We Need To Talk About Ones And Zeroes

I don't think its a great mystery that noise rides on grounds, clocks control the timing of  data packets, the lengths streamer manufactures go to address these issues is part of what differentiates streamers.

 

Perhaps those noisy server farms are indeed limiting the full potential of high end audio  streaming, somewhat analogous to the quality of the power grid and it's influence on our systems.  May not matter as much for streamers since ethernet is galvanically isolated from grounds noise.

Well I guess the hearing demigods amongst us should band together and buy these streaming services and make sure everything is sent through a vacuum to their home untouched. That is the only way they can hear the imperfections that are riddled in music cos the music is made with impure mics, impure tools like noisy controller stages.

This obsession in this space has gone beyond just wanting to enjoy music so I engage less and less with people with certain supposed ideas cos it can become a loop of argument. I just let people be now @devinplombier 

Did we ever move past the question: Why does one vibrating stylus in a groove of vinyl sound different than another? 

Has anyone asked for proof how different turntable setups sound different? Or does everyone just accept that they do? 

Why don't all 300b tubes sound the same? It's all just a flow of electrons. 

This, again?

I did not understand one word after "AWS server farms are any audiophile's nightmare". How? Streaming is streaming. Netflix handles a 100 times more complex requests than listening to a music file. Everything is built on the packages arriving, that's the whole point, zillions of hours of coding and scaling went into those projects, I don't see how it's a miracle (aside from electricity and the internet being a miracle). I honestly think our infrastructure and processing capabilities are way dumber than it should be.

This is too far out there to even discuss. 

Hi-rez digital can sound better than Redbook standard digital.  You don't even need an all out assault on the state of the art system to demonstrate that.

Digital sounds like digital.(no matter what gear IMHO) Analog sounds like analog; to me anyway. Hey, I like them both. I guess I've been a wee bit over top with the hobby for years but I enjoy every minute. .......admittedly, I enjoy the convenience of digital but will spin vinyl whenever I can. To me it is also is very source dependent as well. Sometimes the best versions are CD's SHM CD's, DVDs SACDs or the "selected" vinyl version. Mono and Stereo ???........to me this what makes it all so very fun.  

Not exactly sure what the goal is here. 

My understanding of what you are saying is, in short, that we all receive basically the same digital signal when streamed through our ISPs and that the digital signal is of sufficient quality that when converted and played through an adequate home music system the result can be very satisfying.  Is that what you want us to agree on?

I am not sure why it is important that we agree.  The evidence shows it to be true or otherwise why would so many audio enthusiasts have given up CDPs and turntables in order to have streaming as their sole music source.  The evidence also shows that modifications to the playback chain, i.e., galvanic isolation, reclocking, power supply isolation, etc., can further affect/improve the end result of what we hear, whether or not those modifications change the 1s and 0s.

Have I missed the point?

In any event, as always, we vote with our wallets so, whether or not we consensually agree on the technical aspects of what is happening, the general purchase trends will tell the tale.

In order to test for this one would need to directly connect their streamer to a server with locally stored files, no storage in cloud. This means server with original files at some record company/mastering concern/etc. Ain't never going to happen. And again I'll go back to analogy to power grid, audiophile insistence on providing clean grid/clean streaming chain is of no concern to these entities. Since this the case I guess we need to provide for our own power grid and local storage of Qobuz, Tidal, other music services massive libraries. Again, this ain't gonna happen. Point is why should we bother with things we can't change.

And we have a most obvious comparison. How does one  cd rips in local storage compare to their streams?  Many report, and I agree their streams are equal to the cd rips, what does this say about the importance of server farms, clouds.

"Several well-respected audiophiles in this forum have stated that the sound quality of hi-res streamed audio equals or betters the sound quality of traditional digital sources."

What's a traditional digital source, a CD Player? If so, are we comparing apples with apples? You said hi-res, so I assume you're talking about something other than CDs 16/44.1 - therefore not really comparing like for like.

Anyway, I "stream" from files on a network hard drive and rarely from online streaming services, because in my experience even their hi-res files mostly sound bang average, about on par with CD.

 

TCPIP does a great job of transporting bits and checking that they are correct. Your router receives them (or they are caught coming off a CD transport in the case of a CD Player) and adds a bunch of electrical noise... they are processed in a quiet vibration free environment... or not,  and retimed. All the sound quality stuff happens after being caught and translated into analog. 

What are digital signals?  They're really not 0's and 1's.  They're nothing more than an analog representation, voltage differences, of a 1 and a 0. Any significant change in the voltages impacts what the voltages represent, let alone their timing, ex. reclocking. It's a wee bit more complicated than just 0's and 1's.

@ghdprentice said... "All the sound quality stuff happens after being caught and translated into analog."

Yes, this! What the OP was illustrating by his description of the infrastructure used to support some of the popular streaming platforms is, we're all drinking from essentially the same well. We're all pretty much getting the same one's and zeros. 

Whether that is "good or bad" I'll leave to the reader. What that does however is level the playing field when it comes to streaming. How we each individually handle this homogenious supply of media is what ultimately differentiates what we hear. 

Barring obvious impediments like a noisy switch in the chain or other such physical issues, the stream will be exactly the same. Where it begins to differ is in how each consumer, us, handles it. Be it hard wiring directly from a cable modem or using wifi or perhaps fiber, the changes start there. Now add in the infinite combinations of streamers, DACs, preamps, amps, integrateds, speakers, heaphones, room treatments and dare I say it, cables, and we get what we get.

This is analogous to playing two identical LPs on two different turntables with different cartriges... Think about it.

To me the beauty of this avocation of ours is we can each tailor the sound until we get what we find most satisfying according to our tastes and budget. And there are limitless, space and budget constraints aside, possibilities to try.

And again, as always, I say...

Happy listening.

I do not understand your post and believe your conclusion false.  You have attempted to use syllogistic deductive reasoning.  Let me attempt to explain where this fails.  Please forgive in advance my philosophical pontification for I am a product of my Jesuit Fordham University education with its mandatory philosophy/theology core for a BS degree.  

Your major premise is that digital systems transmit and process nothing less and nothing more than packets packets of ones and zeroes .  You seek agreement.  We all can agree by deductive reasoning this is correct.  

Your minor premise is that these digital packets successfully travel thousands of miles through AWS' digital sewer, only to arrive in our homes completely unscathed ones and zeroes.  Facts prove this premise false.  The transmission of digital data over the WWW introduces a number of errors that cause distortion including, without limitation:

1. Jitter, the distortion we are all most familiar with. ​​​​​​
2. Transmission impairments: signal distortion, attenuation
3. Noise:  From EMI which includes RFI, introduced during transmission. A 

Your syllogistic conclusion is that therefore, this demonstrates that digital transmission protocols just work flawlessly .   Based on the data, this is false. If the protocols were flawless the errors causing distortion would not be present. Removing these errors is feasible but not practical due to cost.  

The correct conclusion by deductive reasoning is that the design of the transmission protocol and systems are adequate because even though errors, are introduced, these errors can be adequately corrected or removed  during processing and conversion of the digital stream to an analog signal.by the design of the DAC.  This seems to be the future discussion you indicated we should progress to.  Good sound quality goes even further than the processing of the ones and zeros to an analog signal.  The design of the DAC’s analog output stage is the most critical subsystem that impacts sound quality.  
 
 

So much misunderstanding on how networking and computing work. 

AWS/Cloud = some one else computer

All cloud platforms are just server farms that you pay to use. There are several tiers and quality. You can even pay AWS for a specific server that is all yours not shared. 

Networking can be very complex, go through several conversions. Anything sent from the East coast to the West coast is converted to optical, will stay that way till the last couple hops. Sadly it will go through the optical/coax conversion a few times before getting to your house. 

There is network jitter that gets sorted through packet headers. Each packet has a lot of info in it that is not the music 1/0's. Packets come out of time, sequence, in short burst. You do not get a dedicated stream of a song, you get a lot of small burst of data, that the DAC will piece into a song. There is built in error correction, and it's a send/receive/send service. Google TCP/IP packet protocols. 

Never in my engineering life, has any networking "noise" caused any computing issue. Servers all use clean power, and they try to separate the power from the data, but it's not always possible. They always use the provided power cords that go into rack long power strips. 

Think years of analog audio with all the rules has bleed over to digital, some of is the same, but a lot of it is garbage. Packets do not contain any noise, cat cables do not carry noise. Think most of the issues is poor consumer network components, poor component placement, DAC's that introduce noise in the D/A conversion. 

@mswale well audiofoolia is filled with people who talk like they're authorities on things but just learned some terms from a forum some years back and are regurgitating it every year till they believe they know more than people who actually work in those fields. That is how you get people confidently saying bull and thinking they're having some intellectual showdown. It's exhausting 

@mswale, I agree with you.

@jsalerno277  you wrote:

Your minor premise is that these digital packets successfully travel thousands of miles through AWS’ digital sewer, only to arrive in our homes completely unscathed ones and zeroes.  Facts prove this premise false.  The transmission of digital data over the WWW introduces a number of errors that cause distortion including, without limitation:

1. Jitter, the distortion we are all most familiar with. ​​​​​​
2. Transmission impairments: signal distortion, attenuation
3. Noise:  From EMI which includes RFI, introduced during transmission.

Your statement is incorrect.  The 3 bullet points impact the "signal" at the digital to analog stage.  Not during the digital to digital transmission.

I’m a computer/network/server guy with over 40 years experience in the field.  I was working with networking systems when "ethernet" was still using coax cable and what we call the Internet (i.e. World Wide Web) didn’t even exist yet.

All network transmission protocols, such as TCPIP, Netbios, etc., whether through the Internet, on a corporate LAN, or on your residential WLAN/LAN, have safeguards built in.  They are designed to insure that the data transmitted and received at either end is correct, bit by bit.  If there is any descripancy, it will request that the data packet be resent over and over again, until it is right.  Even a CD player has safeguards to guard against read errors, it’s called oversampling.  (Something nobody even thinks about anymore since it is so reliable.)

And think about it for a minute.  If the data stream is even a little bit wrong, even one bit of data flipped from a 0 to a 1, it would cause corruption that could be a financial transaction to be wrong, or a database to contain the wrong information, or a music file to be corrupted.  And once the data has been digitized, the network transmission/receipt doesn’t differentiate between the type of data (i.e financial, video, scientific, or even music), it is just a string of 0 and 1’s.  That is the beauty of digital transmission.  What is sent is what is received.  And you should be thankful that is correct, otherwise you might find the decimal place on an online credit card transaction to be one place to the right of where it should be.

Jitter, EMI noise, data buffers running dry do to slowness, etc. don’t affect the correctness of the digital data. They effect the ability of the D to A processor and software to convert it back into an analog output.

 

 

 

I am not a networking expert, but when you request a set of data from a provider, you can't receive "noise". You can't receive anything different than what was packaged and sent. You must receive what the provider sent to the last bit. Nothing will be added removed. This "noise" stuff is pure imaginary BS.

@jeffbij I never said sequence of ones and zeros were corrupted.  I said the signal is has errors including jitter, transmission impairments, and EMI.  None of these involve a corrupted sequence, additional or absent digits or sequences.   We are arguing the over semantics regarding the use of the term unscathed.   It is unscathed with regard to the accuracy of the digital sequencing based on the TCPIP protocol but scathed in its timing and signal quality.  

"Timing and signal quality" the go to for the forum expert.

 

Jesus you lot need to stop

I can't wait until someone comes up with a teleporter that guarantees a bit perfect transfer of someone and watch everyone fight to be the first Brundlefly. 

Carry on. 

All the best,
Nonoise

"I said the signal is has errors" - it doesn't.

"scathed in its timing and signal quality" - that happens after the packages arrived to streamer. Imagine it like a train station. All the containers arrived, numbered and "unscathed" with every single little package in them. 

When the streamer sends stuff to the DAC, maybe it does a lousy job with the signal.

Here's Gemini's explanation of how proprietary software can affect streamer output. It's a little more complicated than 1s and 0s. 

Here is a more technically detailed explanation of how proprietary software in digital streamers can influence the digital output and, consequently, music reproduction.

1. Advanced Jitter Mitigation Strategies:

Adaptive Clocking Algorithms: Proprietary software can implement sophisticated adaptive clocking algorithms. These algorithms continuously analyze the incoming digital audio stream and dynamically adjust the output clock frequency to minimize jitter introduced by the source, network, or the streamer's internal processing. This can involve phase-locked loops (PLLs) or other frequency synthesis techniques controlled by software to provide a more stable and accurate timing reference for the DAC. Reduced jitter translates to improved transient response, clearer stereo imaging (due to more precise timing of left and right channel information), and a less "smeared" or "grainy" sonic texture.

Packet Jitter Compensation: In network streaming scenarios (e.g., Ethernet, Wi-Fi), audio data is transmitted in packets. Variations in the arrival time of these packets (packet jitter) can lead to timing inconsistencies at the DAC. Proprietary software can employ advanced buffering and re-clocking mechanisms to smooth out these arrival time variations, ensuring a more consistent and stable data stream reaches the DAC. This can result in a more stable and less fatiguing listening experience, particularly with high-resolution audio.

2. Optimized Data Path and Noise Management:

Kernel-Level Optimizations: The operating system kernel and device drivers within the streamer's software stack play a crucial role in data flow. Proprietary software can involve custom kernel configurations and highly optimized drivers specifically tailored for audio processing. This can minimize latency, reduce CPU overhead, and ensure a more direct and less noisy data path to the digital output interface (e.g., USB, S/PDIF, AES/EBU). A cleaner data path reduces the potential for digital noise to contaminate the audio signal, leading to a lower noise floor and better dynamic range in the reproduced music. Subtle details and nuances in the recording become more apparent.

Resource Prioritization and Isolation: Real-time operating system (RTOS) principles or carefully managed process prioritization within the streamer's software can ensure that audio-related tasks receive preferential treatment in terms of CPU cycles and memory access. This can prevent other system processes from introducing timing variations or noise into the audio stream. Furthermore, software can manage power states of various hardware components to minimize electromagnetic interference (EMI) that could potentially couple into the audio circuitry.

3. Format-Specific Processing and Output Stage Control:

Optimized Decoding and Rendering Pipelines: Proprietary software can incorporate highly optimized decoding libraries for various audio codecs (e.g., FLAC, ALAC, DSD). These libraries can be fine-tuned for the specific hardware architecture of the streamer, potentially leading to lower processing overhead and more accurate data extraction. For DSD playback, for instance, proprietary software might implement specific DoP (DSD over PCM) or native DSD output methods that are optimized for the connected DAC, potentially affecting the sonic characteristics of DSD reproduction (e.g., perceived smoothness or detail).

Digital Output Stage Parameter Control: In some integrated streamer-DAC solutions or through proprietary communication protocols, the software might offer control over parameters of the digital output stage. This could include adjustments to the output voltage swing, impedance matching, or even dither algorithms applied to the digital signal before it reaches the DAC. These parameters can subtly influence the signal-to-noise ratio and the overall sonic presentation.

4. Error Detection and Correction:

Robust Data Integrity Checks: While less common for real-time streaming, proprietary software might implement advanced error detection and correction mechanisms, particularly for locally stored files or during network transfers. This can help ensure the integrity of the digital audio data and prevent subtle artifacts or dropouts caused by data corruption.

Impact on Music Reproduction:

The cumulative effect of these software-driven optimizations can manifest in several aspects of music reproduction:

Clarity and Detail: Reduced jitter and noise contribute to a clearer and more transparent sound, allowing for the retrieval of finer details and nuances in the recording.

Imaging and Soundstage: Precise timing and minimal crosstalk (often influenced by noise) lead to more accurate placement of instruments and vocals within the stereo image, creating a more holographic and immersive soundstage.

Transient Response: Accurate clocking and efficient data handling result in faster and more precise reproduction of percussive sounds and the attack of musical notes, contributing to a more dynamic and engaging listening experience.

Timbral Accuracy: By minimizing distortions and noise, the unique tonal characteristics of instruments and voices are reproduced more faithfully.

Overall Coherence and Musicality: When all these factors are optimized, the music tends to sound more coherent, natural, and emotionally engaging.

It's important to reiterate that the audibility of these software-driven differences can be subjective and highly dependent on the quality of the entire audio system, the listener's sensitivity, and the specific implementation of the proprietary software. However, from an engineering perspective, well-designed software can indeed play a significant role in optimizing the digital audio output of a streamer and, consequently, the quality of music reproduction.

 Variations in the arrival time of these packets (packet jitter) can lead to timing inconsistencies at the DAC

How? That's the streamer's job. It doesn't matter when the packets arrive if they are not late and are buffered. 

The analog output sections in DACS have a huge effect on the final sound quality of the digital sources. The quality of the transformers & other parts used as well as the circuit board’s & physical candy’s including their feet & isolation capabilities all can have a substantial effect on the final sound quality . This is all after the 1’s & 0’s have arrived. 

I was trying to make my original post both polite and sensitive to various points of view, but it seems I mostly tripped over my own feet.

My goal, or wish if you will, would be that folks who haven’t yet had the opportunity to educate themselves on the fundamentals of digital audio do so, so as to know what is possible vs what isn’t, and what makes sense vs what doesn’t, instead of slapping long-held analog-related beliefs on digital where they don’t belong.

I think it is emblematic of the problem when a clearly intelligent and learned individual accepts and propagates, doubtlessly in good faith, falsehoods about digital within this community and more importantly for themselves, those beliefs may lead them to make unnecessary and / or wasteful purchases.

A lot of folks seem to confuse digital files (made of ones and zeroes) with digital signal (the analog waveform representations of said ones and zeroes on transmission lines) and undesirable (but analog) noise that might travel along over said transmission lines.

Looks like a number of folks agree that the digital audio file that "lands" in your streamer is an exact, bit-perfect copy of the file Qobuz sent you, and of the file coming out of your CD or SACD of the same, assuming resolutions match and they originate from the same master.

In other words: Despite the horrors it traversed through AWS facilities, your digital audio file has suffered absolutely zero degradation or ill effect whatsoever on its journey to your home, explaining why audiophiles largely consider streaming equal in sound quality to traditional digital sources such as the aforementioned CD/SACD, local audio files on a NAS, or DAT transports if you’re into that.

Now, how would Ethernet gear located in the last 10 or 20 feet (aka your home) of that file’s 3000-mile journey somehow manage to compromise it where AWS itself failed?

Why would a simple $18 Monoprice Ethernet switch affect a digital audio file unaffected by a trip through hundreds of super-noisy industrial-grade switches...?

What can reasonably be hoped to be achieved by swapping in a $700 "audiophile" switch, all power supplies being equal?

If that $700 switch sounds better to your ears, I respect that, and I would prefer all the stuff about confirmation bias, sunk-cost fallacy, misery-loves-company, etc. be left out of this thread. It would be really interesting, however, to understand how a device that does nothing but send network packets on their way can favorably impact sound quality.

 hundreds of AWS’s super-noisy industrial-grade switches

I am curious what you mean by this?

respectfully, you can't draw correct conclusions from incorrect facts. I don't understand the point of this thread; I guess I am the exception and I will just stay away from commenting.

two issues might influence how your DAC translates everything back to analog.

Jitter coming from the streamer into the DAC. Yes, the file in the streamer is bit perfect. But the last meter might add jitter to which the DAC might be sensitive.

b) Common noise from the last meter might affect the DAC. 

 

Why can’t we just be happy that we get high quality music files from an almost unlimited library delivered intact, so that we can use whatever streamer and DAC sounds best to us?

Perhaps video is a good analogy…

We all get the same data from Apple TV but an OLED monitor coupled with a nice AVR and speakers blows a cheap LCD/LED tv and a sound bar out of the water,

Isn’t it that simple. Take the same source file and reproduce it with crap, good or great equipment and get a different result?

@gano 

Data center equipment is selected for high throughput, low latency and other factors including manageability and cost. Low noise isn’t one of them, and reasonably so since noise has no effect on digital data transmission. As a result switching mode power supplies and cooling fans are the norm, so these are noisy environments.

 

respectfully, you can’t draw correct conclusions from incorrect facts.

That’s generally true, but I’m not sure what you mean in this context?

@macg19 

I would be happy with that, personally.

@devinplombier - I usually stay out of these conversations because they always seem to go sideways and inevitably lose the point of the original post.  But today I have stepped into the fray....

So, here is my take on things...

I agree with your overriding idea for the post.  The topic is full of assumptions, misconceptions and lack of understanding.  Even after my 40 years experience in computers, networking, servers, and software in multinational manufacturing companies, I’m still guilty of them at times.

Looks like a number of folks agree that the digital audio file that "lands" in your streamer is an exact, bit-perfect copy of the file Qobuz sent you, and of the file coming out of your CD or SACD of the same, assuming resolutions match and they originate from the same master.

Correct.  Digital files, whether complete files or data being streamed should always match between source and destination.  If it doesn’t then the data is corrupted and dies.  Files are unusable and streaming data packets are unable to be converted to an analog signal.

A lot of folks seem to confuse digital files (made of ones and zeroes) with digital signal (the analog waveform representations of said ones and zeroes on transmission lines) and undesirable (but analog) noise that might travel along over said transmission lines.

You are correct about the confusion.  So, let’s discuss the noise that travels over transmission lines.  There is noise, and bottle necks, and delays in transmissions, and even packets taking completely different paths across the Internet to get to the destination.  (Welcome to TCPIP and the original design of the ARPANET, the core of the Internet and many wide area (WLAN) modern networks.)

So, what is the affect of all the general "noise".  Typically it only will cause delays in packet transmission and receipt.  The protocols in place are designed to assure the data comes through "unscathed" (and yes, I’m using that word on purpose), even it if requires a lot of time, possibly to the point of timing out and the connection getting dropped.  And there is one of the rubs, speed of data flow.  More on that in a minute.  But first, it needs to be noted that the "noise" present across any transmission/receiver leg ends at that receiving hardware.  This would include the legs from the original server to network switch, network switch to firewall, firewall to router, router to your ISP, your ISP to home modem, home modem to network switch, or network switch to streamer.  Why is this true? It is because the data always travels in packets, not in a start to finish steady stream like an analog signal.  So each leg starts off with a complete packet and that packet is clean and isolated from the previous leg.

Now back to the rub of the data flow speed.  This is where somethings can go wrong. In the case of a sequencial "streaming" of data, whether being video or audio, eventially the data packets need to be sequenced and converted to a continous analog signal. (BTW, I’m trying to keep this very simple...)  And here is where time comes into play.  If there are delays in receipt due to noise or packets coming into the buffer out of order, the data won’t stay ahead of the requests from the processor.  And thus you get Jitter.  

Now, how would Ethernet gear located in the last 10 or 20 feet (aka your home) of that file’s 3000-mile journey somehow manage to compromise it where AWS itself failed?
Why would a simple $18 Monoprice Ethernet switch affect a digital audio file unaffected by a trip through hundreds of super-noisy industrial-grade switches...?

One misconception in the statement above.  "super-noisy industrial grade switches".  These industrial grade switches are designed to route the data packets in high volumes and with minimal requests for packet resends.  The onboard software control is significant and monitored (i.e. level 3 managed switches).  They have large data transfer backplanes and these days are running at 10 GB upwards of 800 GB ethernet speeds.  Your home networking equipment typically maxes out a 1 GB.  Any noise inside the circuitry is negligible in this discussion.

Then, to the question of how can the last 10 or 20 feet in you house have an impact.  First, the hardware is cheap and relatively slow.  Enterprise level network switches, like what AWS is using, can run up into the $10K plus range.  Routers and firewalls used by corporations and ISP’s in the same range, or even higher.  Your home modem and network switches, a couple of hundred bucks.  In fact, they are actually noiser than Enterprise level equipment.  Second, power supplies.  Typically, home equipment use power supplies that are barely enough to run the equipment.  Start loading it down with constant data flows, and they start to fade out, speeds drop, induced noise goes up, packet resend requests rise and things go boom on the receiving end.  Third, shielding.  Enterprise level equipment is usually in metal cabinets.  Power supplies are shielded internally.  Processors and buffer memory as well.  Most home modems/routers/ and switches, not so much.

What can reasonably be hoped to be achieved by swapping in a $700 "audiophile" switch, all power supplies being equal?

Honestly, power supplies outstanding, I have no idea what some of these companies do to create an "audiophile" switch.  I have seen a few that have been opened or completely torn down, and other than a different paint job, they seem to be typical home equipment.  Just slap a different power supply in, call in audiophile, and charge a $400 markup.  I don’t know.  All I know is that my Enterprise level Cisco switch in my basement will out perform it.

Thanks if you read this all the way though.  I know I written a a novel.  Time for bed.

- Jeff

+1 @jeffbij 

It’s wearisome to answer Ethernet experts with their thinking that their knowledge/profession make them totally knowledgeable in digital High-end audio. Their  “I’m right until you prove me wrong” requires much effort to educate.  Then another one comes along.  

The digital data rides on an analog signal that can pick up noise.

High-end computing ≠ High-end audio where we care how it “sounds”

jeffbij

I have no idea what some of these companies do to create an "audiophile" switch.  I have seen a few ... All I know is that my Enterprise level Cisco switch in my basement will out perform it.

What audiophile switches have you tried?

So am I misconstruing here that a high end battery backed power supply for the whole hi-fi system should be conducive to a cleaner signal even from the packeted network servers?

@kennyc 

I'm confused. You give jeffbij a +1, then you apparently trash his post.

Did you mean to give the +1 to another poster?

Since the concept of “noise” in a data stream is an unknown value to me, and I took  machine and assembly language classes eons ago, I asked ChatGTP: what is noise in a data stream of 1’s and 0’s?

Noise in a data stream of 1’s and 0’s refers to unwanted alterations or interference that causes the bits (1s and 0s) to be received incorrectly compared to how they were transmitted. More precisely:

 

• In digital communication, noise can flip a 1 to a 0 or a 0 to a 1, leading to bit errors.
• The source of noise can be electrical interference, thermal fluctuations, crosstalk, radio frequency interference (RFI), or signal degradation over distance.
• Unlike analog noise (which adds distortion), digital noise usually results in discrete errors—incorrect bits—not gradual degradation.

Example:

If a clean digital stream is:

10110010

And due to noise it is received as:

10111010

The 5th bit has been flipped from 0 to 1—this is a direct result of noise.

Summary:

Noise in a digital data stream is any interference that causes incorrect or unintended changes to the transmitted binary data, resulting in bit errors.

 

Would you like to know how systems correct for or detect such errors (e.g., using error-correcting codes)?

@jsalerno277 

Please forgive in advance my philosophical pontification

It is more than forgiven, it is appreciated!

While your response is factually incorrect as noted by others, it is thoughtful and articulate and a pleasure to read 🙏

 

 

That response lead to the next question. (ChatGTP does lie) If that is true then how are electronic banking transactions conducted error free?

Excellent question—electronic banking transactions aren’t inherently error-free, but they appear error-free to users because of sophisticated error detection, correction, and redundancy mechanisms built into the system. Here’s how they ensure high reliability despite the presence of noise:

 

✅ 1.

Error Detection and Correction

 

 

• Checksums and Cyclic Redundancy Checks (CRC): Each data packet includes extra bits derived from the content. The receiving system recalculates the checksum and compares it. If it doesn’t match, the data is known to be corrupted.
• Forward Error Correction (FEC): Techniques like Hamming codes or Reed-Solomon codes not only detect but automatically correct certain errors on the fly.

 

 

 

✅ 2.

Redundant Transmission

 

 

• Important messages may be retransmitted if an error is detected.
• Protocols like TCP (Transmission Control Protocol) ensure that data arrives completely and correctly by:
  • Acknowledging each packet.
  • Resending lost or corrupted packets.
  • Reordering out-of-sequence packets.
•  

 

 

✅ 3.

Secure Protocols

 

 

• Financial data is sent over encrypted and authenticated channels (e.g., using TLS/SSL) that have built-in integrity checks. Any tampering or bit error will be detected as part of the decryption and hash verification process.

 

 

✅ 4.

Database-Level Safeguards

 

 

• Once a transaction reaches the bank, it’s verified again before being committed.
• Transactions are logged and backed up with atomic operations: they either fully succeed or not at all—never partially.
• Redundancy in server systems ensures high availability and fault tolerance.

 

 

 

✅ 5.

Physical Infrastructure

 

 

• Banking data travels over high-quality, shielded infrastructure (fiber optics, secure server farms), minimizing noise and errors from the start.
• Enterprise-grade routers, switches, and network interfaces have built-in error-checking hardware.

 

 

 

 

 

In Summary:

Electronic banking appears error-free because of layered safeguards:

 

• Detect and fix errors early.
• Ensure correct delivery through protocols.
• Validate and log every transaction at the application and database levels.

@cleeds -  I haven't done much with switches labeled as "audiophile" grade.  So, as I indicated, I don't know what they have all done inside other than changing out the power supply.  Some may be completely reengineered and use top notch jacks, power supplies, etc.  I honestly don't know.  Did I overstate my home network with Enterprise level Cisco equipment, yeah, maybe.  It was late and I was tired when I wrote it.

My home network is running on Cisco C3850 layer 3 switches (over $5K new) setup with VLANs and QoS (quality of service) to segment off my streamers from the rest of the network (i.e. desktop and laptop computers, WiFi access point, Amazon Echo devices, printer, etc.)  My router is also a Cisco Enterprise level appliance.  I picked up the equipment at an auction of a local failed business.  Unfortunately, the cable modem is a typical Motorola that is supported by my local ISP.

The only "audiophile" switch I have actually compared against my setup was an English Electric 8 that a friend purchased from Upscale Audio.  With a "stock" wallwart power supply, and pushing the data volume way up on multiple ports, it was not matching my Cisco setup.  According to management/diagnostic software, it was dropping packets at a much higher rate than I would have expected.  Sound wise, it was ok. Once I changed out to the "better" power supply that came with it, things improved dramatically, both in network performance and sound quality.  But still it did not perform better than the Cisco setup.  If I were to make a guess as to why, I would say the larger and faster backplane of the Cisco and segmenting the ports into VLANs was creating a more stable data stream to my main streamer(s), even when loading it down and taxing it's capacity.  And thus a much lower level of jitter and smoother processing.

I referenced that I have seen pictures of the internals of other audiophile switches.  I remember one that turned out to just be a Netgear GS series 8 port switch in a different colored case with a linear power supply.  Another was a DLink that was supposed to have been "modified" but only had some stuff glued to the top of some caps and chips and was marked up 500%.  And then another that was just a  Linksys that was repainted and sold with a SBooster power supply for high dollars.  

sophisticated error detection, correction, and redundancy mechanisms built into the system. Here’s how they ensure high reliability despite the presence of noise

This, and files can further be checksummed or hashed to confirm that the received copy is identical in all aspects to the sent copy.

Meanwhile, those AI are getting pretty good :)

@hbarrel -

they appear error-free to users because of sophisticated error detection, correction, and redundancy mechanisms built into the system. Here’s how they ensure high reliability despite the presence of noise...

Exactly!  This is the key to any digital network and why it actually works, whether it is a financial transaction, email, video feed, or music.  What you transmit in the beginning is what you get at the end. 

@devinplombier  Thank you. However, as I explained in a later post, I believe I was unclear and misunderstood, for I never said the streaming ITCP protocol assure transmission of anything less than bit perfect files.  I said it is not “unscathed” from an audiophile perspective in that the transmission to conversion process introduces timing errors, transmission impairments, and EMI noise. @kennyc stated it more eloquently than I … The digital data rides on an analog signal that can pick up noise.  High-end computing ≠ High-end audio where we care how it “sounds”.   Therefore, I apologize if my conclusion was unclear.  Restated, is is that audio files are transmitted bit perfect but not unscathed from factors degrade sound quality and it is the design intent of the DAC to correct or limit these factors to improve sound quality.  I also concluded it is not the DAC conversion stage but the analogue output stage that is critical to sound quality. 

Audiophile switch sellers purchase off-the-shelf switches, ditch the noisy switching mode power supply (SMPS) that came with it, repackage the switch with a small linear power supply (LPS), and sell it at a huge markup.

The LPS will in fact yield a significant noise level reduction. In other words, the product they're selling actually performs pretty well.

The only issue then is that they're selling, say, $80 worth of goods for $500, with no other expense than maintaining a website chockfull of audiophile puffery.

In a way, we can look at these people as arbitragers, leveraging audiophiles' lack of interest in or familiarity with basic network equipment.

All the more the reason to be a well-informed community - it's good for our wallets! 😃

 

I guess parts is parts and pieces is pieces and it don’t matter in what order they go cause it’s all gonna sound the same.

Really?

jeffbij

... one that turned out to just be a Netgear GS series 8 port switch in a different colored case with a linear power supply. 

Which one was that?

Another was a DLink that was supposed to have been "modified" but only had some stuff glued to the top of some caps and chips and was marked up 500%.  

Which one was that?

And then another that was just a Linksys that was repainted and sold with a SBooster power supply for high dollars.  

Which one was that?