F0 contour prediction with a deep belief network-Gaussian process hybrid model

By Raul Fernandez, Asaf Rendel, Bhuvana Ramabhadran, Ron Hoory. 2013

38 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Signal Processing

How researchers see this paper

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

In Artificial Intelligence

In Signal Processing

Citations in the corpus

Deep Learning: Methods and Applications (2014, methodology): “Finally, in [115], the discriminative model of the DNN is used as a feature extractor that summarizes high-level structure from the raw acoustic features.”
Unidirectional long short-term memory recurrent neural network with recurrent output layer for low-latency speech synthesis (2015, unknown): “Introduction of the deep neural network (DNN) [3], which is a feed-forward artificial neural network with many hidden layers, has opened a new research direction for acoustic modeling in SPSS [4–7].”
A Deep Generative Architecture for Postfiltering in Statistical Parametric Speech Synthesis (2015, methodology): “A hybrid model which combines a DBN with an Gaussian process regression has been used for F0 modeling [8].”
Prosody contour prediction with long short-term memory, bi-directional, deep recurrent neural networks (2014, methodology): “…layer-wise pre-training pass using Restricted Boltzmann Machines for each layer, followed by (ii) a supervised end-to-end update of the weights using stochastic gradient descent to minimize the loss function in (2) and the back-propagation al-gorithm to evaluate the network derivatives [2].”
A DNN-based Mandarin-Tibetan cross-lingual speech synthesis (2018, methodology): “the successful application of deep neural networks(DNNs) to speech recognition [9], DNNs have also been applied to statistical parametric speech synthesis and achieved significant improvements [8].”
Deep mixture density networks for acoustic modeling in statistical parametric speech synthesis (2014, methodology): “They were also introduced as acoustic models for SPSS [13–15].”
Review of end-to-end speech synthesis technology based on deep learning (2021, methodology): “TTS methods based on deep learning have been widely researched [52, 131, 168, 247].”
Multi-output RNN-LSTM for multiple speaker speech synthesis with α-interpolation model (2016, background): “In the case of speech synthesis, many works included DNNs and DBNs to perform acoustic mappings and prosody prediction [2, 3, 4], Also, Recurrent Neural Networks (RNNs) and their variants, like the Long Short Term Memory (LSTM) architecture [5], have leveraged completely the sequences processing and”
Modeling Spectral Envelopes Using Restricted Boltzmann Machines and Deep Belief Networks for Statistical Parametric Speech Synthesis (2013, background): “In [29], a DNN which is pre-trained by the”