What makes One Music Server Sound Better than Another?
So this week my Mojo Audio DejaVu music server that I have used for the past 2-3 years crapped out. Benjamin at Mojo was more than helpful and the DejaVu is on its way to Mojo Audio where it will make a full recovery.
Thankfully, I still have my Antipodes DX2 Gen 3 (their former flagship) music server so I hooked it up. After wrestling with Roon protocols, transfers, and set-up menus, I was able to get it going so I have music. The DX and my Sonore Sig Rendu SE opt. are both connected to my network so the DX (like the DejaVu), is only being used as a Roon core and the Sig Rendu SE serves as the Roon endpoint for streaming Tidal and Qobuz, with a direct USB connection to my DAC.
The point of this thread is to ask, how come I perceive the the DejaVu server as sounding better than the Antipdes DX? In fairness, the differences I perceive are not great but it seems the DejaVu is fuller sounding, more tonally rich, and bolder. Is this why some here spend $10K+ on a Grimm, Taiko or something else?
If a server is basically a computer, sending digital information to a streamer/endpoint and, assuming that digital information is transmitted asynchronously and reclocked by the DAC’s master clock, and assuming noise is not the issue (i.e., both units are quiet and there is an optical break between the network and both the server and endpoint) then what are the technical reasons one should sound better than the other? It is not that I want to spend $10K+ on a music server with a lifespan of maybe 5 years before becoming obsolete, but I would like to understand what more you are getting for your money. So far, the best I can come up with is lower internal noise as the major factor.
As a side note to the above, when I thought things looked hopeless for getting set up, I scheduled a support session with Antipodes and, although I lucked into the solution before the meeting time, Mark Cole responded ready to help. Setting up the session was super easy and reminded me of the superior level of support I had come to enjoy from Antipodes during the time that the DX was my primary server, including multiple updates and 2 or 3 hardware upgrades, which prolonged the service life of the DX. Good products and good company.
Exactly. The server, modem, router, etc. are in my network room and the streamer and DAC are in a separate room with my audio system. The streamer connects to the router by 45 feet of fiber and USB connects the streamer to the DAC. |
Well I’ll be darned, Roon’s basic software changes the sound without using any fancy filters or DSP. I guess that other guy was right. Live and learn.
|
OP: I don’t know exactly how those two different servers run Roon - it’s possible they’re adding some DSP or otherwise doing non--Roon-standard manipulations. But if not - same Roon version, same configuration, across a network, bit perfect is bit perfect. Doesn’t matter the server source. For clarity, my post is not about hooking a DAC up to a server directly, where at least there is a form of direct electrical connection. It’s about server streaming to endpoint over a network. If some of the posters’ suggestions here were true, when you go to an ATM to withdraw cash sometimes you get a few dollars less and sometimes a few dollars more. When you check your bank account online the numbers will be different every time. When you email someone, the network will introduce typos. When you send a word document, text will change. IP network transmission simply does not work that way. As long as you have bit perfect music input at the server end you’re going to have the same bit perfect output, no matter what else is at the server end, at the streaming end. [Admit the distant possibility of streamers sounding different]. If you want to explore this, I suggest you take a computer and use that as a Roon server to your same endpoint and do those comparisons. As long as you’re not hearing dropouts, and each is configured for identical DSP, volume, etc., whatever processing you have configured is identical (and there’s sufficient horsepower!), it’s gonna sound the same. I have 3 roon servers here on different platforms for different reasons, but it’s not SQ. |
That is exactly what I am doing, along with having optical fiber isolation of both the server and the endpoint from the network. and
This is the presumption I am going by. My plan is to continue using a reliable, well-built, server, somewhere south of $5K, and then spend a little more as needed on the endpoint and DAC. I may actually be there now with the Sonore endpoint and Mojo Audio DAC but, in either event, I do not plan to purchase a meg-buck server to chase potential SQ improvement that may not actually be realized for the server-only function.. |
Sorry, should have been more clear - the reason I added that paragraph is that someone always posts about concerns only related to having the DAC connected to the server. All of this about noise inside the server running down the USB cable. I wanted to be clear that concern cannot apply to your situation or what I was discussing.
|
Part of the point is you don't need to do that, albeit I am not criticizing the choice. It's more of a matter of convenience if you want auto CD ripping and things like that. Roon works with any PC with sufficient horsepower to run whatever DSP etc. you want to use. You won't get any sound bump from any choice unless you hear hiccups or dropouts caused by an overtaxed server, which you can easily determine with the processing speed indicator in Roon. I have a fairly powerful machine currently running at 60x, meaning I can theoretically support 60 streams before any issue. Not everyone wants to build their own PCs, I get that. But it's actually not rocket science and you can build a well overpowered Roon server for $1000 maybe less if you have a PC with some of the parts already that you can salvage (power supply, case, the stuff that gets obsolete less quickly). My personal view is people buy these pre-built audio server computers because they look cool. Which they do. But they're sold with stories of superior audio quality when you get to identical quality with the above plus your chosen streamer. [Repeat acknowledgment of theoretical possibility of streamers sounding different]. Anyway, I just say this so that when newbies search "what music server should I buy to use Roon" there will be some balance of opinion against those expensive, fancy servers that get obsolete within a few years due to ever increasing CPU, memory, and hard drive speed, when you can upgrade a standard computer for ~$500 instead of spending 4 to 5 figures to replace the whole fancy prebuilt server. |
It is interesting how we are so skeptical of the whys and hows of a better sounding streamer, or for that matter anything in the digital front end. Sure implementation and components and software make a difference. But when it comes to better sounding amps, while we can study the components, capacitance, power supplies, ratings and schematics, we generally accept that this amp or that sounds better than others. Same with speakers. Is it the crossover? the cabinet? the driver material? the internal wiring? the placement? the cables? Or do we all generally know which brands and models sound better? Our ears tell us if we listen and can hear. |
That may be for some but I suspect it has as much to do with people being concerned with upgrading every possible component in their system to the highest possible level so as not to miss out on the n’th degree of sound quality. My server sits in a back room with my network equipment so from my perspective it could look like a cardboard box, as long as it works well. To the point by @fastfreight about skepticism related to digital front end equipment, I think that is related to our preconditioning that 1’s and 0’s are relatively immune to outside effects so as long as the 1’s and 0’s arrive at the "receiver" intact, the resulting isolation, error-correction, and processing will handle it from that point. In contrast, most seem to believe that the downstream analog processing (i.e., D/A conversion, amplification, and loudspeaker conversion of an electrical signal to a sound wave) is not immune to outside effects, and therefore believe the music we hear is largely dependent on the quality of the DAC, amplification, cables, and speakers. |
“preconditioning that 1’s and 0’s” Your last post aptly addresses the skepticism around spending more money for a well designed server. There are always going to be those who are completely content with running ROON core on a < $1K off the shelf NUC and then there are those who recognizes what’s needed to get a better SQ from a ROON based setup. |
I'm talking about the SQ of a server when using an endpoint over a network. It is the same set of bits at the receiving end, no matter the transmitter. That exact configuration is all I'm referring to. As I said in my post above, if that wasn't true, then emailing word files would introduce typos and your bank account balance would be different every time you check it. That isn't to say that fancy servers don't have their advantages in terms of other functions and features, support, being well built, and looking cool. But over a network, the packets don't know if they are coming from a supercomputer or a networked doorbell. |
but @jji666 it sounds better. it does. you do not have to enjoy better sound. |
Not sure if this is jest. But if it sounds better, which empirical result I am open to, then it is because there is a different configuration. The server is not sending the same set of bits, which necessarily means that the server has something different configured within the software. Because it cannot sound anything but exactly the same unless the bits it sends are different. The receiver simply doesn't know whether those bits are coming from a fancy server or a Raspberry Pi. |
Digital data transmission can be perfect for computing, and bit perfect when comparing the data streams of many music servers/streamers/players at widely varying prices. What can account for significant sonic differences despite being bit perfect has to do with the timing of the data stream as well as embedded noise and jitter. The objectivists will argue that they’re just ones and zeros, but when handling audio data streams there’s much more involved than just the data being bit perfect. |
@jji666 and that is why it won't sound as good as dedicated music servers. |
It is not about the packets, it is not about the bitperfect-ness, the data will get there regardless, it is about noise. Read the link I posted previously from Antipodes. Imagine someone throwing a floating candy in a stream of water, and then 1 mile downstream you pick the candy out of the stream and eat it. A low grade computer is a contaminated sewer infested stream, with industrial waste, dark brown in color. A high end music server dedicated to audio the stream is pristine, perfectly clean, pure water. You get the candy with either stream, it is the same piece of candy either way, but which one would you eat. |
I think you just nullified your own argument? I'm not saying that to get into a fight - but you say it is the same piece of candy either way. Yes it is the same, identical, exactly the same, not different, not dirtier, piece of candy. In an IP network, the candy is broken down and re-integrated at the receiving end, exactly as it was before. Other than the lag it would cause, it could go around the world, into space through a satellite, and back down and be the same. What you are saying is that a dirtier computer sends different bits. It does not, or it would not be bit perfect. It just doesn't and can't work the way you describe. Sewer infested stream, brown water, those are analog concepts if they can be applied at all. What comes out of the network card, over the cable, and to the switch is identical regardless of your pollution analogy. The network doesn't care about the brown water in the server. It just doesn't. I am not saying that you should not purchase fancy servers. But don't purchase them for sound quality unless you insist on plugging the DAC directly into it without using a streamer, which isn't a best practice according to Roon. |
OK, so we have chicken, word salad from Antipodes, and candy. At least we won't go hungry. But the SQ remains the same. Digital logic, especially in IP networks, simply isn't amenable to analog logic, much less analog metaphors.
This *could* apply to the digital transmission of data from a computer or other digital device via USB to a DAC, which is a kind of a stream. Technology has addressed it a long time ago, but theoretically at least your concern above could apply. Doesn't apply to IP networks. The packets are reassembled, anything missing is requested and reintegrated, before that info goes anywhere. The buffer assures there is sufficient data for continuous music. If that failed, you'd hear a dropout, not less depth and bloom.
|
Okay well I tried :) But did you read the link? It does a pretty good job of explaining "why". I think you just need to go a good audio dealer and ask them to play you your favourite track with a macbook and then a high end streamer to prove it. I just received a high end streamer, and I proved it to myself. I don't need to read anything from anybody anymore. I know the truth. |
I have actually done quite a bit more than that. I've been building all variations of PCs from fanless quiet nothings to super beasts. So I've had my hands on a lot of different variations. |
Now now, no need for ad hominem attacks because someone posts a contrasting viewpoint. That reflects much more poorly on the attacker and just means you don't have any substantive point to add. If I were to be snarky in kind, I'd agree that my expertise is irrelevant to the matter at hand because the matter at hand is purchase decisions irrelevant to the actual objective of sound quality. But I won't. Instead I will just say that I'd rather have a positive "relationship" (such as it is with a forum) with someone who loves audio even if we cannot see eye to eye on these matters than get into a flame war. The point being there are so few of us audio lovers why do we have to battle. But if you're going to flame, I'm not going to just be a target either. It is absolutely true that I have never caught a chicken. Not unless it came from a drive-through window. But I do remember when my relatives in Sicily taught my sisters how to pluck one, thinking it would be a useful skill for them in the US. |
I had scanned it before, but I have now read it closely. Actually, I think it supports the position that the server end of a server-network-streamer configuration does not contribute to SQ, assuming sufficient processing resources to use DSP and avoid dropouts. Here is what Antipodes says about their servers:
So Antipodes does what Roon suggests: it has a high powered, electronically noisy server that decompresses the FLAC to PCM and applies DSP. This is an acknowledgement that no matter the electro-noise at the server side, the network will clean it off for them. Here's what they say about their "player" side (streamer in our lingo):
Right. the noise at Step 1 doesn't matter - it is "cleaned up" later. While Antipodes allows their streamer to take credit for getting the level of electronic noise down from what the server sent, it is actually just the network that does it. However, fine, good to have an electrically quiet streamer just to be sure. The remainder of the Antipodes steps are not relevant to the conversation. The underlying point is that Antipodes itself acknowledges that it is not cleaning up the audio quality at the server end. It is simply doing the same thing that ANY sufficiently powered computer will do. Except, and I don't know this part, maybe there is a proprietary protocol in communicating with their streamers so that only the Antipodes server can talk to the Antipodes streamer so that you have to buy both even though the server part doesn't need to be quiet or clean or anything but a computer. I will say those are beautiful looking pieces and I appreciate how they relabel the backplane for audio purposes so that those who aren't comfortable with computers can use them. However, I'd bet if you plugged a ripper into the "disk" port or a disk into the "Ripper" port, they would work either way because they're just standard USB ports. Look, these guys make beautiful high end computers for use with audio. There is nothing wrong with buying one of those. I would if I had that kind of income. And they cannot just come out and say "you don't need our servers to feed a streamer and get the same quality" albeit that is the natural result of what they do say. But, please, just don't buy into the idea that you HAVE TO have one of these to optimize sound quality. It's a shortcut. You know it's quality gear. But the server side simply isn't relevant to SQ. Not as long as the server can keep up with the stream it needs to send. |
| Post removed |
I absolutely agree with @jji666 . And there’s a ton of support for his position from a subset of the audiophile community, that includes engineers, designers, Roon Labs itself! There seems to be a bias embedded in the arguments from a different subset of audiophiles. It goes like this: “I hear a difference. If you don’t hear a difference, my experience trumps yours.” That makes no sense from a logic perspective. In the absence of any other explanations, those two observations have equal weight. It is certainly possible that one person has a more resolving system, and/or better ears, but ceteris paribus, they have equal weight. But then, when you introduce the digital science, that seems to give more weight to the listener who hears nothing. But wait, the first listener hears a difference, that has to be explained by science too, doesn’t it? Well yes, as a matter of fact, there’s a whole science behind confirmation bias. Now to be clear, the second listener is also susceptible to confirmation bias, perhaps to hear nothing. But on balance, the better argument goes to the second listener, because that argument does not require an assumption about greater resolution, golden ears, pseudo science, or faith, to make sense. Btw, when I started my own journey on the streaming side, before I did any serious research, I assumed I’d hear a huge qualitative difference when I changed servers and cobbled together a Raspberry Pi as one of my first post-retirement projects (i.e., my own bias was to hear differences). Just my two cents….
|
@jji666 You have done your homework, I commend you on your perseverance. It's obvious you know more about computers than I do, and I think you are a better arguer. But I don't think people buy Porsche's just because they look nice and they want to brag about them. All I'm going to say is what I said before: take your server/player to somewhere where their is a high-end "audiophile" server/player, setup with appropriate highly revealing other components and cables and compare. |
Dear jji666, you miss the point about catching chickens. Here is the point: You can talk about how best to catch a chicken but until you have experience catching chickens, what you have to say is mostly meaningless. The First Rule of Audio: Your system sounds great, until you hear a better system. If you truly love audio, stop postulating, get out there and hear some good hifi systems and some hifi streamers/servers for yourself. You might or might not hear a difference. That’s ok. It’s a personal matter. Music, like all art is personal. The issue that one person can hear something that another doesn’t is much much deeper than confirmational bias. That’s merely a cop out for the ASR crowd. Many factors come into play beyond the listener variable. A good example was what happened last week to me. I found a song on Qobuz that had some bad microphone clipping. Sounds like crackling noise. I have a very high resolution system. The noise was like a slap in the face. I texted my cousin to try that track on his stereo. The track sounded fine to him. I played the track on my iPhone with headphones and I played it in the car. I could not detect the mic clipping at all in either case. I bought the CD. The CD plays cleaner than the Qobuz version but the clipping is still there- just not as bad. I ripped the CD to FLAC and the same thing. But on the Roon app I can see that the recording levels are maxed out. That’s one of the downsides to a high resolution system. |
I think your example misses the point (by a mile or more). My home system is way more resolving than my car system, of course. I always hear more on a more resolving system, of course. The only question here is whether a change in servers - beyond basic performance parameters - can contribute anything to that increased resolution. |
Dear mdalton, I looked at your big rig. Very nice indeed. Let me ask you- which do you prefer most when listening, your vinyl source or your digital source? I going to guess your vinyl source. I bet you hear a difference in not just the sound but in the rhythm and pace of the music. That's where that Garrard TT excels. You might stream or play digital in the background but I bet when you sit down to listen you favor records. No? |
Thx, I totally get your point. Here’s mine: Avg DAC + Avg. Server = Average Sound Good DAC + Avg. Server = Good Sound Great DAC + Avg. Server = Great Sound. The main difference is I can explain why, and I saved alot of $ on a server. Having said that, I still love your system - if I had to do solid state, I’d be tempted by Pass Labs - and I’m quite sure your system sounds great. |
I had the good server and got a great DAC. Tried the great server with the 30 day trial safety net. Great server is not going back. Previous server was a NUC based RS9 (an improved version of the Nucleus+) with a Keces P8 LPS. I thought it sounded great. Refer to the first rule of audio. As with any expensive purchase I had to make the decision what am I willing to give up? Audio came first but I had to agree to new floors for my wife. So even more so what am I willing to give up... |
I plan to write a review of my new music server after I've had it a month or so. But I will list a few things that persuaded me to keep it. 1) The music sounds better. All digital grain, glare- that cringing that happens with peaks in the music is gone. The thing that I have noticed is that with my new DAC, I could play the music louder. Now with this new music server I can play the music even more louder. I'm not talking about run everyone out of the room loud. I mean just good levels for jamming to the music without cringing now and then. 2) Rhythm and Pace are excellent now and as good as my vinyl. If I played records for a while and then switched to digital, that's when I could really tell the difference. The new DAC was a great improvement when playing CDs with my transport but not so with my old server. That's one of the things that prompted me to try a better music server. The new server delivers on rhythm and Pace. 3) Noise. No noise. The background is black like I have not experienced before. When I hit play the music explodes out of nothing. I jumped every time I hit play for the first few days. With my old server I could hear the noise floor raise up when I hit play. Not a lot but audible like a prelude to the music. 4) More detail and resolution. This is not necessarily always a good thing but it is addictive to the point that I find it hard to give up once I have it. The added detail can be distracting and take away from the music at first. It takes some getting used to. While it brings out more of the "being there" it also reveals flaws and errors in recordings. |
I believe I've already done this without having to take it anywhere. I've built all level of servers, from the AudiophileStyle's totally quiet fanless model with no moving parts and using the various OS tweaks that are/were supposed to bring OS operations to the quietest levels possible, to powerful beasts that may clearly have noisy electro-stuff. I mean, I have probably built 15 Roon servers. All flavors. The transmitter in a network configuration just cannot generate a different sound. I've been designing and building media computers for over 30 years - I'm not just guessing here. What I don't have are the fancy milled aluminum parts to make those beautiful chassis. Please, don't tell me the chassis affects SQ! In terms of resolving gear, I have Magnepan, PSB, KEF, Monitor Audio, B&W, Krell, Balanced Audio, Focal, Levinson, Classe, Bryston, Parasound, Wyred4Sound, Auralic, Schiit, and Mytek. I'm good on resolving.
See above. By your analogy, I have caught a lot of chickens. I have been obtaining, churning, buying, listening, tweaking, all manner of resolving enough gear for a long, long time.
Music is personal, for sure. What isn't personal is how IP networks function. What isn't music is what goes from the server to the streamer. It's packets of IP data, the same regardless of the sender. This "my system is bigger than yours" method of winning arguments, well, just try to read it objectively. |
Your K50 is a server/player, performing both server and player functions before directly feeding your Aries-Cerat Helene DAC. Since the player is in the same box as the server, and since the K50 server/player resides in your equipment room, it needs to be quieter than a server only component that resides at a location away from your analog gear. I have no doubt it sounds excellent. The interesting experiment would be to first have the K50 in your system room connect directly to your network, perform the player-only function, and output directly into the DAC. Second, set up a second K50 in a separate room, also connected to your network, and performing the server-only function. Finally, replace the server-only K50 with a different, lower priced computer-type (i.e., not audiophile royalty) server, although still using the K50 in your system room as the player, and then listen for a difference in sound quality.
|
Or, maybe, just correct? As above, ad hominem attacks really just affect the credibility of the attacker.
And absolutely the same to you. As I said above, I would very much prefer to focus on our shared passions rather than differences in belief. And to wrap it up (hopefully), compared to many of these debates, we've gone back to our corners relatively peacefully. I think we should both be commended for nothing worse than a few swipes. |
Antipodes also sell the server and player as separate boxes. The K22/K41 is equivalent to the K50 in outputs and performance. I considered that option but it ends up costing more after buying an extra power cord and extra ethernet cable. I looked for some information about differences in performance between the combo and separates but couldn’t find anything. Their top of the line Server/Player comes as a single box only option. I agree with keeping all those noisy digital boxes away from my analog gear. The K50 is 3ft from my preamp. I could probably move it a few inches more. I’m not really sure how much noise radiates from the server/player or the network switches. I added ferrite cores to my ethernet cables as a wild guess at reducing radiated noise but no idea how effective that is. |
This is not my area of knowledge, so just passing on what I've read. You may want to Google the efficacy of ferrite chokes on network cables. I have read that it can actually introduce errors. Presumably the network components can correct for that as I and others have described above, but the ferrite core may actually be more of a concern than anything a fancy server can resolve. To be clear, I am not expressing an opinion or disagreeing with anyone. Just suggesting you do some reading and confirm you want to take this approach. |
Tony, the point was not really about how it sounds in your system (I suspect it sounds fantastic) since both the K50 and the Aries-Cerat Helene are well-regarded, top notch digital components. The question is whether the extensive build properties of the K50 (and resulting price) would be necessary if it were used as a server-only, or whether the same sound quality could be achieved by using a (less expensive computer-type) server located in another room away from the system, performing server-only duties, and feeding a K50 used as a player-only into the Aries-Cerat Helene DAC, i.e., would you be able to tell the difference between the server-only K50 and a different server? |
Using Roon that would be really easy to do, as the user interface in the K50 allows one to switch server and player duties- all he would have to do is press a button on the web interface to swap the Roon core from K50 to the NUC back and forth with the Roon remote, where the K50 player is constant for both. But @tonywinga did say he was going to do a review, so perhaps this comparison would be included in that. |
Yeah well, I already traded in the NUC. But I would not be able to do that with my old music server anyway. The old NUC based server had just one ethernet port and then USB out. So to use it as a server with the Antipodes, I would need two ethernet ports- one port in and one port out to the player. The K21 or the K22 both have just an ethernet port for an input. The K41 server has two ethernet ports- one purposed for input and one purposed for output to the player. |
