Okay I've just come across the new software by Nvidia and been playing with it on my live stream and it is incredible.

Then I thought it must improve speech recognition, and without doing much testing it seems to have made a huge difference!

Check out this video: https://youtu.be/Q-mETIjcIV0?t=536

I started it at the most extreme part.

Here is a link to the software and it helps if you do have an RTX card, but you don't need one.

It works with any microphone, it also gets rid of background noise in terrible YouTube videos.

Linked to the software: https://www.nvidia.com/en-us/geforce/guides/nvidia-rtx-voice-setup-guide/

Wow, it sure cuts out background white noise! And the video does a good job of explaining how to use it on non-RTX-card systems. Be sure to read the video description for a correction note.

-------------------------

Win10/11/x64, AMD Ryzen 7 3700X/3950X, 64/128GB RAM, Dragon 15.3, SP 7 Standard, SpeechStart, Office 365, KB 2017, Dragon Capture, Samson Meteor USB Desk Mic, Amazon YUWAKAYI headset, Klim and JUKSTG earbuds with microphones, excellent Sareville Wireless Mono Headset, 3 BenQ 2560x1440 monitors, Microsoft Sculpt Keyboard and Logitech G502 awesome gaming mouse.

The more I have been using this more amazing it is.

I can see this being built into the next version of Dragon NaturallySpeaking.

They would probably have to pay royalties to Nvidia. Slim chance of that happening.
Zig

I don't have an RTX card, but tried to install it with the workaround described in the YouTube video. Didn't work unfortunately, however I'm getting a new video card in the coming weeks so will try again. My help to cut out the noise of the kids fighting in the background when I'm trying to dictate.

Quite amazing! I have a Quadro T1000, do you think the software is compatible out of the box?

I wonder if it will help with the MS Word jumping cursors problem

-------------------------

Win 10 - DPI 15 - AT 8 pro + Andrea USB

this sounds interesting, i am in much need to have something remove background noise when using Dragon, but i am afraid to try it with this much information only. Woudl be happy if someone would write down instructions... and how do i know whether it will work on my computer or not?

With the suggested workaround, I was able to install the software, but I couldn't check the box at 'remove background noise', because that gave an error message 'unable to start microphone denoising', or something like that. So I assume there's no benefit for me to using this.

I have a recorded audio file with a lot of background noise.  I was wondering if there was some way I could use this software to clear that up using a virtual cable or something else by playing the audio file again and recording it with this NVidia RTX Voice filter on.  Is this possible and if yes how do I go about this.

We have experienced a lot of with this idea and driver in the past. Although you may eventually make the "trick" work with a few cards other than those from Nvidia, it will probably not work in most cases, neither be too legal to do so.

 

This is why we are currently exploring the possibility of integrating such a functionality in our Octopus USB Controller application and/or our TableMike and TravelMike microphones.

 

Let us know whether you may be eventually interested in such a development through this thread for us to allocate more resources and priority to it, since we are only focused in bringing to the Speech recognition market UNIQUE and value added solutions!

-------------------------

SpeechWare Team

 

 

 

Windows 7, Intel  i7, 8 GB, USB TravelMike or SpeechWare USB MultiAdapter with FlexyMike Dual Ear

I'd buy it right away !

-------------------------

Memory: 16GB Microphone Brand and Model: LFH 4000 & Flexy Mike  Operating System: win 10, latest update; Surface Book 2, Processor (CPU) Type & Speed: I7 8650 Soundcard Brand and Model: none Speech Software: Dragon Medical Practice Edition, french version: 4.2 Using KnowBrainer?:Yes

 

I recently took out my tablemike 6 in 1 from my microphone museum, since I did not try it again since I'm working with DMPE 4. I became very clear it's what gave me the best result of all I tried, in my context (home office, voice around, and prof office with a little echo because i'm alone in a gib room).

I'm trying to work with it with RTX voice enabled, with no RTX card and it adds a marginal benefit. with the price to pay of an added latency. If you were able to integrate the benefits without the latency (maybe having an RTX card would reduce it, but given the price of thos cards it's a costly bet), it would be a very good step

-------------------------

Memory: 16GB Microphone Brand and Model: LFH 4000 & Flexy Mike  Operating System: win 10, latest update; Surface Book 2, Processor (CPU) Type & Speed: I7 8650 Soundcard Brand and Model: none Speech Software: Dragon Medical Practice Edition, french version: 4.2 Using KnowBrainer?:Yes

Yes, I sure would be interested in such a development. Thanks.

Thanks for your feedback.

 

The special function that you are proposing for this denoising audio functionality irrespective of your audio card, i.e. filtering an existing recorded audio file, is also quite interesting for our project and we will take into consideration...

-------------------------

SpeechWare Team

 

 

 

Windows 7, Intel  i7, 8 GB, USB TravelMike or SpeechWare USB MultiAdapter with FlexyMike Dual Ear

https://arstechnica.com/gaming/2020/04/you-can-get-nvidias-rtx-voice-noise-filtering-without-a-pricey-rtx-card/

I followed the link from Ars Technica above and successfully installed the RTX noise filtering software on my laptop which has a GTX.

No license constraints that I can see, but I would not be at all surprised to find out that some future release of the software refuses to run on my GTX laptop. Which may not be too bad - I have been considering replacing my mortally wounded Microsoft Surface Book to with the Surface Book 3 that has an RTX Quadro. In fact, one of the big things holding me pack from purchasing the Surface Book 3 with RTX is my concern that this GPU consumes considerably more power than the GTX alternative, and my experience so far has been that intermittent fan-based cooling on laptops is not good for speech recognition. This is a sort of test drive.

I think it's highly likely that the noise cancellation may work well, but only in steady-state. But there may be problems when the noise level changes, e.g. in the furnace fans turn on or off.

Too early to tell so far, but I thought I would just provide the link above.

Like I said, too early to tell anything so far, except I somehow "feel" that there is a bit more latency in the recognition. With the Dragon parameters set to as fast as possible.

Q: does anyone have a set up to measure latency from saying something, to text appearing? of course the best way would be from an external sound source, but there might be value doing it just inside the software stack.

This latency is different from the occasional long latency delays or stalls that I have seen with Dragon. This latency seems to be rather consistent with the RTX software.

 

---

 

By the way, I saw presentations on this software when I was at Nvidia. It really does look good.  and although it does seem to run on my older GPU, the newer GPUs do have dramatically increased computational bandwidth, which may translate to reduce latency depending on the workload.

 

-------------------------

DPG15.6 (also DPI 15.3) + KB, Sennheiser MB Pro 1 UC ML, BTD 800 dongle, Windows 10 Pro, MS Surface Book 3, Intel Core i7-1065G7 CPU @ 1.3/1.5GHz (4 cores, 8 logical, GPU=NVIDIA Quadro RTX 3000 with Max-Q Design.

I have already mentioned this:

 

DragonBench

I am currently overhauling it. Wait a few days for the next release to be published.

-------------------------

No need to buy if all you want to do is try ...

DragonCapture KB Download (Latest)
DragonCapture Homepage

The application has been updated now:

DragonBench

 

-------------------------

No need to buy if all you want to do is try ...

DragonCapture KB Download (Latest)
DragonCapture Homepage

Early results:

Nvidia's voice/noise canceling does seem to help a bit.

However, my PC, with an MX250 GPU (Pascal, now quite obsolete, not even a GTX), feels significantly more sluggish.

When the Dragon microphone is on the "NV RTX Voice.exe" consumes 5 to 6% of CPU. Even when nothing is being said. Apparently this is the cost of doing this voice "noise cancellation" on background noise when nothing is being said. Note that this is CPU, not GPU utilization. Process Explorer reports no GPU utilization. Task Manager says that the GPU is being utilized, but the Copy Engine, not the actual SM Streaming Processors. This may make sense, just copying data in and out of the GPU, where it is quickly determined to be quiet.

Even this low utilization makes my PC fans turn on. The constant background noise seems not to hurt speech recognition, but when they ramp up and down, it hurts.

There seem to be more occurrences of the annoying 20+ second stalls. As might be expected, with yet another concurrent process in the mix, plus 10 more threads.

--

Anyway, much of this is probably an artifact of my old MX250 GPU. 12.4 GFlops FP16, 797 GFlops FP32, versus 11.20 TFlops FP16, 5.599 TFlops FP32 on the Quadro RTX 3000 Max-Q in a more recent machine like the Microsoft Surface Book 3 high end. I.e. FP16 = one thousand X faster, FP32 circa 60X faster. I expect that NVIDIAS RTX Voice uses FP16, but I don't know for sure. FP16 on the old Pascal based GPU was not really in hardware, but was provided for SW development, amd was hence slower than FP32; whereas on the newer machines FP16 is circa 2X faster than FP32, as one would expect.

--

BOTTOM LINE: NVIDIA RTX Voice seems to work even on this old machine. It feels like it improves quality, but at the cost of making this older but muscular PC feel sluggish.

I look forward to trying NVIDIA RTX Voice on a modern GPU, with Dragon.




-------------------------

DPG15.6 (also DPI 15.3) + KB, Sennheiser MB Pro 1 UC ML, BTD 800 dongle, Windows 10 Pro, MS Surface Book 3, Intel Core i7-1065G7 CPU @ 1.3/1.5GHz (4 cores, 8 logical, GPU=NVIDIA Quadro RTX 3000 with Max-Q Design.

Trying this while dictating medical progress notes, there is barely perceptible increase in latency, but accuracy seems to be better.

 

Q; what's your configuration? e.g. CPU/GPU/frequency?

 

 like I said, I have a rather old Pascal generation GPU.

-------------------------

DPG15.6 (also DPI 15.3) + KB, Sennheiser MB Pro 1 UC ML, BTD 800 dongle, Windows 10 Pro, MS Surface Book 3, Intel Core i7-1065G7 CPU @ 1.3/1.5GHz (4 cores, 8 logical, GPU=NVIDIA Quadro RTX 3000 with Max-Q Design.

It worked without problem on my 2 years old sb2. The vent just blows a little bit more, which is not a problem since noise is now filtered out.

 

-------------------------

Memory: 16GB Microphone Brand and Model: LFH 4000 & Flexy Mike  Operating System: win 10, latest update; Surface Book 2, Processor (CPU) Type & Speed: I7 8650 Soundcard Brand and Model: none Speech Software: Dragon Medical Practice Edition, french version: 4.2 Using KnowBrainer?:Yes

ag,

Memory: 64gb

Microphone Brand and Model: phillips speechmike premium/ANDREA usb pod/KB HANDS FREE MIC- mostly use the old phillips

Operating System: WIN 10 home 64 bit

Processor (CPU) Type & Speed: Intel(R) Core(TM) i7-9700 CPU @ 3.00GHz, 3000 Mhz, 8 Core(s), 8 Logical Processor(s)

Soundcard Brand and Model: nvidia Geforce GTX 1660 Ti

Speech Software (exact version and edition): DPI 15.3

Speech Software Version: 15

@docinfiniti: thanks.  Your system is a lot more powerful than mine, which might explain why you're getting negligible slowdown for NVIDIA RTX voice.

 When next I can afford a hardware upgrade…

 

-------------------------

DPG15.6 (also DPI 15.3) + KB, Sennheiser MB Pro 1 UC ML, BTD 800 dongle, Windows 10 Pro, MS Surface Book 3, Intel Core i7-1065G7 CPU @ 1.3/1.5GHz (4 cores, 8 logical, GPU=NVIDIA Quadro RTX 3000 with Max-Q Design.

thanks for sharing this information !

-------------------------

Memory: 16GB Microphone Brand and Model: LFH 4000 & Flexy Mike  Operating System: win 10, latest update; Surface Book 2, Processor (CPU) Type & Speed: I7 8650 Soundcard Brand and Model: none Speech Software: Dragon Medical Practice Edition, french version: 4.2 Using KnowBrainer?:Yes

Here is my feed back after 2 days trial. I tried this on 3 computers :

1. 2018 Surface Book 2
2. 2017 Destkop Core i7 7th gen, 16 GB RAM, SSD samsung evo 970
3. 2019 Desktop AMD 1950 X, an Nvidia card 18 months old (cannot remember which right here)

-------------------------

Memory: 16GB Microphone Brand and Model: LFH 4000 & Flexy Mike  Operating System: win 10, latest update; Surface Book 2, Processor (CPU) Type & Speed: I7 8650 Soundcard Brand and Model: none Speech Software: Dragon Medical Practice Edition, french version: 4.2 Using KnowBrainer?:Yes

Merci pour vos recherches.
Zig

I have switched PCs, new details in my .signature: overall, my new PC has less DRAM (32GB instead of 64 GB), and lower frequency CPUs (1.3/1.4 GHz rather than 4.9GHz). The CPUs are much lower power, and the fans are much quieter when they are running at all. Plus, relevant here, my new PC GPU is an NVIDIA Quadro RTX 3000 with Max-Q Design, IE a GPU that can run Nvidia RTX Voice without any hacking of configuration files, whereas my old PC's GPU was an GeForce MX150, rated circa 1000x slower for some benchmarks that might be relevant to speech recognition.


Upshot: I am now using Nvidia RTX voice without any apparent problems. And it seems to be helping.

-------------------------

DPG15.6 (also DPI 15.3) + KB, Sennheiser MB Pro 1 UC ML, BTD 800 dongle, Windows 10 Pro, MS Surface Book 3, Intel Core i7-1065G7 CPU @ 1.3/1.5GHz (4 cores, 8 logical, GPU=NVIDIA Quadro RTX 3000 with Max-Q Design.

Did you try with a USB speechware connected mike ?

-------------------------

Memory: 16GB Microphone Brand and Model: LFH 4000 & Flexy Mike  Operating System: win 10, latest update; Surface Book 2, Processor (CPU) Type & Speed: I7 8650 Soundcard Brand and Model: none Speech Software: Dragon Medical Practice Edition, french version: 4.2 Using KnowBrainer?:Yes

 

Any difference in latency to get result from Dragon ?

-------------------------

Memory: 16GB Microphone Brand and Model: LFH 4000 & Flexy Mike  Operating System: win 10, latest update; Surface Book 2, Processor (CPU) Type & Speed: I7 8650 Soundcard Brand and Model: none Speech Software: Dragon Medical Practice Edition, french version: 4.2 Using KnowBrainer?:Yes

Im using this with phillips speechmike premium, running phillips speech cpntrol. Im not certain about the set up, I tried selectong in DPI nvia as the mic source and nothing happens at all.

You have to setup gtx settings from tray icon 1st, choose mic source ffor GTX from there, maike xour choice, keep window open, then choose mic in DPI

-------------------------

Memory: 16GB Microphone Brand and Model: LFH 4000 & Flexy Mike  Operating System: win 10, latest update; Surface Book 2, Processor (CPU) Type & Speed: I7 8650 Soundcard Brand and Model: none Speech Software: Dragon Medical Practice Edition, french version: 4.2 Using KnowBrainer?:Yes

Update: I am reasonably happy using Nvidia RTX Voice denoising with my SennheiserMB Pro 1 UC headset, on a Microsoft Surface Book3, 32GB DRAM, but the fanciest GPU  available at the time of purchase for this  PC. (Details in my .sig). 

Minor hiccup: The Surface Book 3 fairly regularly fails to recognize the Nvidia GPU, typically after power management events like sending the system to sleep. Symptom: Error message "unable to start microphone denoising". Further: look at device manager, and of the Nvidia GPU will either be disabled or sometimes not show up at all. frequently power cycling/rebooting does not bring the GPU back. However, detaching and reattaching the LCD display (which carries the CPU but not the big GPU) reliably leads to the GPU being reconnected.

(It took me a regrettably/unfortunately long time to figure this out. Now detaching/reattaching the display is one of my debug BKMs, before restarting the PC.)

-------------------------

DPG15.6 (also DPI 15.3) + KB, Sennheiser MB Pro 1 UC ML, BTD 800 dongle, Windows 10 Pro, MS Surface Book 3, Intel Core i7-1065G7 CPU @ 1.3/1.5GHz (4 cores, 8 logical, GPU=NVIDIA Quadro RTX 3000 with Max-Q Design.

@docdoc asked "Did you try [NVIDIA RTX Voice] with a USB speechware connected mike ?"

No, I do not have such a microphone. I pretty much only use my Sennheiser MB Pro 1 UC ML wireless mic. USB cables get tangled up in my work environment

-------------------------

DPG15.6 (also DPI 15.3) + KB, Sennheiser MB Pro 1 UC ML, BTD 800 dongle, Windows 10 Pro, MS Surface Book 3, Intel Core i7-1065G7 CPU @ 1.3/1.5GHz (4 cores, 8 logical, GPU=NVIDIA Quadro RTX 3000 with Max-Q Design.

A recent Microsoft windows update broke Nvidia RTX Voice on my Surface Book 3 laptop PC[*].


This quickly showed how dependent I am on Nvidia RTX Voice. Without it, I was getting the annoying "him him him" problem all over the place.


Looking around found that Nvidia RTX Voice has been upgraded and is now part of the Nvidia Broadcast app, which also does video filtering. After upgrading my GPU driver, and installing the new app, I am back and running and very happy.


--


Note *: the same upgrade broke my laptop's built-in keyboard and trackpad. Right now they are still broken, and I am mainly controlling my PC by Dragon/KnowBrainer, although I also have an external keyboard and trackball.

-------------------------

DPG15.6 (also DPI 15.3) + KB, Sennheiser MB Pro 1 UC ML, BTD 800 dongle, Windows 10 Pro, MS Surface Book 3, Intel Core i7-1065G7 CPU @ 1.3/1.5GHz (4 cores, 8 logical, GPU=NVIDIA Quadro RTX 3000 with Max-Q Design.

In our opinion you're using a Band-Aid approach. If Dragon is producing "him him him" without Nvidia RTX Voice, you are masking rather than fixing the source problem. "him him him" is nearly always interference which ranges from a bad ground, oscillating chip, frayed cable, RF interference and a ton of other possibilities. Nvidia RTX Voice can mask the problem but your accuracy is likely still suffering, albeit less. We strongly suggest searching for and fixing the root problem.

-------------------------

Change "No" to "Know" w/KnowBrainer 2022
Trial Downloads
Dragon/Sales@KnowBrainer.com 
(615) 884-4558 ex 1

 

Thanks for the advice.

 

Problem occurs on a laptop, disconnected,  wireless headset, hence no frayed cable.

 

Problem occurs both in the fairly noisy RF environment at my home, but also in the desert, no nearby RF, and in deep canyons,  not even very much satellite or GPS RF.

 

Problem occurs on more than one PC/laptop.  hence oscillating chip in the PC unlikely, unless all of my PCs have the same problem.

 

Wireless headset, so the problem could be  in the Sennheiser headset or dongle electronics.  I cannot exclude that, and I have not yet gone shopping for alternative headsets.

 

However, I can fairly reliably reproduce the "him him him"  symptom, by exhaling through my nose. This leads me to suspect that it is an acoustic problem. 

 

Exhaling perhaps a little bit more forcefully than usual, but not necessarily snorting like a bull.  more like the nasal equivalent of a heavy sigh.  Possibly related to allergies -  the problem was much worse during this summer of wildfire smoke.   even now, with Nvidia RTX Voice connected, if I breathe deeply through my nose  I get Dragon's recognition error . without Nvidia RTX Voice,  I get the "him him"  errors on much less forceful nose breathing.

 

Apart from Nvidia RTX Voice, I can remedy  the problem by swinging the headset's microphone arm so that it is above my nose.   how far above depends on how strongly I exhale through my nose. but that brings a lot of other problems.  Swinging the mic below my mouth to below my chin leads to  it catching on my clothes.  The Sennheiser headset mic arm has limited adjustability,  mainly just this swinging arc.

 

I wonder if a better windscreen for the mic  might help. Or, rather,  When I lost my original Sennheiser windscreen I learned that a cheap windscreen for the mic hurts, so it is well worth using the official Sennheiser windscreen. But I wonder if there is a still better windscreen.

 

 (just for grins I am dictating with the microphone swingarm way up on my eyebrows. It still catches some of my nasal  exhalations, but not as many)

 

(I tried a number of experiments with Nvidia RTX Voice disabled, wondering if it was because of some of the performance problems I had with Dragon. inconclusive.  other issues, such as voice enabling menus, have a larger effect.)

 

I hope in the next few months to be able to try a table mic,  to see if it provides better results.

 

 

-------------------------

DPG15.6 (also DPI 15.3) + KB, Sennheiser MB Pro 1 UC ML, BTD 800 dongle, Windows 10 Pro, MS Surface Book 3, Intel Core i7-1065G7 CPU @ 1.3/1.5GHz (4 cores, 8 logical, GPU=NVIDIA Quadro RTX 3000 with Max-Q Design.

If your interference is caused by windage, a standard inexpensive Windscreen might help and keep you wireless. A broadcast pop screen would be better but difficult to use. Having said that, we suspect your wireless microphone is the real culprit. Do you have another USB microphone you can use to test this theory?

-------------------------

Change "No" to "Know" w/KnowBrainer 2022
Trial Downloads
Dragon/Sales@KnowBrainer.com 
(615) 884-4558 ex 1

I have tried quite a few windscreens, ranging from Sennheiser's, through cheap, to some supposedly high end recommended for aviation.  The latter work best, but none cure the issue.

 

I have many alternate mics, quite a few wireless, several USB wired, both headset and table.  However, all are either cheap, or old (like my very old Andreas, from my first pass at speech.)  The next try will be a table mic and/or an array mic. I hope that a good large cardiod will be able to capture my voice as I move/sway +/- 1-2 feet, without capturing my nose. Saving up, and expecting to have to try and return.

 

I had hopes for mics built into the earpiece, or bone conduction - nothing near my nose. However, initial attempts unsuccessful - and then I discovered this forum, and AFAICT you don't recommend any such.

 

I am still hopeful about headsets.  E.g. the new generation of VR headsets has improved audio input, plus has enough processing power in the headset that good noise cancellation should be possible.

-------------------------

DPG15.6 (also DPI 15.3) + KB, Sennheiser MB Pro 1 UC ML, BTD 800 dongle, Windows 10 Pro, MS Surface Book 3, Intel Core i7-1065G7 CPU @ 1.3/1.5GHz (4 cores, 8 logical, GPU=NVIDIA Quadro RTX 3000 with Max-Q Design.

Lunis, I wanted to buy a windscreen for my SpeechWare 3-in-1 microphone, but when I went to check out, I saw that shipping would amount to almost 3 times the cost of the windscreen. Couldn't something that small just be slipped in an envelope and dropped in the mail?

-------------------------

James McVay

You are right about our FedEx shipping rates. For some reason, our ground shipping is much higher than it should be. We recommend sourcing this item on Amazon

-------------------------

Change "No" to "Know" w/KnowBrainer 2022
Trial Downloads
Dragon/Sales@KnowBrainer.com 
(615) 884-4558 ex 1

Thanks for the Amazon tip, Lunis. As far as I could tell, none are marketed specifically for SpeechWare TableMikes. Nevertheless, I went ahead and ordered these windscreens: AmazonSmile: kwmobile Microphone Foam Covers (Set of 5) - 0.8 x 1.3 inches (2x3.2 cm) Windscreen Protective Pop Filter Pack for Microphones - Black: MP3 Players & Accessories.

 

As far as I can tell from the dimensions given, they should fit. And they're cheap. They come five in a set, so when the cat runs off with one I will still have four replacements.

-------------------------

James McVay

I thought the "ML" version of MB PRo, which stands for Microsoft Lync optimized, introduces complications for speech recognition. Or was that old news no longer applicable?

Lunis probably knows this better.

The original "ML" model was a problem with Dragon but Sennheiser fixed this a few years ago. That's also when they discontinue the MB Pro1/2 UC model and now only offer the UC/ML because it's no longer an issue.

-------------------------

Change "No" to "Know" w/KnowBrainer 2022
Trial Downloads
Dragon/Sales@KnowBrainer.com 
(615) 884-4558 ex 1

Update with respect to NVIDIA's denoising software: now renamed NVIDIA Broadcast.


I remain a fan. Perhaps I could make it unnecessary as Lunis describes, but this is working right now, whereas repeated efforts to make what he describes work of so far not succeeded.


Minor issue, recently discovered: I sometimes switch microphones, and use more than one microphone through Nvidia voice. E.g. recently I managed to leave my Sennheiser headset at the coast, so I had to use a wired headset for a week.


From Dragon's point of view these are the same microphone: NVIDIA Broadcast. it is within Nvidia Broadcast that I actually switched microphone.


This seems to lead to some confusion on Dragon's part. Moral: don't do that, or build a new profile, or at least do a microphone check, when switching microphone within Nvidia Broadcast.


-------------------------

DPG15.6 (also DPI 15.3) + KB, Sennheiser MB Pro 1 UC ML, BTD 800 dongle, Windows 10 Pro, MS Surface Book 3, Intel Core i7-1065G7 CPU @ 1.3/1.5GHz (4 cores, 8 logical, GPU=NVIDIA Quadro RTX 3000 with Max-Q Design.

I love the Nvidia RTX based noise filtering software. It completely removed the "him him him" problem. But the downside is that it is yet another thing to go wrong. As I describe in these verses, intended to be sung to the tune of "woke up this morning, you were on my mind"



woke up this morning
work was on my mind
sound, was on, my mind
but my mic was not working
first I blamed Nvidia
but nor was my
Senn - heiser dong - le working

Unplugged and plugged it in
it started working again
the naked Sennheiser headset
so I - could dic - tate this

but Nvidia software
noise filtering
is still, not working, yet

In fact it won't even start
I do not know what to do
there is no tray icon
no running process
although, there are many, services

checked device manager
the display adapter
with dGPU builtin
that does noise filtering
still, seems to, be there

I do not know what to do
now I am worried shit
because this morning
my PC fan, started running, very fast

Now I am worried shit
that my PC is failing
it's still on warranty
but sucks to turn it in
because I need to work
and if I switch, PCs, no speech
re-cog-nition

but the hardware is flaky
touchscreen is already dead
I really need to turn it in
and install my licenses
on a, back up, PC

Must think of what to do
I think I'll boot again
perhaps let it cool down
oh God, I hate, this crap


-------------------------

DPG15.6 (also DPI 15.3) + KB, Sennheiser MB Pro 1 UC ML, BTD 800 dongle, Windows 10 Pro, MS Surface Book 3, Intel Core i7-1065G7 CPU @ 1.3/1.5GHz (4 cores, 8 logical, GPU=NVIDIA Quadro RTX 3000 with Max-Q Design.

 

Ag - dude/dudette/du-nb, put yourself out of your misery, get this and get some work done:

 

https://www.ebay.ca/itm/Lenovo-30D1000UUS-ThinkStation-P330-Workstation-Intel-Xeon-Quad-core-4-Core/353406194428

 

There are a few floating around the Bay as we speak (a couple hundred $ more than what I linked).  I was eying the above, even though I can't really justify the purchase, and the "rationalization" nevertheless did not prevent me from low-balling an offer ... the specs were just too tempting.  Impulses from the reptilian parts of the brain are hard to overcome indeed. 

 

I already have a perfectly working P320 and Z2 mini G3 - both new old stock.  I only buy computers that are new old stock, or even lightly refurbished. 

 

Literally you can't afford flaky hardware, as you said yourself.  2021, with the flood gate of money coming everywhere (not quite in my paycheque, however), and with the general flakiness going around in places that supply electronics, you will get worse copper wire, worse capacitors, worse drivers, worse everything if you buy this year's models.  

 

Your Surface Book 3 is a testament.  

 

I even scoured the net for an NOS TS150 server a year ago (why that particular model?  For it's the only entry "server" that has driver support for Win 7/10 at the factory level, and none was floating in the Bay, still none today - at least not "new" or NOS).

 

All those who buy consumer grade hardware this year (XPS, IdeaPads etc.) will come here and cry.  And your SB3 is hardly "consumer-grade"!

 

Mark them words.

Man, that was a miserable morning.

After the day's rush of meetings, unisntalled NVIDIA Broadcast, installed the latest version, it's working again.

Why?  Who knows! Bit rot? MS's latest update?

It's a twisty maze of software packages, all slightly incompatible.

 

-------------------------

DPG15.6 (also DPI 15.3) + KB, Sennheiser MB Pro 1 UC ML, BTD 800 dongle, Windows 10 Pro, MS Surface Book 3, Intel Core i7-1065G7 CPU @ 1.3/1.5GHz (4 cores, 8 logical, GPU=NVIDIA Quadro RTX 3000 with Max-Q Design.

Adding a smidgen to my own "sage" advice (ahem):

What about warranty? Most brand-name workstation / server grade PCs come with a 3/3 warranty. Prior to Covid, it might have been 3/3/3 (last 3 for on-site ... not sure how practical in this day and age). In my limited experience, it's the first year that really counts, as that's when you do your "burn-in".

So if the workstation you are looking at from the Bay (or trusted local shop) has a 1 yr warranty left out of the 3, and could be yours at a decent discount. Then that's the kind of "NOS" that you want.

A reputable lightly used "refurb" might be as golden as that proverbial 4 year-old 5000-mile car owned by the "lil' ol' lady" who only drove it during spring and fall, when it's not too hot and there is no salt on the road. That "ol' lady" has burnt it in for you, in addition to babying it for you. In reality random folks never get to these vehicles because they are usually snapped up by the dealer for his favourite niece ... But on refurb higher-end PCs the odds are better. May just need to pop in your own trusted SSD.

Here we wish the old-timer Phil Schaadt is still around and would perhaps drive home the importance of "burn-in", backed up with some stats. Granted that some of the local boutique "system integrators" may oversell you on that "burn-in". But it really is worth something IMO.

Most of the visitors to this forum are highly educated, quite likely more so than population average.

One look at the copper price chart and what's around the world tells us that the chance that your IdeaPads or XPSes this year will be more reliable than they were 2 years ago (which were wobbly even then) is ... you might as well believe the next version of desktop Dragon, whatever and whenever, will play nice with Word and Outlook, like the proverbial peanut butter and jam with sandwich.

This is amazing. I currently have the air conditioner, the fan, and music playing on speakers in the background, but I can't hear any of that when I have Nvidia RTX voice app running. I say "play that back" and I hear my utterance without any of the noise.

Watching the resource consumption in the task manager, the Nvidia RTX voice app consumes between 0.5 and 1.4 % of my CPU power. Memory consumption hovers around 25 MB. When I am not saying anything, CPU consumption is about 0.5. Memory usage doesn't change.

Nvidia GeForce GTX 1660.
Processor AMD Ryzen 5 2600 Six-Core Processor, 3400 Mhz, 6 Core(s), 12 Logical Processor(s)
Installed Physical Memory (RAM) 16.0 GB

-------------------------

Dragon Professional Individual v15.6. Windows 10. Knowbrainer 2017.

Another update on Nvidia's noise filtering software - now called Nvidia Broadcast, I believe officially supported, replacing the experimental Nvidia RTX Voice.

I continue to love it.

But... (you know that a but was coming):

I recently did a warranty replacement of my Surface Book 3. The old SB3 ran Nvidia Broadcast without the fan coming on - but over time its touchscreen, keyboard, and trackpad all failed. I blame the infamous SurfBook hinge. I was able to use it for a few months (!) essentially as something like a Mac Mini with display, but made sure to replace it before the warranty expired. The warranty replacement - exactly the same specs - cannot run Nvidia Broadcast, even on the lowest noise cancellation settings, without the fan going into hyperdrive. Same OS, etc.

Having worked at both Intel and Nvidia, I am aware that there is considerable variation in power efficiency and heat production even between chips with the same specs. Sometimes even in the same wafer.

Nevertheless, the fan overdrive is so annoying that I have stopped using Nvidia Broadcast noise cancellation.

I have some hope that when I return to air conditioning the fan problem may be fixed. (I am currently in non-air-conditioned COVID quarantine quarters - not sick, just travelled to Canada for family reasons.)

Various monitoring tools - Core Temp, Open Hardware Monitor - don't show any overheating. It is probably just fan policy settings. I know how to change Windows' CPU fan settings, but haven't found GPU fan policy by Googling.

BTW: I am 99.44% certain that the problem is GPU,  hardware or software. Disconnect the GPU, fan turns off. Reconnect the GPU, fan turns on  when I start using Nvidia Broadcast. Fan occasionally turns on even when I am not using Nvidia Broadcast. Annoyingly,  the Nvidia GPU video engine is running, and it doesn't need to, non-GPU graphics is fine for my application. All I want is the noise filtering.  GPU utilization circa 2% or less. But fan is still on.

--

As frequently happens when I make such a post, I realize a possible cause: I restored the old Surface Book image on the "new" (refurbished) warranty replacement Surface Book. It is possible that there were some tuning parameters on the new SB3.2 image. Fortunately, I made a backup, and might try going back.

-------------------------

DPG15.6 (also DPI 15.3) + KB, Sennheiser MB Pro 1 UC ML, BTD 800 dongle, Windows 10 Pro, MS Surface Book 3, Intel Core i7-1065G7 CPU @ 1.3/1.5GHz (4 cores, 8 logical, GPU=NVIDIA Quadro RTX 3000 with Max-Q Design.

 

They don't provide air-conditioning in "quarantine camps" in 30+C weather here in Canada?

 

And you are still trying to get work done and helping trouble-shoot folks' keyboard mayhem. 

 

Hats off to you!

Not in the apartment attached to my sister's barn. Cheaper than an airport quarantine hotel. Lousy broadband :-(    Counting blessings: temperatures exceeded  40°C as I left the West Coast.

-------------------------

DPG15.6 (also DPI 15.3) + KB, Sennheiser MB Pro 1 UC ML, BTD 800 dongle, Windows 10 Pro, MS Surface Book 3, Intel Core i7-1065G7 CPU @ 1.3/1.5GHz (4 cores, 8 logical, GPU=NVIDIA Quadro RTX 3000 with Max-Q Design.

Another update:

I was getting many annoying beeps, errors in the recognition history. Turns out I had reduced the NVIDIA Broadcast (old RTX Voice) noise filtering in a mostly successful attempt to reduce CPU/GPU load during the very hot weather. Increasing the noise filtering => problem went away.

Interesting that the reduced noise filtering worked fine in the apartment attached to my sister's barn - quiet, no AC, little noise except for occasional turkey gobbling - but did not work well at home in the city - AC, fans, traffic noise. Echo properties also different: high ceiling/rough wood surfaces/small windows versus low ceiling/glossy paint on wallboard/big windows directly behind PC. For that matter I suspect that the many monitors I have at home also lead to more echo.

Anyway, I remain a big fan of this noise filtering software. Almost makes me regret leaving NVIDIA.

-------------------------

DPG15.6 (also DPI 15.3) + KB, Sennheiser MB Pro 1 UC ML, BTD 800 dongle, Windows 10 Pro, MS Surface Book 3, Intel Core i7-1065G7 CPU @ 1.3/1.5GHz (4 cores, 8 logical, GPU=NVIDIA Quadro RTX 3000 with Max-Q Design.

I have been using Nvidia broadcast/RTX voice on my desktop computer for a while now, and it works great. My laptop computer that does not have a dedicated graphics card does not get the same benefit, however.

Are there any alternatives that people on here use for dictation?

I tried to get NoiseGator to work but couldn't figure it out.

Most of the other solutions I find are for conference calls, and I'm not sure if they would work for creating a new virtual microphone the same way that Nvidia broadcast does.


-------------------------

Dragon Professional Individual v15.6. Windows 10. Knowbrainer 2017.

I started this post to mention that there are quite a few laptops that have Nvidia GPUs that are not on a "dedicated graphics card". But I suspect you know that, and it depends on your definition of "dedicated graphics card" [*].

I was interested by your mention of NoiseGator, googled, and found Krisp recommended as an easier to use alternative. I have not tried Krisp, however.



-------------------------

DPG15.6 (also DPI 15.3) + KB, Sennheiser MB Pro 1 UC ML, BTD 800 dongle, Windows 10 Pro, MS Surface Book 3, Intel Core i7-1065G7 CPU @ 1.3/1.5GHz (4 cores, 8 logical, GPU=NVIDIA Quadro RTX 3000 with Max-Q Design.

https://en.wikipedia.org/wiki/Screen_burn-in

Burn-in is almost not a problem with modern LCD screens.

CRTs had big burn-in problems.

Plasma screens (eg big TVs) had burn-in problems, at least prior to 2007.

OLEDs - a flat screen technology different from LCDs - can suffer burn-in. OLEDs are thinner and lighter than LCDs, and have greater contrast. OLEDs are common in phones and smartwatches (thinner, lighter) and some TVs (greater contrast). Also in some laptops (https://www.pcmag.com/picks/the-best-oled-laptops). OLEDs in general suffer color degradation over time, usually faster than LCDs go bad -- IIRC burn-in is this color degradation accelerated by use.

I have long hungered after some of the best looking OLED displays... but in general I am cheap and have LCDs. Some OLEDs

LCDs and OLEDs tend to suffer image persistence / retention problems - an old image remains slightly visible even though a new image is projected, but fades over time. "Over time" can be a while- Apple used to recommend mitigating image retention by displaying a white screen for the same amount of time as the image that you want to "un-persist" was displayed. So if you displayed it for several hours... ?

But LCDs and OLEDs can still suffer burn-in. Although much, much, less than CRTs.

At least, companies that sell anti-burn-in technologies say that LCD and OLED burn-in still occurs, Like https://www.agneovo.com/global/anti-burn-in-technology

And sites like https://www.makeuseof.com/tag/why-do-images-get-burned-into-lcd-and-plasma-displays-and-how-you-can-fix-it/ have pictures of burn-in on real flat-screen monitors.

Most people no longer worry about LCD and OLED burn-in, but if they do they do things like:

a) use screen savers (yup)

b) turn the screen off

c) display a blank (typically white) screen - which tends to equalize pixels

d) display noise / static patterns that change over time, B&W/gray or multicolor

e) for static images, regularly shift pixels.

Oh, did I mention that excessive heat can cause screen discoloration?

Anyway, several of these mitigation techniques may be automatically applied by your LCD or OLED or other display controller. Such automatic application is one reason why most of us worry much less about LCD and OLED burn-in.

For the most part, turning off your display - screen blanking as mentioned by others - is the most you need. Plus, it saves power, energy, battery life, ...

(Random noise patterns can help more, but are quite distracting if bright.)

-------------------------

DPG15.6 (also DPI 15.3) + KB, Sennheiser MB Pro 1 UC ML, BTD 800 dongle, Windows 10 Pro, MS Surface Book 3, Intel Core i7-1065G7 CPU @ 1.3/1.5GHz (4 cores, 8 logical, GPU=NVIDIA Quadro RTX 3000 with Max-Q Design.