• Optimal training in continuous flat-fading massive MIMO systems

  Truong, Kien T.; Lozano Solsona, Angel; Heath, R. W., Jr. (UNLISTED PUBLISHERVDE Verlag, 2014)

  Massive multiple-input multiple-output (MIMO) communication promises the full potential of MIMO communication realized through the deployment of hundreds of antennas at each base station. Accurate channel state information ...
• Exploring the effectiveness of video viewing in an introductory x-MOOC of algebra

  Triay, Joan; Minguillón, Julià; Sancho Vinuesa, Teresa; Daza, Vanesa (CEUR Workshop Proceedings, 2016)

  The huge amount of gathered data in a MOOC allows providing professors and course managers with insightful information about real course usage and consumption. The main aim of this work is to explore how efficient ...
• Fully end-to-end composite recurrent convolution network for deformable facial tracking in the wild

  Sukno, Federico Mateo; Aspandi, Decky; Martínez, Oriol; Sukno, Federico Mateo; Binefa i Valls, Xavier (Institute of Electrical and Electronics Engineers (IEEE), 2019)

  Human facial tracking is an important task in computer vision, which has recently lost pace compared to other facial analysis tasks. The majority of current available tracker possess two major limitations: their little use ...
• Decentralized AP selection using multi-armed bandits: opportunistic ε-greedy with stickiness

  Carrascosa Zamacois, Marc (Institute of Electrical and Electronics Engineers (IEEE), 2020)

  WiFi densification leads to the existence of multiple overlapping coverage areas, which allows user stations (STAs) to choose between different Access Points (APs). The standard WiFi association method makes the STAs select ...
• Mood classification using listening data

  Korzeniowski, Filip; Nieto Caballero, Oriol; McCallum, Matthew C.; Won, Minz; Oramas, Sergio; Schmidt, Erik M. (International Society for Music Information Retrieval (ISMIR), 2020)

  The mood of a song is a highly relevant feature for exploration and recommendation in large collections of music. These collections tend to require automatic methods for predicting such moods. In this work, we show that ...
• Combining musical features for cover detection

  Doras, Guillaume; Yesiler, Furkan; Serrà Julià, Joan; Gómez Gutiérrez, Emilia, 1975-; Peeters, Geoffroy (International Society for Music Information Retrieval (ISMIR), 2020)

  Recent works have addressed the automatic cover detection problem from a metric learning perspective. They employ different input representations, aiming to exploit melodic or harmonic characteristics of songs and yield ...
• Less is more: faster and better music version identification with embedding distillation

  Serrà Julià, Joan; Yesiler, Furkan; Gómez Gutiérrez, Emilia, 1975- (International Society for Music Information Retrieval (ISMIR), 2020)

  Version identification systems aim to detect different renditions of the same underlying musical composition (loosely called cover songs). By learning to encode entire recordings into plain vector embeddings, recent systems ...
• CATOTRON – A Neural text-to-speech system in catalan

  Külebi, Baybars; Öktem, Alp; Peiró Lilja, Àlex; Pascual, Santiago; Farrús, Mireia (International Speech Communication Association (ISCA), 2020)

  We present Catotron, a neural network-based open-source speech synthesis system in Catalan. Catotron consists of a sequence-to-sequence model trained with two small opensource datasets based on semi-spontaneous and read ...
• Naturalness enhancement with linguistic information in end-to-end TTS using unsupervised parallel encoding

  Peiró Lilja, Àlex; Farrús, Mireia (International Speech Communication Association (ISCA), 2020)

  State-of-the-art end-to-end speech synthesis models have reached levels of quality close to human capabilities. However, there is still room for improvement in terms of naturalness, related to prosody, which is essential ...
• Deep learning based source separation applied to choir ensembles

  Petermann, Darius; Chandna, Pritish; Cuesta, Helena; Bonada, Jordi, 1973-; Gómez Gutiérrez, Emilia, 1975- (International Society for Music Information Retrieval (ISMIR), 2020)

  Choral singing is a widely practiced form of ensemble singing wherein a group of people sing simultaneously in polyphonic harmony. The most commonly practiced setting for choir ensembles consists of four parts; Soprano, ...
• Multiple F0 estimation in vocal ensembles using convolutional neural networks

  Cuesta, Helena; McFee, Brian; Gómez Gutiérrez, Emilia, 1975- (International Society for Music Information Retrieval (ISMIR), 2020)

  This paper addresses the extraction of multiple F0 values from polyphonic and a cappella vocal performances using convolutional neural networks (CNNs). We address the major challenges of ensemble singing, i.e., all melodic ...
• A deep learning based analysis-synthesis framework for unison singing

  Chandna, Pritish; Cuesta, Helena; Gómez Gutiérrez, Emilia, 1975- (International Society for Music Information Retrieval (ISMIR), 2020)

  Unison singing is the name given to an ensemble of singers simultaneously singing the same melody and lyrics. While each individual singer in a unison sings the same principle melody, there are slight timing and pitch ...
• Engineering and social responsibility: a case-based course

  Nadeu Camprubí, Climent; Mariño Acebal, José B.; Farrús, Mireia (2007)

  This paper describes a teaching experience. In spring 2006, a new optional course about engineering and responsibility was started at the Universitat Politècnica de Catalunya. Its methodology was mainly based on preparation ...
• An experience on statistical machine translation between Spanish and the regional languages of Spain

  Farrús, Mireia; Iglesias, Gonzalo; Henríquez, Carlos; Poch, Marc; Muñoz, Roberto; Ezeiza, Nerea; Banga, Eduardo R.; Mariño Acebal, José B. (2009)

  Statistical machine translation systems between Spanish and other regional languages from Spain has become an interest of research during the last decade. However, regional languages are usually characterized by the lack ...
• Machine translation in medicine: a quality analysis of statistical machine translation in the medical domain

  Costa-jussà, Marta R.; Farrús, Mireia; Serrano Pons, Jordi (2012)

  Machine translation is evolving quite rapidly in terms of quality. Nowadays, we have several machine translation systems available in the web, which provide reasonable translations. However, these systems are not perfect, ...
• DCASE-models: a phyton library for computational environmental sound analysis using deep-learning models

  Zinemanas, Pablo; Hounie, Ignacio; Cancela, Pablo; Font, Frederic; Rocamora, Martín; Serra, Xavier (Detection and Classication of Acoustic Scenes and Events (DCASE), 2020)

  This document presents DCASE-models, an open–source Python library for rapid prototyping of environmental sound analysis systems, with an emphasis on deep–learning models. Together with a collection of functions for ...
• Shorter quadratic QA-NIZK proofs

  Daza, Vanesa; González, Alonso; Pindado, Zaira; Ràfols, Carla; Silva, Javier (Springer, 2019)

  Despite recent advances in the area of pairing-friendly Non-Interactive Zero-Knowledge proofs, there have not been many efficiency improvements in constructing arguments of satisfiability of quadratic (and larger degree) ...
• Cross-dataset music emotion recognition: an end-to-end approach

  Pandrea, Ana Gabriela; Gómez Cañón, Juan Sebastián; Herrera Boyer, Perfecto, 1964- (2020)

  The topic of Music Emotion Recognition (MER) evolved as music is a fascinating expression of emotions, yet it faces challenges given its subjectivity. Because each language has its particularities in terms of sound and ...
• Joyful for you and tender for us: the influence of individual characteristics and language on emotion labeling and classification

  Gómez Cañón, Juan Sebastián; Cano, Estefanía; Herrera Boyer, Perfecto, 1964-; Gómez Gutiérrez, Emilia, 1975- (International Society for Music Information Retrieval (ISMIR), 2020)

  Tagging a musical excerpt with an emotion label may result in a vague and ambivalent exercise. This subjectivity entangles several high-level music description tasks when the computational models built to address them ...
• Designing fully secure protocols for secure two-party computation of constant-domain functions

  Daza, Vanesa; Makriyannis, Nikolaos (Springer, 2017)

  In a sense, a two-party protocol achieves fairness if the output from the computation is obtained simultaneously by both parties. A seminal result by Cleve (STOC 1986) states that fairness is impossible, in general. ...

View more