Sorry, you need to enable JavaScript to visit this website.

This paper presents a new adaptation of a Gaussian echo model (GEM) to estimate the distances to multiple targets using acoustic signals. The proposed algorithm utilizes m-sequences and opens the door for applying other modulations and signal designs for acoustic estimation in a similar way. The proposed algorithm estimates the system impulse response and uses the GEM to limit the effect of noise before applying deconvolution to estimate the time of arrival (TOA) to multiple targets with high accuracy.

We propose a novel neural network-based adaptive image denoiser, dubbased as Neural AIDE. Unlike other neural network-based denoisers, which typically apply supervised training to learn a mapping from a noisy patch to a clean patch, we formulate to train a neural network to learn context- based affine mappings that get applied to each noisy pixel. Our formulation enables using SURE (Stein’s Unbiased Risk Estimator)-like estimated losses of those mappings as empirical risks to minimize.

Motivation:
Speech signal is an important information carrier in many social applications such as WeChat and GoogleTalk；
Modern digital technologies have put the security of speech at risk.
Solution: Watermarking is a promising solution to protect the speech signals by embedding digital data into them [1, 2].
Problem:
Many existing methods cannot satisfy the requirements of watermarking, e.g., inaudibility and robustness, simultaneously;

Specific emitter identification (SEI) is gaining popularity since it can distinguish different individuals in same type of radar emitter under complex electromagnetic environment. However, classification of signals is still a challenging task when the feature has low physical representation. In this work, we propose a compressed sensing mask feature in ambiguity domain, which can significantly improve the recognition rate of civil flight radar emitters.

The detection of overlapping speech segments is of key importance in speech applications involving analysis of multi-party conversations. The detection problem is challenging because overlapping speech segments are typically captured as short speech utterances far-field microphone recordings. In this paper, we propose detection of overlap segments using a neural network architecture consisting of long-short term memory (LSTM) models. The neural network architecture learns the presence of overlap in speech by identifying the spectrotemporal structure of overlapping speech segments.