Class D FAQ

[Overseas]

Serious question. Can one sit and not think? I've attempted meditation and mindfulness training and I just can't stop thinking about stuff.

Not according to the old adagio 'Cogito ergo sum'. But meditation and non-thinking come a very different way, not sure if a good one.

 

[Vive la dissonance!]

Q7: Yeah, but when we use a higher bandwidth measurement like 45 kHz or 90 kHz we can see the THD of high frequencies "ballooning" with high distortion. These manufacturers are lying by using using lower bandwidth 20 kHz to hide them! What about the measurements standards from last century?

A7: Remember that this is THD, meaning the harmonics of 10 kHz are 20 kHz, 30 kHz, etc, and the harmonics of 15 kHz are 30 kHz, 45 kHz, etc. They are all inaudible. This is intentional by design: maximize feedback loop to reduce distortions where it is audible below 20 kHz, and let it go where it is inaudible. See here. The 20 kHz bandwidth measurements just represent better what we actually hear.

Thank you for this update.

Here's the thing. We have a couple posters on ASR hounding us relentlessly with the supposedly critical importance of measuring SINAD at bandwidths well above 20 kHz, even up to 80 kHz or higher.

I decided to take a moment to consider this.

It's been remarked on correctly that humans cannot hear above 20 kHz as a theoretical limit, and that for the vast majority of humans, the actual limit is certainly quite a bit lower than that. I'll also note that 80 kHz is in fact well above the theoretical limit of hearing for a dog.

I've had some experience in the music world as a professional composer and musician, and I've dabbled in recording engineering myself. I've recorded professionally as classical performer as well, and I've very rarely seen in actual use microphones that are sensitive enough to pic up frequencies above 20 kHz at any decent dB level. A quick perusal of any of the most commonly preferred microphones used by the top recording engineers all have documented steep fall offs in terms high frequency response, usually well before 20 kHz. For example the famous Neumann U87s are at -10 db already at 20 kHz, and falling fast. Those are considered "vintage," but with tons of clones that are now commonly in use, included updated versions from Neumann, such as their U89: these all fall off significantly well before 20 kHz.

There are some mics available, such as the Sennheiser MKH 800, that actually do capture information at a reasonable dB above 20 kHz, but to my knowledge and experience they are actually not at all very common as a preference in the industry, oddly enough not even for high-resolution formats. Certainly there's no guarantee such mics are included in those recordings; when recordings have included mic information, the consistently most usual choices in my experience are not these ultra high-resolution mics. Maybe someone in the industry here can chime in as to why this is?

In any case, certainly Red Book CDs cannot include any sounds above 22 kHz. That's a hard cut-off, a consequence of the Nyquist Theorem. In fact, any frequencies in the signal above 22 kHz will "fold over" at equal amplitude at the difference between the signal and 22 kHz, subtracted from 22 kHz. Frequencies above 22 kHz are definitely therefore something the engineer would want to avoid, with an eye towards adhering to the Red Book standard, at some point in the mastering process.

Higher-resolution formats such as SACD or Blu-ray Audio can certainly include information above 22 kHz, if the source recording was made with microphones that have that sensitivity. Again, this is not at all guaranteed to be the case.

And let's be clear: the sound energy produced by ordinary instruments' harmonic spectra at such frequencies is extremely low! ETA: likely well below an audible range in dB terms even if human hearing included those frequencies.

Vinyl as a playback medium certainly can't come close to 22 kHz, and to my knowledge there are no purely acoustic recording formats that can.

And even with high-resolution formats, as far as I can tell there is not actually sufficiently consistent usage of those ultra high-frequency mics to be sure to be sure these recordings include information above 22 kHz (I could be wrong about this but it sure doesn't look like it). And they certainly won't when "mixed down" to the Red Book standard, nor indeed if they are sourced from an originally acoustic master.

What about speakers? Perusing the specs of most of even the most high-end speakers and monitors, I noticed that their frequency response almost always falls off of a cliff at 20 kHz. True, there are some studio monitors such as the Focal Solo6 BEs that are rated at -3dB at 40 kHz. But the overwhelming majority of speakers and monitors in people's homes and recording studios include tweeters that definitely fall off very quickly indeed above 20 kHz.

Those hounding for ultra high-frequency bandwidth measurements of amplifiers are therefore crying out for measuring distortion at ultra high frequencies at dB levels that:

• definitely all humans (and probably most dogs) cannot hear.
• most microphones cannot pick up.
• most playback formats cannot include.
• the overwhelming majority of tweeters cannot reproduce.

The first point explains the remainder. It doesn't make much sense to engineer for frequencies no one can hear; that's ultimately just a waste of effort and resources.*

I think it's fair to be persuaded by the measurement standards Amir is employing in his reviews.

Furthermore, I see zero reason to slander amplifier manufacturers such as Hypex and Purifi with thinly-veiled accusations of fraud, especially from someone who is also trying to sell their own brand of amplifiers.

I conclusion, A7 of this FAQ certainly answers this question to my satisfaction.

(*However, I'll concede that there do appear to be some advantages in the mastering stages of a digital recording to make use of higher bit depth than the Red Book standard 16.)

 

[jooc]

Q2: Yeah, but the continuous power is a fraction of the rated power. They simply cannot play 20 kHz full scale sine waves continuously for long! Look at the datasheet, they even admit it! Their FTC power rating is a fraction of what they advertise. This is a fraud!

A2: Music signal is dynamic, its RMS it about -12dB from full scale. Also it has much more energy in the bass area, 20 kHz is usually -40dB. In practice, playing loud music in difficult speakers, class D amplifiers run cool and for long periods. More info here.

I was having trouble understanding the full significance of this question and answer, so I asked ChatGPT. I found this response helpful (if accurate! , hopefully others do too:

...

Certainly! Here's a breakdown of the statement you provided about audio processing equipment:

• "Music signal is dynamic": This means that the volume and intensity of the music signal is constantly changing.
• "Its RMS is about -12dB from full scale": RMS stands for "Root Mean Square," which is a measure of the average power of the audio signal. In this context, it refers to the average power of the music signal. A level of -12dB means that the audio signal is 12 decibels below the maximum level (full scale).
• "Also it has much more energy in the bass area, 20 kHz is usually -40dB": This means that the music signal has a lot of low-frequency energy (bass) compared to high-frequency energy. The -40dB refers to the level of the signal at a frequency of 20 kHz, which is typically much lower than the rest of the frequency range.
• "In practice, playing loud music in difficult speakers, class D amplifiers run cool and for long periods": This statement is discussing the use of class D amplifiers when playing loud music through difficult speakers. Class D amplifiers are known for being efficient and generating less heat than other amplifier types, which allows them to run for long periods of time without overheating.

Putting it all together, the statement is saying that music signals are dynamic and have more low-frequency energy than high-frequency energy. When playing loud music through difficult speakers, it's beneficial to use class D amplifiers, which can run for long periods without overheating due to their efficiency.


Regenerate response

 

[babadono]

That is a very bold statement in 2021.. Somewhere, somehow, someone is always offended .. and that offends me very much

well I'm offended that you're offended