BRN Discussion Ongoing

Diogenese

Top 20
I think I can speak for us all when I say I don't understand what all the fuss is about:



Raw Speech Enhancement with Deep State Space Modeling

Yan Ru Pei, Ritik Shrivastava, FNU Sidharth


We introduced a lightweight deep state-space autoencoder, aTENNuate, that can perform raw audio denoising, superresolution, and de-quantization. Compared to previous works, the key features of this network are: 1) consisting of statespace layers that can be efficiently trained and configured for inference, 2) allowing for real-time inference with low latency, 3) architecturally simple and light in parameters and MACs, 4) capable of processing raw audio waveforms directly without requiring pre/post-processing, and 5) highly competitive with other speech enhancement solutions.
 
Last edited:
  • Like
  • Fire
  • Love
Reactions: 37 users

Diogenese

Top 20
I ask myself what tension have they set on the share price release valve???

You're gonna need a bigger stock exchange!
 
  • Like
  • Love
  • Fire
Reactions: 25 users

Diogenese

Top 20
I'm working on the script for an espionage movie starring Robert Redford called:

"Three Days of the Giant Toblerone".
 
  • Haha
  • Like
  • Fire
Reactions: 9 users
Reckon we can have a bit of creative fun with TENNs.
aTENNuate … not bad

TENNsor

- give your sensors the competitive edge

aTENNsion

- demand the best for your AI solutions
TSEX could do with a little help. There has been a bit of TENNsion here lately. 😁

SC
 
  • Haha
  • Like
Reactions: 12 users

MDhere

Top 20

View attachment 68983
1000018171-jpg.68984

View attachment 68985
I agree the denoise capabilityis outstanting. At the agm when they did a demo, i had my hearing aids on and when they played the sentence with the words and noise then they played it with the denoise function i heard every word. Its not if but when. ❤
 
Last edited:
  • Like
  • Fire
  • Love
Reactions: 47 users
Should be a mention for brainchip but not watched it.

 
Last edited:
  • Like
  • Fire
  • Love
Reactions: 17 users

MrNick

Regular
  • Like
  • Fire
  • Love
Reactions: 16 users
  • Fire
  • Like
Reactions: 4 users
Did it mention us?
Akida 1000 was the star hardware used in their study and it passed with flying colours. They did say in the concluding statements that SNN hardware has some limitations but I imagine the current Akida hardware/software was designed to overcome those limitations. lGreat exposure for Akida. Good work Pom.
 
  • Like
  • Fire
  • Love
Reactions: 25 users

JB49

Regular
I agree the denoise capabilityis outstanting. At the agm when they did a demo, i had my hearing aids on and when they played the sentence with the works and noise then they played it with the denoise function i heard every word. Its not if but when. ❤
I wonder if it can improve a cochlear implant. If it does, surely they are taking note.
 
  • Like
  • Fire
Reactions: 12 users
Did it mention us?
At. 35.30 it starts to talk about the advantages of Akida
 
Last edited:
  • Like
  • Fire
Reactions: 16 users

TheDrooben

Pretty Pretty Pretty Pretty Good
Should be a mention for brainchip but not watched it.


Great find Pom. The Assistant Professor was very impressed with the energy saving and speed to achieve 90% accuracy. Interesting that Missouri University of Science and Technology is not even in our University AI Accelerator program.

Screenshot_20240907_095125_Chrome.jpg


Screenshot_20240907_094236_Chrome.jpg


Happy as Larry
 
Last edited:
  • Like
  • Fire
  • Love
Reactions: 27 users

Quiltman

Regular
1725667166589.png


As demonstrated on AKIDA 1000
 

Attachments

  • 1725666630345.png
    1725666630345.png
    86.8 KB · Views: 94
  • 1725666727134.png
    1725666727134.png
    58.2 KB · Views: 81
  • 1725666852424.png
    1725666852424.png
    58.3 KB · Views: 86
  • 1725666872308.png
    1725666872308.png
    58.3 KB · Views: 85
  • Like
  • Fire
  • Love
Reactions: 42 users

DK6161

Regular
My opinion won’t make a difference to anything
The way I see it is either you invest and enjoy the journey or you don’t.

The way I see it is it’s going to be good if they do well and I hope they do

Every body is saying it’s taking longer than they thought
It’s not just BRN
It’s industry wide

Give it another 4 years at least
You have been saying that for the last 8 years.
At this rate, give it another 12 years at least
 
  • Haha
Reactions: 1 users

Esq.111

Fascinatingly Intuitive.
Morning Chippers ,

Good to see the new development , and more articles our tech.

The flywheel is slowly gaining momentum



Regards,
Esq.
 
  • Like
  • Haha
  • Fire
Reactions: 19 users

JB49

Regular

2024 study utilising akida 1000 for driver assisted braking system by Nathan Lutes from Missouri University. He has also worked for Boeing for the last 4 years
 
  • Like
  • Fire
  • Wow
Reactions: 32 users

IloveLamp

Top 20
1000018191.jpg
 
  • Like
  • Fire
  • Wow
Reactions: 33 users
  • Like
Reactions: 7 users
Top Bottom