J
Jordi Bonada
Researcher at Pompeu Fabra University
Publications - 147
Citations - 2677
Jordi Bonada is an academic researcher from Pompeu Fabra University. The author has contributed to research in topics: Violin & Signal. The author has an hindex of 29, co-authored 145 publications receiving 2483 citations. Previous affiliations of Jordi Bonada include Yamaha Corporation.
Papers
More filters
Journal ArticleDOI
A Neural Parametric Singing Synthesizer Modeling Timbre and Expression from Natural Songs
Merlijn Blaauw,Jordi Bonada +1 more
TL;DR: This work extends the proposed model for singing synthesis to include additional components for predicting F0 and phonetic timings from a musical score with lyrics and compares its method to existing statistical parametric, concatenative, and neural network-based approaches using quantitative metrics as well as listening tests.
Journal ArticleDOI
Synthesis of the Singing Voice by Performance Sampling and Spectral Models
Jordi Bonada,Xavier Serra +1 more
TL;DR: The paper presents a singing voice synthesizer, pointing out the main issues and complexities emerging along its design, especially in the areas of expression, spectral modeling and sonic space design.
Proceedings Article
Score-Performance Matching using HMMs
TL;DR: An implementation of a score-performance matching, capable of score following, based on a stochastic approach using Hidden Markov Models, is described.
Proceedings Article
Automatic Technique in Frequency Domain for Near-Lossless Time-Scale Modification of Audio
TL;DR: A new frequency domain approach is proposed for an automatic near-lossless time stretching of audio for time-scale modification of sounds.
PatentDOI
Voice converter with extraction and modification of attribute data
TL;DR: In this article, an apparatus is constructed for converting an input voice signal into an output voice signal according to a target voice signal, where the original attribute data is characteristic of the original voice signal and the target attribute data are derived from at least the target sinusoidal components.