Oversampling vs upsampling

I believe that upsampling refers to the 16/20/24 numbers. Oversampling changes the sampling rate (44.1/96/192). I'm sure someone here can elaborate on what sounds better...I'm not sure myself.

I try to do my best:

First of all, as far as the mathematic goes, upsampling and
oversampling is exactly 100% the same according to digital filter technology (sampling is basically having an electrical signal pass through a digital filter). Upsampling and oversampling BOTH convert a 16bits/44k original signal from a CD into a higher frequency, usually multiple of this 44Khz frequency. I won't go into detail but converting a digital signal into an audio signal (hence the name DAC) can be done much better when the digital signal is at a much higher frequency than the audio signal. Some DAC converts the original digital signal from 44k to 256Khz or even higher before converting to analog signal... So you can say that most DAC have some kind of upsampling done within it, but by convention in the audio industry, any upsampling done inside a DAC is called oversampling.

Pretty much all CD players have some kind of oversampling and this oversampling is all done in one single all purpose DAC chip , especially budget cd player. You can think of a cd player as the below diagram:

Original signal from disk -> oversampling DAC -> preamp

Now enters the Upsampling thing.
You might ask if upsampling as oversampling is mathematically the same then why the fuss?

Physically, an upsampling is a dedicate digital filter that is used solely for the purpose of converting a digital signal to a higher frequency that is multiple of the original signal (as opposed to a DAC which has to upsample the signal then have to convert the signal to analog). This "upsampling signal", after passing through the upsampler, then get inputed to a DAC then the DAC would upsample some more, perhaps to 256K, then coverts it into analog. With upsampling the above diagram can be view as followed:

Original CD signal -> upsampling to 96 or 192 -> ovesampling DAC -> preamp.

The trick is you have to use a high quality dedicated digital filter for your upsampling stage. If your upsampling is crap, then everything else after that will be crap so you would be better off without all this upsampling altogether. In most cases, it's a lot easier to make a high quality upsampler by itself than to having to incoporate it into a DAC. Of course, you can make a very good, high quality stand alone DAC and can outperform a so-called CDP that uses upsampling technology, but I guess that it is more cost-effective to use upsampling as opposed to spend all that money into a really complex, high quality DAC.

Hope this help.

By the way, the number 24 in 24/96 has nothing to do with
upsampling or oversampling. It simplies indicate the digital filter (or DAC) would convert the original 16 bits into 24 bits. Number of bit and sampling rate are mutually exclusive. You can certainly have the original 16bit/44k signal converted (or upsampled) to 18bit/96khz or 18bit/192khz.
But nowaday, most DAC companies such as Analog Devices and so on only manufacture 24 bit DAC hence their popularity in cdp.

I think a lot of confusion are due to the way companies marketing their products but it really boils down some basic technology.

Andy, Thank you very much!!

Thanks for a great explanation, Andy2! Now does the number of DAC chips used in the upsampling/anolog conversion have anything to do with sonic improvement. I know that Accuphase uses more I/C's in their higher pried models?

Statistically, I would think that it "smooths" out the signal at the output.
Having two dac is equivalent to summing the output level of the DAc, average them (like (a + b)/2), then send them out to the output. It's like taking the average of two signals.

Whenever you take the average of anything, you reduce the peak and dip of that things that you try to average.
It's like the average income of people who live in California and people who live in Nevada is more or less the same. But if you look at the income of each individual in each state, you would see a lot of "peak and dip".

The same applies for electrical signal when you try to average them.

I have a Cary 303/200 and it also uses 2 dac per channel.
The Cary 306 uses up to 4 dac per channel and I think that's why it sounds smoother than the 303.

Close. What happens when you sum the outputs of two devices is that the signals they have in common (the real data or music) is summed (x2) while the random signals (noise) is cancelled. This is because the real signals occur at the same time in the same phase while the noise on one DAC is likely to be slightly different from the noise on the other. When you sum, the noises cancel and the real data sums.

Result is improved SNR.

Check out the following URL for an excellent article on this subject.

www.audiophilesystems.com/dcs/upandover.htm

Cheers! JZ

Another very informative article on the subject written by Mike Story of dCS Ltd., (manufacturer of the Ring-DAC), can be found at:

http://www.audiophilesystems.com/dcs/dacsandupsamplers.htm

JZ.