Search

Recent advances in image, video, text and audio generative techniques, and their use by the general public, are leading to new forms of content generation. Usually, each modality was approached separately, which poses limitations. The automatic sound recording of visual sequences is one of the greatest challenges for the automatic generation of multimodal content. We present a processing flow that, starting from images extracted from videos, is able to sound them. We work with pre-trained models that employ complex encoders, contrastive learning, and multiple modalities, allowing complex representations of the sequences for their sonorization. The proposed scheme proposes different possibilities for audio mapping and text guidance. We evaluated the scheme on a dataset of frames extracted from a commercial video game and sounds extracted from the Freesound platform. Subjective tests have evidenced that the proposed scheme is able to generate and assign audios automatically and conveniently to images. Moreover, it adapts well to user preferences, and the proposed objective metrics show a high correlation with the subjective ratings., Comment: 10 pages, in Spanish, Tecniac\'ustica

This article arises as an alternative solution to the problem of estimating the future population of some care centers for children and adolescents at social risk. The population of these centers fluctuates from month to month due to various social, economic and political factors, so there is no way to calculate exactly how many children will enter and how many will leave. To make the estimate, a mathematical model was developed to estimate the population of the centers in the following month based on linear regressions and it was implemented in a spreadsheet to facilitate its use., Comment: Presented at "Congreso de Electr\'onica e Inform\'atica 2010", Universidad Centroamericana "Jos\'e Sime\'on Ca\~nas", in Spanish language

This article describes the features of a compiler for a superset language of the well-known PL/0 created by Niklaus Wirth. The main feature is that it implements the build phases in such a way that the information passed between each one is reflected as an XML file., Comment: in Spanish language. Presented at "Congreso de Electr\'onica e Inform\'atica 2010", Universidad Centroamericana "Jos\'e Sime\'on Ca\~nas"

This article describes an implementation of low-cost portable touch screen technology, applied to university teaching, using as a base the remote control of the Nintendo Wii console (known as Wiimote), a normal projector, a computer and free software. The purpose is to show the feasibility of such implementation to improve teaching/learning processes, without incurring high costs associated with unaffordable technological equipment, special infrastructure in classrooms, or expensive computer programs. Also included is a summary of a test of the system in two college courses., Comment: in Spanish language. Presented at "Congreso de Electr\'onica e Inform\'atica 2010", Universidad Centroamericana "Jos\'e Sime\'on Ca\~nas"