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/x64, AMD Ryzen 7 3700X, 64GB RAM, Dragon 15.61, SP 6 PRO, SpeechStart, Office 365, KB 2017, Dragon Capture, Samson Meteor USB Desk Mic, Klim and JUKSTG earbuds with microphones, 3 BenQ 2560x1440 monitors, Microsoft Sculpt Keyboard and fat 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.

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

Forum Mission Statement
Trial Downloads
Dragon/Sales@KnowBrainer.com 
(615) 884-4558 ext 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?

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

Forum Mission Statement
Trial Downloads
Dragon/Sales@KnowBrainer.com 
(615) 884-4558 ext 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

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

Forum Mission Statement
Trial Downloads
Dragon/Sales@KnowBrainer.com 
(615) 884-4558 ext 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.

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

Forum Mission Statement
Trial Downloads
Dragon/Sales@KnowBrainer.com 
(615) 884-4558 ext 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.