Speech synthesis using artificial neural networks trained on cepstral coefficients

By Christine Tuerk, Tony A. Robinson. 1993

How researchers see this paper

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

In Natural Language Processing

Citations in the corpus

WaveNet: A Generative Model for Raw Audio (2016, background): “…models, such as hidden Markov models (HMMs) (Yoshimura, 2002), feed-forward neural networks (Zen et al., 2013), and recurrent neural networks (Tuerk & Robinson, 1993; Karaali et al., 1997; Fan et al., 2014), is trained from the extracted vocoder parameters and linguistic features as where Λ…”
Merlin: An Open Source Neural Network Speech Synthesis System (2016, methodology): “In the 1990s, neural networks had already been used to learn the relationship between linguistic and acoustic features [7, 8, 9], as duration models to predict segment durations [10], and to extract linguistic features from raw text input [11].”
Unidirectional long short-term memory recurrent neural network with recurrent output layer for low-latency speech synthesis (2015, methodology): “Tuerk and Ronbinson [16] and Karaani et al. [17] applied standard RNNs to speech synthesis, whereas long short-term memory RNNs (LSTM- RNNs) [18], which can capture long-term dependencies, were recently applied to acoustic modeling for SPSS [19] [20] [21]; Fan et al. and Fernandez et al. applied dee”
TalkNet 2: Non-Autoregressive Depth-Wise Separable Convolutional Model for Speech Synthesis with Explicit Pitch and Duration Prediction (2021, methodology): “Neural networks have been used for TTS in 1990 [12, 13, 14, 15].”
Recent Advances in Recurrent Neural Networks (2017, methodology): “RNNs were first used for speech synthesis to leverage these sequential dependencies [109], [110], and were then replaced with LSTM models to better learn long term sequential dependencies [111].”