Browsing by Author "Blaauw, Merlijn"

Sort by: Order: Results:

  • A neural parametric singing synthesizer
    Blaauw, Merlijn; Bonada, Jordi, 1973- (International Speech Communication Association (ISCA), 2017)
    We present a new model for singing synthesis based on a modified version of the WaveNet architecture. Instead of modeling raw waveform, we model features produced by a parametric vocoder that separates the influence of ...
  • A neural parametric singing synthesizer modeling timbre and expression from natural songs
    Blaauw, Merlijn; Bonada, Jordi, 1973- (MDPI, 2017)
    We recently presented a new model for singing synthesis based on a modified version of the WaveNet architecture. Instead of modeling raw waveform, we model features produced by a parametric vocoder that separates the ...
  • A Vocoder based method for singing voice extraction
    Chandna, Pritish; Blaauw, Merlijn; Bonada, Jordi, 1973-; Gómez Gutiérrez, Emilia, 1975- (Institute of Electrical and Electronics Engineers (IEEE), 2019)
    This paper presents a novel method for extracting the vocal track from a musical mixture. The musical mixture consists of a singing voice and a backing track which may comprise of various instruments. We use a convolutional ...
  • Bird song synthesis based on hidden Markov models
    Bonada, Jordi, 1973-; Lachlan, Robert; Blaauw, Merlijn (International Speech Communication Association (ISCA), 2016)
    This paper focuses on the synthesis of bird songs using Hidden Markov Models (HMM). This technique has been widely used for speech modeling and synthesis. However, features and contextual factors typically used for human ...
  • Content based singing voice extraction from a musical mixture
    Chandna, Pritish; Blaauw, Merlijn; Bonada, Jordi, 1973-; Gómez Gutiérrez, Emilia, 1975- (Institute of Electrical and Electronics Engineers (IEEE), 2020)
    We present a deep learning based methodology for extracting the singing voice signal from a musical mixture based on the underlying linguistic content. Our model follows an encoder-decoder architecture and takes as input ...
  • Data efficient voice cloning for neural singing synthesis
    Blaauw, Merlijn; Bonada, Jordi, 1973-; Daido, Ryunosuke (Institute of Electrical and Electronics Engineers (IEEE), 2019)
    There are many use cases in singing synthesis where creating voices from small amounts of data is desirable. In text-to-speech there have been several promising results that apply voice cloning techniques to modern deep ...
  • Expressive singing synthesis based on unit selection for the singing synthesis challenge 2016
    Bonada, Jordi, 1973-; Umbert Morist, Martí; Blaauw, Merlijn (International Speech Communication Association (ISCA), 2016)
    Sample and statistically based singing synthesizers typically require a large amount of data for automatically generating expressive synthetic performances. In this paper we present a singing synthesizer that using two ...
  • Modeling and transforming speech using variational autoencoders
    Blaauw, Merlijn; Bonada, Jordi, 1973- (International Speech Communication Association (ISCA), 2016)
    Latent generative models can learn higher-level underlying factors from complex data in an unsupervised manner. Such models can be used in a wide range of speech processing applications, including synthesis, transformation ...
  • Modeling timbre for neural singing synthesis: methods for data-efficient, reduced effort voice creation, and fast and stable inference
    Blaauw, Merlijn (Universitat Pompeu Fabra, 2022-07-22)
    Singing synthesis has seen a notable surge in popularity in the last decade and a half. Music producers use this technology as an instrument, there is an audience for music with synthetic vocals, and an entire range of ...
  • Sequence-to-sequence singing synthesis using the feed-forward transformer
    Blaauw, Merlijn; Bonada, Jordi, 1973- (Institute of Electrical and Electronics Engineers (IEEE), 2020)
    We propose a sequence-to-sequence singing synthesizer, which avoids the need for training data with pre-aligned phonetic and acoustic features. Rather than the more common approach of a content-based attention mechanism ...
  • Statistical modeling of bowing control applied to violin sound synthesis
    Maestre Gómez, Esteban; Blaauw, Merlijn; Bonada, Jordi, 1973-; Guaus, Enric; Pérez Carrillo, Alfonso Antonio, 1977- (Institute of Electrical and Electronics Engineers (IEEE), 2010)
    Excitation-continuous music instrument control patterns are often not explicitly represented in current sound synthesis techniques when applied to automatic performance. Both physical model-based and sample-based synthesis ...
  • WGansing: a multi-voice singing voice synthesizer based on the Wasserstein-Gan
    Chandna, Pritish; Blaauw, Merlijn; Bonada, Jordi, 1973-; Gómez Gutiérrez, Emilia, 1975- (Institute of Electrical and Electronics Engineers (IEEE), 2019)
    We present a deep neural network based singing voice synthesizer, inspired by the Deep Convolutions Generative Adversarial Networks (DCGAN) architecture and optimized using the Wasserstein-GAN algorithm. We use vocoder ...