
  
• Why: It targets tonal interference, not random noise, so it doesn’t depend on SNR of the desired signal — only on the strength of the interfering tone relative to total signal power.
  
  
• Rule: The tone must be at least 10 dB stronger than the background to be recognized and notched effectively.
  
  

ANFT – Adaptive Notch Filter FFT

• Optimal SNR Range: Any, provided tone amplitude ≥ –110 dBFS and ≥ 10 dB above background.
  
  
• Why: FFT-based detection looks for narrow, stable spectral peaks. SNR of the main signal is largely irrelevant; what matters is tone prominence.
  
  
• Caution: In very low SNR conditions with fluctuating tones, detection latency may increase.
  
  

NRF – Noise Reduction Filter

• Optimal SNR Range: +3 dB → +20 dB
  
  
• Why: Spectral subtraction assumes the signal spectrum is distinct from the stationary noise floor.
  
  
• Below +3 dB: Noise and signal spectra overlap, causing audible “musical noise” or speech clipping.
  
  
• Above +20 dB: Filtering has negligible benefit.
  
  

NRS – Noise Reduction Speech

• Optimal SNR Range: 0 dB → +15 dB
  
  
• Why: The VAD component can detect speech reliably down to about 0 dB SNR; below that, it may misclassify weak speech as noise during syllable gaps.
  
  
• Benefit: Best audible quieting for average voice signals near the noise floor (3–10 dB SNR typical).
  
  

RNN – Recurrent Neural Network

• Operational SNR Range: –5 dB → +20 dB
  
  
• Why: The neural network is trained to recover speech even when buried below noise — it can function at slightly negative SNR because it models speech characteristics rather than statistical separation.
  
  
• Below –5 dB: Speech recovery becomes unreliable; noise dominates all features.
  
• Above +15 dB: Processing may subtly dull transients; otherwise transparent.
  

🔹 Summary Table

Filter	Best SNR Range (approx.)	Notes
NRL	0 → +15 dB	Adaptive LMS; needs correlated content.
ANFL	Any; tone ≥ +10 dB over noise	Works on tonal hums, not dependent on SNR.
ANFT	Any; tone ≥ –110 dBFS and ≥ 10 dB above background	Multi-tone FFT notch; tone prominence matters.
NRF	+3 → +20 dB	Spectral subtraction; best for steady noise.
NRS	0 → +15 dB	Adds voice activity detection for speech.
RNN	–5 → +20 dB	Deep-learning model; effective even below noise.

Takeaway

• For weak voice signals (SNR 0–10 dB): Try RNN, NRS, or NRL.
  
  
• For steady hums or carriers: Use ANFL or ANFT — they’re insensitive to speech SNR.
  
  
• For clean but slightly noisy audio (> 10 dB SNR): NRF provides subtle polish.
  
  
• For deep noise (negative SNR): Only RNN has any hope of recovering intelligible speech.

serialcoder

Thanks Mike, great insight

IK8HCG

Mike-VA3MW

Mike don't judge me, even though I've been a Flex fan since 2005, but in this period I'm using and I recommend you test Thetis, you'll see how NR and NB work as well as lots of free news

lou