Abstract
The application of Deep Learning techniques to point clouds for urban object classification is limited by the large number of samples needed. Acquiring and tagging point clouds is more expensive and tedious labour than its image equivalent process. Point cloud online datasets contain few samples for Deep Learning or not always the desired classes This work focuses on minimizing the use of point cloud samples for neural network training in urban object classification. The method proposed is based on the conversion of point clouds to images (pc-images) because it enables: the use of Convolutional Neural Networks, the generation of several samples (images) per object (point clouds) by means of multi-view, and the combination of pc-images with images from online datasets (ImageNet and Google Images). The study is conducted with ten classes of objects extracted from two street point clouds from two different cities. The network selected for the job is the InceptionV3. The training set consists of 5000 online images with a variable percentage (0% to 10%) of pc-images. The validation and testing sets are composed exclusively of pc-images. Although the network trained only with online images reached 47% accuracy, the inclusion of a small percentage of pc-images in the training set improves the classification to 99.5% accuracy with 6% pc-images. The network is also applied at IQmulus & TerraMobilita Contest dataset and it allows the correct classification of elements with few samples.

Abstract
Advances in technology are leading to more and more devices integrating sensors capable of acquiring data quickly and with high accuracy. Point clouds are no exception. Therefore, there is increased research interest in the large amount of available light detection and ranging (LiDAR) data by point cloud classification using artificial intelligence. Nevertheless, point cloud labeling is a time-consuming task. Hence the amount of labeled data is still scarce. Data synthesis is gaining attention as an alternative to increase the volume of classified data. At the same time, the amount of Building Information Models (BIMs) provided by manufacturers on website databases is increasing. In line with these recent trends, this paper presents a deep-learning framework for classifying point cloud objects based on synthetic data sets created from BIM objects. The method starts by transforming BIM objects into point clouds deriving a data set consisting of 21 object classes characterized with various perturbation patterns. Then, the data set is split into four subsets to carry out the evaluation of synthetic data on the implemented flexible two-dimensional (2D) deep neural framework. In the latter, binary or greyscale images can be generated from point clouds by both orthographic or perspective projection to feed the network. Moreover, the surface variation feature was computed in order to aggregate more geometric information to images and to evaluate how it influences the object classification. The overall accuracy is over 85% in all tests when orthographic images are used. Also, the use of greyscale images representing surface variation improves performance in almost all tests although the computation of this feature may not be robust in point clouds with complex geometry or perturbations. © 2022 American Society of Civil Engineers.

Abstract
Advances in technology are leading to more and more devices integrating sensors capable of acquiring data quickly and with high accuracy. Point clouds are no exception. Therefore, there is increased research interest in the large amount of available light detection and ranging (LiDAR) data by point cloud classification using artificial intelligence. Nevertheless, point cloud labeling is a time-consuming task. Hence the amount of labeled data is still scarce. Data synthesis is gaining attention as an alternative to increase the volume of classified data. At the same time, the amount of Building Information Models (BIMs) provided by manufacturers on website databases is increasing. In line with these recent trends, this paper presents a deep-learning framework for classifying point cloud objects based on synthetic data sets created from BIM objects. The method starts by transforming BIM objects into point clouds deriving a data set consisting of 21 object classes characterized with various perturbation patterns. Then, the data set is split into four subsets to carry out the evaluation of synthetic data on the implemented flexible two-dimensional (2D) deep neural framework. In the latter, binary or greyscale images can be generated from point clouds by both orthographic or perspective projection to feed the network. Moreover, the surface variation feature was computed in order to aggregate more geometric information to images and to evaluate how it influences the object classification. The overall accuracy is over 85% in all tests when orthographic images are used. Also, the use of greyscale images representing surface variation improves performance in almost all tests although the computation of this feature may not be robust in point clouds with complex geometry or perturbations. (C) 2022 American Society of Civil Engineers.

Abstract

Abstract
In this paper we focus on the real-time frequency domain analysis of speech signals, and on the extraction of suitable and perceptually meaningful features that are related to the glottal source and that may pave the way for robust speaker identification and voice register classification. We take advantage of an analysis-synthesis framework derived from an audio coding algorithm in order to estimate and model the relative delays between the different harmonics reflecting the contribution of the glottal source and the group delay of the vocal tract filter. We show in this paper that this approach effectively captures the shape invariance of a periodic signal and may be suited to monitor and extract in real-time perceptually important features correlating well with specific voice registers or with a speaker unique sound signature. A first validation study is described that confirms the competitive performance of the proposed approach in the automatic classification of the breathy, normal and pressed voice phonation types.

Abstract
In this paper, an accurate method that estimates the HNR from sustained vowels based on harmonic structure modeling is proposed. Basically, the proposed algorithm creates an accurate harmonic structure where each harmonic is parameterized by frequency, magnitude and phase. The harmonic structure is then synthesized and assumed as the harmonic component of the speech signal. The noise component can be estimated by subtracting the harmonic component from the speech signal. The proposed algorithm was compared to others HNR extraction algorithms based on spectral, cepstral and time domain methods, and using different performance measures.