PEQ Beta - Testing Experience

Brantome

Moderator
Joined
Oct 20, 2022
Messages
5,745
Location
Scotland, UK
Please use this thread only to discuss your personal experience with the testing of the PEQ feature and the beta firmware you requested. This thread should not replace submitting tickets as that route provides WiiM support with the necessary device and app logs to diagnose and hopefully fix any issues.

From what WiiM have already posted:

“For those testing please see the tutorial below
We appreciate your ongoing participation as a Beta tester.

The PEQ firmware will be released early next week.

If you encounter any issues during the update process or while using this function, please do not hesitate to contact us. Your feedback is invaluable to us.

Thank you for your continued support and contribution to our Beta testing program!”
 
Last edited:
It wasn't easy at all to set the same PEQ settings on both ADI and WiiM units ...

Negative gain test:

LS 82 -1.5 0.9
PK 340 -6.5 0.5
PK 1980 -0.5 1.0
HS 9900 -2.5 0.5



1691944946327.png


Very similar results.
 
These noise level issues look similar to the ones observed by ASR user mdsimon2 here:

 
The behavior is so similar to some of the gears tested in the link you post, that probably wiim shares something (libraries or other stuffs) with them.
 
No idea, it's beyond my expertise level, but mentioned "quantization errors/noise" which are "amplified by the recursive part of IIR filters" and result in "the error/noise in the output signal" "higher when the pole frequencies are lower" look convincing to me. All due to insufficient precision or bit depth during DSPing.
 
ChatGPT 4 is helpful as always ;)

>"What can be the reason of elevated noise floor when PEQ filters are applied? It's especially high for low frequencies."
<"The elevated noise floor when PEQ (Parametric Equalizer) filters are applied, particularly at low frequencies, can be attributed to several factors:
(...)
Digital Processing: Digital processing can sometimes introduce quantization noise, which can raise the noise floor. This is more noticeable when dealing with lower frequencies because they have more energy and thus more potential for quantization errors."

>"The effect is in the digital domain so probably factor in point 3 is responsible for such behavior. Can you explain it further?"
<"Sure, I'd be happy to explain further.
In the digital domain, signals are represented as a series of discrete values, rather than a continuous waveform. This process of converting a continuous signal to a discrete one is known as quantization.
Quantization noise is a type of error that occurs during this process. It's the difference between the actual analog value and the quantized digital value. This noise is typically random and has a uniform distribution.
When you're dealing with low frequencies, these signals have more energy and are represented by larger values in the digital domain. Therefore, the potential for quantization errors is greater. This is because the difference between the actual analog value and the quantized digital value can be larger.
When you apply a PEQ filter, you're altering the digital representation of the signal. If the filter isn't designed or implemented correctly, it can introduce additional quantization errors, which can raise the noise floor.
Moreover, if the bit depth of the digital audio is not high enough, the quantization noise will be more noticeable. This is why professional audio processing is usually done with a bit depth of 24 bits or higher, as it allows for a much lower noise floor.
In conclusion, to minimize quantization noise, it's important to use high-quality filters and a sufficient bit depth when processing audio in the digital domain."

>"Can it be the effect of quantization errors/noise amplified by the recursive part of IIR filters? Due to insufficient precision or bit depth during the signal processing?"
<"Yes, absolutely. IIR (Infinite Impulse Response) filters are recursive, meaning they use previous output values in their calculations. If there are quantization errors or noise present in these previous output values, the IIR filter can indeed amplify these errors each time the filter is applied, leading to an elevated noise floor.
This is particularly problematic when dealing with low frequencies, as these signals have more energy and thus more potential for quantization errors, as mentioned earlier.
The precision or bit depth during signal processing plays a crucial role here. If the bit depth is too low, the digital representation of the audio signal won't be accurate enough, leading to quantization errors. These errors can then be amplified by the IIR filter.
In order to minimize this issue, it's important to use a sufficient bit depth when processing audio signals. This will ensure a more accurate digital representation of the audio signal, reducing the potential for quantization errors. Additionally, using high-quality IIR filters that are designed to minimize noise can also help reduce the noise floor."
 
You might be right.
can be more hoped for at least 24 ... and possibly 32 (your mini dsp is in?but that is also in his area of expertise...)
(I had already asked the question ( more of a small warning ) a while ago.. but had remained unanswered)
 
Last edited:
Thank you for implementing the PEQ. In principle, this is going in the right direction. The 4 band PEQ works smoothly for now. Switching between graphic and PEQ stops the playback. All my pending wishes have already been formulated;

  • 10 Band PK Filter PEQ
  • Numerical parameter input
  • right / left
  • Balance control
This is such a joy with you 🥰
 
Both modes have no pregain actually so must be compensated with the volume when needed.
there may be a funny approach to trying to rationally understand this level setting to adapt..: realize with the generator of rew...since the essential of the level will be under 4-5khz. realize a white noise 20hz -5khz -0.1db ... to test the saturation after correct positive gain and adapt the level
 
Last edited:
Hey Team,

I wanted to share some exciting updates regarding our progress on improving PEQ, all thanks to your valuable feedback:

1. Q Value Limit: We've successfully addressed the issue where the Q value couldn't be set above 1. It's now working as expected.

2. Noise Floor Fix: The problem of a high noise floor in the low-frequency range when the gain value is set to zero has been resolved.

3. Enhanced User Experience: Now, you can easily input frequency and Q values via the keyboard, thanks to the new App update (to be released next week).

Your contributions through feedback are invaluable, and we're immensely grateful for your ongoing support!
 
Hey Team,

I wanted to share some exciting updates regarding our progress on improving PEQ, all thanks to your valuable feedback:

1. Q Value Limit: We've successfully addressed the issue where the Q value couldn't be set above 1. It's now working as expected.

2. Noise Floor Fix: The problem of a high noise floor in the low-frequency range when the gain value is set to zero has been resolved.

3. Enhanced User Experience: Now, you can easily input frequency and Q values via the keyboard, thanks to the new App update (to be released next week).

Your contributions through feedback are invaluable, and we're immensely grateful for your ongoing support!
Is the elevated noise floor issue solved in PEQ in general, or only for 0 dB gain scenario?
 
Back
Top