Mr. Pei is certainly excited about this development as he should be. Congratulations to Mr. Pei and the Brainchip Research Team.
My opinion only DYOR
Fact Finder
- Forums
- ASX - By Stock
- BRN
- aTENNuate for raw speech denoising in real time
BRN
brainchip holdings ltd
Add to My Watchlist
0.00%
!
20.5¢

aTENNuate for raw speech denoising in real time, page-2
Featured News
Add to My Watchlist
What is My Watchlist?
A personalised tool to help users track selected stocks. Delivering real-time notifications on price updates, announcements, and performance stats on each to help make informed investment decisions.
|
|||||
Last
20.5¢ |
Change
0.000(0.00%) |
Mkt cap ! $415.2M |
Open | High | Low | Value | Volume |
20.5¢ | 21.0¢ | 20.0¢ | $1.208M | 5.898M |
Buyers (Bids)
No. | Vol. | Price($) |
---|---|---|
52 | 2248810 | 20.0¢ |
Sellers (Offers)
Price($) | Vol. | No. |
---|---|---|
20.5¢ | 369721 | 7 |
View Market Depth
No. | Vol. | Price($) |
---|---|---|
43 | 1850019 | 0.200 |
26 | 1277507 | 0.195 |
56 | 1841112 | 0.190 |
40 | 1366842 | 0.185 |
65 | 1233007 | 0.180 |
Price($) | Vol. | No. |
---|---|---|
0.205 | 257259 | 3 |
0.210 | 978887 | 19 |
0.215 | 1370152 | 18 |
0.220 | 2146303 | 50 |
0.225 | 741889 | 12 |
Last trade - 16.13pm 04/07/2025 (20 minute delay) ? |
Featured News
BRN (ASX) Chart |
The Watchlist
NUZ
NEURIZON THERAPEUTICS LIMITED
Dr Michael Thurn, CEO & MD
Dr Michael Thurn
CEO & MD
SPONSORED BY The Market Online
Speech enhancement is a very difficult task that requires an incredible amount of domain expertise. There are typically many moving parts and expertly crafted pipelines for processing audio features.
Here atBrainChip, we continue the trend of using the hashtag#TENNs model as an end-to-end elegant solution. Introducing aTENNuate, a highly performant network for raw speech enhancement. The input can be noisy, down sampled, and quantized, yet the output is still near crystal-clear. By virtue of being a state-space model, the network can perform real-time enhancement with minimal memory and compute footprint, while at the same time efficiently trainable on parallel hardware.
Contact Brianchip to learn more.
Paper:https://lnkd.in/gMPJ3Fan
Massive thanks to my coauthors Ritik Shrivastava and FNU Sidharth, and everyone from the Brainchip research team for this great work.