BRN brainchip holdings ltd

aTENNuate for raw speech denoising in real time

  1. 10,974 Posts.
    lightbulb Created with Sketch. 30616

    Just released:

    Real-timeSpeech Enhancement on Raw Signals with Deep State-space Modeling

    Yan Ru Pei, Ritik Shrivastava†, Sidharth‡ Brainchip Inc. Laguna Hills, USA [email protected], [email protected]†, [email protected]‡ arXiv:2409.03377v1 [cs.SD] 5 Sep 2024

    AbstractWe present aTENNuate, a simple deep state-space autoencoder configured for efficient online raw speech enhancement in an end-to-end fashion. The networks performance is primarily evaluated on raw speech denoising, with additional assessments on tasks such as super-resolution and de-quantization. We benchmark aTENNuate on the VoiceBank + DEMAND and the Microsoft DNS1 synthetic test sets. The network outperforms previous real-time denoising models in terms of PESQ score, parameter count, MACs, and latency. Even as a raw waveform processing model, the model maintains high fidelity to the clean signal with minimal audible artifacts. In addition, the model remains performant even when the noisy input is compressed down to 4000Hz and 4 bits, suggesting general speech enhancement capabilities in low-resource environments.

    VI. CONCLUSION We introduced a light weight deep state-space autoencoder, aTENNuate, that can perform raw audio denoising, super resolution, and de-quantization. Compared to previous works, the key features of this network are:

    1) consisting of state space 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.

    VII. ACKNOLWEDGEMENT

    We thank Temi Mohandespour and Keith Johnson for contributing to the early stages of the project. We also thank M. Anthony Lewis, Douglas McLelland, Kristofor Carlson, and Chris Jones for providing useful feedback on the manuscript.

    A significant development with widespread applications across many industries.

    My opinion only DYOR

    Fact Finder

 
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.
(20min delay)
Last
20.5¢
Change
0.005(2.50%)
Mkt cap ! $415.2M
Open High Low Value Volume
21.0¢ 21.3¢ 20.5¢ $1.245M 6.005M

Buyers (Bids)

No. Vol. Price($)
11 1671491 20.5¢
 

Sellers (Offers)

Price($) Vol. No.
21.0¢ 1345577 16
View Market Depth
Last trade - 16.10pm 02/04/2025 (20 minute delay) ?
BRN (ASX) Chart
arrow-down-2 Created with Sketch. arrow-down-2 Created with Sketch.