Claim Your Author Page
Ensure your research is discoverable on Semantic Scholar. Claiming your author page allows you to personalize the information displayed and manage publications.
Most speech processing techniques use magnitude spectrograms as front-end and are therefore by default discarding part of the signal: the phase. In order to overcome this limitation’ we propose an… (More)
This paper describes Task 2 of the DCASE 2018 Challenge, titled "General-purpose audio tagging of Freesound content with AudioSet labels". This task was hosted on the Kaggle platform as "Freesound… (More)
In this paper, we offer a structural contrast of a new economic geography model in Spain over three different periods: the 1920s, the 1960s, and the early years of the 21st century. In line with… (More)
The focus of this work is to study how to efficiently tailor Convolutional Neural Networks (CNNs) towards learning timbre representations from log-mel magnitude spectrograms. We first review the… (More)
The purpose of this paper is to analyse the determinants of the localisation of industrial activity in Spain during the second half of thenineteenth century and the effects of economic integration in… (More)
This paper examines whether access to markets had a significant influence on migration choices of Spanish internal migrants in the interwar years. In it we perform a structural contrast of a New… (More)
This paper analyses the relationship between spatial density of economic activity and interregional differences in the productivity of industrial labour in Spain during the period 1860–1999. In the… (More)
Comunicacio presentada al 18th International Society for Music Information Retrieval Conference celebrada a Suzhou, Xina, del 23 al 27 d'cotubre de 2017.
The lack of data tends to limit the outcomes of deep learning research, particularly when dealing with end-to-end learning stacks processing raw data such as waveforms. In this study, 1.2M tracks… (More)
The computer vision literature shows that randomly weighted neural networks perform reasonably as feature extractors. Following this idea, we study how non-trained (randomly weighted) convolutional… (More)