RETRO-AUTOPSY: Museatex Melior BS-1 Bitstream S/PDIF DAC (circa 1995?). A few words about external clocks for audiophiles. And a speaker cable blind test?

The company Museatex was formed around 1990 by Ed Meitner and John Wright based in Calgary, Alberta, Canada. Over the years, the brand was assumed under A/D/S which eventually closed in 2001. There's still a web page for information on Museatex products here. Ed Meitner has moved on these days to EMM Labs since 1998 and given his work with SACD, his name has been associated with "bitstream" type technologies since (some more info/video).

By the end of the 1980's, 1-bit Philips "Bitstream" PDM DAC chips started to show up in the market with the Philips SAA 7321 chip as one of the 1st generation devices (see Stereophile reporting back in 1989). Some of these chips were incorporated in CD players like the Meridian 208 that came out in early 1990, well-reviewed by Paul Miller in High Fidelity.

By 1991, the "second generation" Philips SAA 7350 "bitstream" DAC became available, capable of taking up to 20-bit PCM (from 16-53kHz sample rate) and upsampling to 1-bit SDM applying 3rd order noise shaping (some more history here). It is this DAC chip that's at the heart of the Museatex Melior Bitstream DAC, I believe first released in 1992. Here are the specs from the company.

The exact history of this particular unit I had access to has been shrouded in the sands of time, but was probably purchased around 1995. The original suggested price on one of these was US$899 which would be about equivalent to over US$1500 in 2023. Even to this day, I've seen comments from audiophiles who have a special affinity to the sound of this vintage DAC. Claims to fame included anti-jitter input circuitry (supposedly reducing "glare and harshness"), a custom digital filter allowing for "more accurate signal conversion", and high quality power supply with line noise filtering.

Thanks again to my friend linnrd for digging this unit out from his audio device archives. While externally it looks to be in very good shape, unfortunately, it didn't quite power up normally for me which sadly resulted in this article being more of an "autopsy" rather than actual measurements. I guess having a look inside is still better than nothing for historical documentation if nothing else.

REVIEW/MEASUREMENTS: AOSHIDA A7 Class D TI TPA3255 amplifier. Good sound. Good power. Economical.

Above, you see the small AOSHIDA A7 Class D amplifier which we'll go in depth with in this post. It's inexpensive and can be purchased for less than US$150 these days. This design is also sold as the Douk Audio H7 with a different color scheme, presumably the innards must be very similar if not identical. I preferred the look of the black AOSHIDA version with orange-ringed VU meter. I purchased this amplifier through the usual retail channels.

Over the years, it has been good to see the evolution of Class D designs and the inexpensive "chip" amplifiers. Internally, this is based on the TI TPA3255 "PurePath" chip (released in 2016) rated to provide up to 315Wpc into 4Ω stereo but at 10% THD when provided with adequate power (data sheet max is 53.5V). Notice the italics to emphasize that these numbers must be put into context. For audiophiles who want lower distortion in their amps (like <1% THD), we would be looking at much more conservative power figures than that 300+W being promoted for these amps.

(The chip also has a mono configuration that's spec'ed at up to 600W into 2Ω which would not apply for this review.)

The Audiophile Wisdom of ChatGPT (Feb 13, 2023 Version): Learnings from an artificial intellect on an esoteric hobby. (And on creativity?)

I'm sure none of us these days have escaped news about ChatGPT from OpenAI. Articles have been ubiquitous covering the implications of what this "chatbot" is able to do. No doubt, there will be deep implications stemming from this technology already being debated through the halls of academia on how it will affect everything from education, to work, to legal ramifications. As with any likely transformative technology, there will be promise and fear.

Already, I've seen many articles out there including in our little corner of the universe with Stereophile's "As We See It" in February referencing ChatGPT.

As you're likely aware, ChatGPT achieves its remarkable abilities based on Generative Pre-trained Transformer (GPT-3.5) "large language model", a sophisticated "self-supervised" general AI model based on >175B parameters combed through 570GB of data as text off the Internet, books, and Wikipedia. Yes, human feedback is part of the training process and data continues to be gathered from users to improve the model. At the time of this article, the openly available online ChatGPT has been trained with data up until September 2021 as can be seen here:

Arch: Who won the Superbowl in 2023?

ChatGPT: I'm sorry, but I am not capable of predicting future events as I am a machine learning model trained on historical data. As of my knowledge cutoff date, which is in September 2021, the most recent Super Bowl was Super Bowl LVII and it has not happened yet. It is scheduled to take place on February 5, 2023, so we won't know the winner until the game is played.

Given the level of knowledge ChatGPT has access to, I wondered how would it perform currently in March 2023 if asked about broad audiophile topics. I think this is interesting because the answers it gives must be an integration of all those hundreds of gigabytes of texts fed into the system. What does all that information teach the machine about the current understanding of audiophile topics? Are the answers reasonable, and relatively free of errors? Do the answers show "common sense" or even a level of "wisdom" one might wish to receive when talking to a knowledgeable audiophile friend requesting advice?

Let's dive into a Q&A discussion and see what ChatGPT can tell us about this niche audiophile hobby... (Grab a warm beverage by the fireside friends, we go deep and broad.)

Internet Blind Test: 24-Bit vs. Dithered 16-Bit Part Deux - Daft Punk Edition! And the honest desire to seek truth as audiophiles.

BTW: 1.5kHz sine waveform, -65dBFS. 16-bits on the left, 24-bits on the right.

It's amazing how time flies. Nine years ago - 2014 - at a time when hi-res audio downloads were being promoted as the "next best thing" for audiophiles, we ran a 24-bit vs. 16-bit blind listening test on this blog. I'll leave you to examine the results.

Since then, electronics like DACs have advanced quite significantly. Compared to 2014, these days, high quality asynchronous USB DACs have become ubiquitous. Jitter is basically a non-issue now. Inexpensive audio streamers like Raspberry Pi devices can be easily put together. We can all play music with wide selections of digital filters without great difficulty. Very high quality headphone amps and phenomenal headphones have become commonplace with a growing "head-fi" community.

Recently, I had some fun on this Steve Hoffman Forums thread engaging in the discussion about 16-bit vs. 24-bit; the topic of audibility again came up. As usual, things can get pretty contentious among audiophiles and since it has been awhile and perhaps some of you did not have the opportunity to participate in 2014, let's do a blind test again for those wanting to listen to 24-bit vs. 16-bit audio.

Let's use popular music rather than the more esoteric 24-bit 2L classical recordings last time - let's try some "classic" Daft Punk. ;-)

RETRO-MEASURE: Dynaco A-35 speakers (1972-1976). Technological maturity and audio. Comparison of the qSpin predicted room response vs. in-room measurement.

Audiophilia has a rich history filled with many products and ideas over the decades. Many of the "vintage" products can still be found these days on the used market and many carry with them an interesting story or might have developed "cult followings". I find it interesting examining these older "retro" products to help provide context when we think about the sound quality we have these days.

Some companies like the one we're looking at today - Dynaco - founded by David Hafler and Ed Laurent back in the mid-50's are well known. The company's products were popular through the '60-'70s including a foray into quad-channels. The company eventually got acquired and the brand decommissioned by 1980.

Dynaco was known for their amplifiers and "Dynakit"s they sold in the emerging hi-fi market back in the day to audio enthusiasts. Along the way, by 1969, they got into the speaker market with their "A-Series" line of products including the very popular A-25 (>1M sold worldwide according to Ed Laurent) and the speaker we'll be examining today - the less popular, larger Dynaco A-35 sibling.

Thanks again to linnrd for digging up this pair of old speakers for me to examine from his gear archive. It looks like these have been very well taken care of over almost half a Century. Well, at least there's no need to "break in" these speakers. ;-)

SURVEY: What audio playback system and/or streaming music service are you using in 2023?

Hey there gals and guys. I've been busy over the last while getting some things at work going, so this means it's time for a survey to hear from you ;-).

It's always good to know what audio lovers are doing out there and this could of course help me look at interesting topics to examine in the future. The last time I did this was back in 2019, looking at adoption of streaming services and lossy vs. lossless among the readership - much has changed since then!

I've seen various hobbyist poll results over the last while. A common question being asked these days is "Which digital streaming service is most popular?". This certainly makes sense given the growth of Internet streaming over the years, but much too simplistic! As an audiophile blogger, my interest isn't so much about which commercial service is "winning" since it really doesn't matter too much to most of us I think, and will fluctuate depending on where one lives and what services are available. Instead, audio enthusiasts these days have access to all kinds of ways to listen to music and choices to make including whether we like "spatial audio" as a recent feature.

In Archimago's Musings style ;-), let's go deeper and get a detailed survey going, collecting anonymous data on who you are, what you use mostly, and what kind of systems you enjoy in 2023 - not just what music service...

MEASUREMENTS: Intona 7055-C USB 3.0 SuperSpeed Isolator. And Darko & Lavorgna hear no difference with the Silent Angel ethernet switch. [Importance of open discussions.]

Over the last couple years, I've shown in my PC measurement system the benefit of using USB isolation to break ground loops when test devices are connected to the ADC. There was the ADuM4160 device which was limited to "Full Speed" (12Mbps). Then I posted on the Topping HS01 which operates at a fixed USB 2.0 "High Speed" (480Mbps).

Over the Christmas holidays, I got a hold of the Intona 7055-C USB Isolator which can run at USB 3.0 "SuperSpeed" (5Gbps), basically a pass-through device which provides galvanic isolation of the USB signal and ground lines, with the flexibility of being downward-compatible with 480Mbps (most important for USB audio), 12Mbps, and even Low Speed 1.5Mbps devices.

Although audiophiles have been talking about isolators like this for years used in home set-ups, they're really meant for industrial applications where devices with USB ports might be subjected to high-voltage surges and spikes. This "C" model is designed for protection up to a modest 1kV over 60 seconds. The more expensive 7055-D can handle up to 5kVrms over 60 seconds.

MUSINGS: On Michael Fremer's "How Best to Hear Patricia Barber's 'Clique!'" - selective hearing and more MQA nonsense. [Extended Edition!]

A little bit of dramatics for effect. ;-)

Like many audiophiles, I've been well aware of Patricia Barber's recordings over the years. Her discography of "reference"-sounding quality albums have already had decades of influence among hi-fi enthusiasts with increased exposure beginning in the 1990's (her first album was Split in 1989). Personally, I was introduced to her music with Café Blue released in 1994.

I think Barber is an interesting contrast to the other well-known female jazz vocalist we all know well - Diana Krall. Barber's material tends to be more original (less of the standards), more edgy, compared to Krall's accessibility and mainstream appeal.

Already, on this blog, I've mentioned the most recent album Clique! (2021, DR14 hi-res, DR13 MQA-CD) but we're not going to be mainly talking about the music on the album in this post. Rather, I want to explore the opinions and beliefs of Michael Fremer in his article "How Best to Hear Patricia Barber's Clique!" recently posted on Tracking Angle.

MEASUREMENTS: Knockoff "Kimber Kable" 12TC Speaker Cables. And do cable risers / lifters / elevators make a difference?

 

As I'm sure we're all aware, in the world of luxury goods, there will be fakes out there. Wandering the streets of basically any city these days, we'll run into all kinds of cheap "Gucci" and "Hermès" bags, fake "Rolex" and "Omega" watches, knock-off "Nike" sneakers, and counterfeit "Ray-Ban" sunglasses.

So too in the world of the audiophile. It's not hard these days to browse through "used" eBay listings or explore the copious products on Alibaba/AliExpress to find fake "High End Audio" products.

As you probably know, I'm not one to be impressed by most cable claims and believe that there's little value in a lot of what's being sold (collected articles here). Given the high prices for lengths of wire, is it any wonder then that some might want to capitalize on brand names to entice buyers?

A friend who knows I'm into audio stuff, "for fun", decided to get me the cables in the picture above from Singapore recently while on a business trip. The cables are more than likely made in China. As you can see, these are labeled as "Kimber Kable", with the same geometry and supposed build of 12TC speaker cables. He purchased them for <US$75 as a pair of 2.5m lengths.

[Back in 2015, I examined and had a listen to genuine Kimber 8TC.]

Home Network: Update on mixed 10 gigabit network, Roon stability & value? (And a quick look at Pi-Hole.)

Happy 2023, dear audiophiles!

While I typically publish articles like measurements of audio hardware, discuss albums (usually as part of reviews or examination of things like dynamic range), and offer critiques about extreme "High End" audiophilia, every once awhile I'll talk more generally about my computer hardware and local area network (LAN). I see the network stuff as part of a broader foundation of the modern digital audio system which simply has to work reliably and efficiently for digital streaming/computer audiophiles. Like other parts of the "perfectionist" audiophile system (like say the room which is often also neglected in audiophile hardware talk), this should be optimized for best performance such that those using it will not have to suffer from speed issues or dropouts. Sometimes it's easier said than done given potential interoperability nuances of the multitudes of network hardware!

Apart from silly "audiophile ethernet switches", or "audiophile ethernet cables", there's generally nothing specific to sell to audiophiles when it comes to home network hardware. As a result, it's atypical to see long articles at audiophile websites or in the magazines about this stuff despite the importance.

As a reminder, in my experience, unless we're dealing with faulty gear, "Bits Are Bits" when it comes to sound quality - that's just reality if you take the time to analyze the audio signal objectively or run some controlled listening trials. Despite all kinds of subjective voices/claims out there otherwise, high performance modern computer networks are simply not going to change the sound of audio playback so long as they're reliably "bit-perfect". After all these years, I find no reason to be concerned about ethernet cables, or switches transferring packet data around. Whether the data is of audio content or otherwise is irrelevant - the network doesn't care whether it's audio meant for the DAC or pixels aimed at the printer.

Digital data, given how it's packaged and transmitted, when corrupted will result in rather obvious audible anomalies if not corrected (like an error-prone USB cable). You will not hear subtle changes (like "more bass" or "better soundstage" or even more vaguely "improved presence") as some reviewers seem to promote when hyping nonsensical claims of what they supposedly "heard".

As We Hear It: Yet Another Christmas Playlist (2022) - Guest post by Allan Folz

Greetings and Merry Christmas Archimago and readers. For new readers, the Christmas playlist is a recent tradition (2020, 2021) at Archimago Musings that had as its genesis recognition that great dynamic range makes for great music, even if you didn't necessarily know it or weren't even looking for it.

It started way back in the 90's. I accumulated a small collection of Christmas CD's which sounded great. My wife and I never tired of listening to them between Thanksgiving and Christmas every year. Several years later I happened across this humble blog and learned about dynamic range, among a great many other things. When I started measuring some of the albums in my CD collection I noticed that all my favorites had pretty high dynamic ranges. Additionally, the albums I bought, only to be disappointed in them after I got them home and had a few listens had pretty low dynamic ranges. One year as Christmas approached I thought I'd test the theory against my Christmas albums. To my pleasant non-surprise I saw that they all scored respectably well on dynamic range. A couple years later it occurred to me to share my epiphany (heh) with Arch and the blog in a guest post. It was well received, so the next year I did another playlist, again with nod to dynamic range.

This year, I am going to break slightly with tradition and won't be overtly covering dynamic range. I trust that's been proven to everyone's satisfaction. Plus, these are albums I discovered from streaming services, and I don't actually know the dynamic ranges. Not to mention, streaming services today often fudge around with albums' loudness since the number one complaint from streaming listeners is loud songs coming after relatively quiet ones when they are listening to mix playlists. The dynamic range of the song you stream is often probably not the same as on the CD you would buy. [Ed: Indeed. Much depends on which mastering is on the streaming service!]

MUSINGS: On audio gear appearance and design. (A case of the HiFi Rose RA180 and Audio Jewelry.)

As work calms down into the holiday season, I thought it would be fun today to talk about what's obviously a subjective matter... Appearance.

Clearly, aesthetics are matters to be adjudicated "in the eye of the beholder". Although in these pages, I'm more curious about sound quality and using objective means to test and demonstrate the resolution of devices, appearances certainly do matter even if for me that's not the highest priority. Of course a good looking sound system is pleasing to the eye, improves the ambiance of one's room, might impress other audio friends, and there's always that "wife/spouse/partner acceptance factor" (let's just call this the traditional WAF). For marital harmony, it is only fair to receive feedback about one's system occupying a shared space. Whenever possible, I would highly recommend a dedicated room as the only way to go if you're desiring to be a hardcore, freedom-loving audiophile beyond "head-fi". ;-)

REVIEW: E1DA #9038D6K Dongle DAC / Headphone Amp (Part II): Headphone Amp Power, DSD, Subjective Impressions, AMPT & Perfectionistic Tweaking!

A great sounding music listening station! (Samsung Galaxy Tablet, Drop+HiFiMan HE-4XX, classic Jacky Cheung cantopop.)

Okay friends, today we continue with Part II of the discussion on E1DA's #9038D6K portable DAC/headphone amp. Please refer to Part I last time for the general overview of DAC performance which already tells us about the PCM resolution of the device. The data from last time shows that for the price and size, this unassuming dongle is one heck of an accurate, high-fidelity, high-resolution digital-analogue converter.

This time, let's move forward with exploring other areas not yet discussed. Specifically, let's focus on resolution when under headphone-like loads, look at DSD performance characteristics, have a listen to the DAC, and given that E1DA is known to be tweaker/DIY-friendly (including making devices like the Cosmos line), let's also talk about what I would consider more "extreme" tweaking for the perfectionist audiophiles!

REVIEW: E1DA #9038D6K Dongle DAC / Headphone Amp (Part I) - PCM DAC performance. And (potentially) higher dynamic range in Spatial Audio 2-channel fold-downs.

Little E1DA DAC to Sennheiser HD800 headphones via 1/4" adaptor... Looks ridiculous if walking around in public with this! But sounds great. ;-)

A few weeks back, I received a package from Ivan Khlyupin (IVX) of E1DA containing both the Cosmos Scaler and the device we'll be looking at today - the E1DA #9038D6K DAC / headphone amplifier.

This is the latest iteration of the #9038D models which feature 3.5mm single-ended output, to be distinguished from the #9038S models which are balanced devices with 2.5mm output jacks. And the "6K" refers to 6000μF (!) of power rail filtering (original #9038D has 4000μF).

As the name implies, internally, these DACs are based on the ESS ES9038Q2M low-power chips. They are capable of playing back PCM to 32/384 as well as up to DSD256. Over the last year or two, we've seen a proliferation of DACs based on this component and I would say that overall, the performance on these devices have in general been very good. Thanks to the low power consumption, we can now have mobile converters that perform at least to the resolution of many desktop DACs while being fully USB-powered.

To generate the amplified headphone output, op-amps used include the OPA1622 and OPA1602 based on the E1DA specs. To achieve very high resolution, internal components are advertised to be quality Susumu resistors, Murata C0G caps, Kyocera AVX tantalum caps, and connectors from Taiwan. In my discussions with Ivan, I know in the last while it has been slow for him to source some of these components and at times difficult to avoid fake parts out there!

"High End" Audiophile Science? On Milind N. Kunchur's hard-to-believe research articles.

It has been a busy week so let's keep this article somewhat shorter. ;-)

Beyond the typical audiophile magazines, websites, and videos, I think it's interesting once awhile to think about some of the research out there in the academic literature related to "audiophile" topics.

As I have said many times, I believe that typical 2-channel hi-fi audio is very much a "mature" science these days so on balance it's probably unlikely that understanding of core technologies should be too contentious. I know, some audiophiles and companies will protest this idea with the belief that human hearing somehow has much more potential and that we cannot measure all domains of auditory acuity as applied to our audio tech. As science-driven hobbyists, since we can perform blind tests and show that people have difficulty differentiating high bitrate MP3 from lossless, even relatively high distortions are difficult to hear, and hi-res audio is generally indistinguishable from 16/44.1 lossless (except for a few minor instances which can be statistically significant but practically not likely relevant for music listening), I think the onus of proof remains on those who make contentious or dramatic claims outside of the standard paradigm.