Igor Muzetti Pereira

Genís Plaja-Roglans, Yun-Ning Hung, Xavier Serra et al.

Separating the individual elements in a musical mixture is an essential process for music analysis and practice. While this is generally addressed using neural networks optimized to mask or transform the time-frequency representation of a mixture to extract the target sources, the flexibility and generalization capabilities of generative diffusion models are giving rise to a novel class of solutions for this complicated task. In this work, we explore singing voice separation from real music recordings using a diffusion model which is trained to generate the solo vocals conditioned on the corresponding mixture. Our approach improves upon prior generative systems and achieves competitive objective scores against non-generative baselines when trained with supplementary data. The iterative nature of diffusion sampling enables the user to control the quality-efficiency trade-off, and also refine the output when needed. We present an ablation study of the sampling algorithm, highlighting the effects of the user-configurable parameters.

Igor Muzetti Pereira, Tiago Garcia de Senna Carneiro, Eduardo Figueiredo

The growing demand for connected devices and the increase in investments in the Internet of Things (IoT) sector induce the growth of the market for this technology. IoT permeates all areas of life of an individual, from smartwatches to entire home assistants and solutions in different areas. The IoT concept is gradually increasing all over the globe. IoT projects induce an articulation of studies in software engineering to prepare the development and operation of software systems materialized in physical objects and structures interconnected with embedded software and hosted in clouds. IoT projects have boundaries between development and operation stages. This study search for evidence in scientific literature to support these boundaries through Development and Operations (DevOps) principles. We rely on a Systematic Literature Review to investigate the relations of DevOps in IoT software systems. As a result, we identify concepts, characterize the benefits and challenges in the context of knowledge previously reported in primary studies in the literature. The main contributions of this paper are: (i) discussion of benefits and challenges for DevOps in IoT software systems, (ii) identification of tools, concepts, and programming languages used, and, (iii) perceived pipeline for this kind of software development.