Collecting data using a UAV nomadic gateway, which serves as a "go-between" edge device between resource-limited end sensor devices and a cloud instance may lead to data quality issues. Power outages on end devices together with MCU lacking the system clock may not only make collected time series data incomplete but also disrupt timestamping of sequences of samples. The proposed data fusion method performed at the cloud side combines information from a number of sensors to align the sequences along time.

This paper presents 2D image processing approach to playback detection in automatic speaker verification (ASV) systems using spectrograms as speech signal representation. Three feature extraction and classification methods: histograms of oriented gradients (HOG) with support vector machines (SVM), HAAR wavelets with AdaBoost classifier and deep convolutional neural networks (CNN) were compared on different data partitions in respect of speakers or playback devices: for instance with different speakers in training and test subsets. The playback detection systems were trained and tested on two speech datasets S1and S2manufactured independently by two different institutions. The test error for both datasets oscillates about the level of 1% for HOG+SVM and even below it for CNN in bigger S1base. In cross validation scenario in which one base was used for training and second base for the test the results were very poor what suggests that the information relevant for playback detection appeared in each base in different way.