Articulatory Control of HMM-Based Parametric Speech Synthesis Using Feature-Space-Switched Multiple Regression

64 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Deep Learning: Methods and Applications (2014, background): “Similar trajectory HMMs also form the basis for parametric speech synthesis (Zen et al., 2011; Zen et al., 2012; Ling et al., 2013; Shannon et al., 2013).”
A tutorial survey of architectures, algorithms, and applications for deep learning (2014, background): “Similar trajectory HMMs also form the basis for parametric speech synthesis (Zen et al., 2011; Zen et al., 2012; Ling et al., 2013; Shannon et al., 2013).”
Deep Encoder-Decoder Models for Unsupervised Learning of Controllable Speech Synthesis (2018, methodology): “MR-HMMs and their extensions have been used for smoothly controlling properties such as speaking style [20], [21] or articulation [22].”
Speech Synthesis Based on Hidden Markov Models (2013, methodology): “An HMM-based speech synthesis system having such articulatory features as optional configurable inputs allows users to manipulate HMM-based synthetic speech via articulation [32], [33], which becomes a good link and contrast to conventional articulatory synthesis [1].”
Sentence-level control vectors for deep neural network speech synthesis (2015, result): “This is consistent with previous experience in controllable speech synthesis: [24] notes that to properly steer a data-driven articulatory-controllable to produce modified vowels, tongue movements must be specified of a far greater magnitude than those observed in the training data.”