Artificial neural networks for voice activity detection Technology

Currently, the direction of voice biometrics is actively developing, which includes two related tasks of recognizing the speaker by voice: the verification task, which consists in determining the speaker's personality, and the identification task, which is responsible for checking the belonging of the phonogram to a particular speaker. An open question remains related to improving the quality of the verification identification algorithms in real conditions and reducing the probability of error. In this work study Voice activity detection algorithm is proposed, which is a modification of the algorithm based on pitch statistics; VAD is investigated as a component of a speaker recognition system by voice, and therefore the main purpose of its work is to improve the quality of the system as a whole. On the example of the proposed modification of the VAD algorithm and the energy-based VAD algorithm, the analysis of the influence of the choice on the quality of the speaker recognition system is carried out.

Through-the-Wall Micro-Doppler De-Wiring Technique via Cycle-Consistent Adversarial Network

The radar penetrating technique has aroused a keen interest in the research community, due to its superior abilities for through-the-wall indoor human motion monitoring. Micro-Doppler signatures in this situation play a significant role in recognition and classification for human activities. However, the live wire buried in the wall introduces additive clutters to the spectrograms. Such degraded spectrograms drastically affect the performance of behind-the-wall human activity detection. In this paper, an ultra-wideband (UWB) radar system is utilized in the through-the-wall scenario to get the feature enhanced micro-Doppler signature called range-max time-frequency representation (R-max TFR). Then, a recently introduced Cycle-Consistent Generative Adversarial Network (Cycle GAN) is employed to realize the end-to-end de-wiring task. Cycle GAN can learn the mapping between spectrograms with and without the live wire effect. To minimize the wiring clutters, a loss function called identity loss is introduced in this work. Finally, the proposed de-wiring approach is evaluated through classification. The results show that the proposed Cycle GAN architecture outperforms other state-of-art de-wiring methods.

Visualizing cell death in live retina: Using calpain activity detection as a biomarker for retinal degeneration

Calpains are a family of calcium-activated proteases involved in numerous disorders. Notably, previous studies have shown that calpain activity was substantially increased in various models for inherited retinal degeneration (RD). In the present study, we tested the capacity of the t-BOC-Leu-Met-CMAC calpain-specific substrate to detect calpain activity in living retina, in organotypic retinal explant cultures derived from wild-type mice, as well as from rd1 and RhoP23H/+ RD-mutant mice. Test conditions were refined until the calpain substrate readily detected large numbers of cells in the photoreceptor layer of RD retina but not in wild-type retina. At the same time, the calpain substrate was not obviously toxic to photoreceptor cells. Comparison of calpain activity with an immunostaining for activated calpain-2 furthermore suggested that individual calpain isoforms may be active in distinct temporal stages of photoreceptor cell death. Notably, calpain-2 activity may be a relatively short-lived event, occurring only towards the end of the cell death process. Finally, our results support the development of calpain activity detection as a novel in vivo biomarker for RD, suitable for combination with non-invasive imaging techniques.