Combining a vector space representation of linguistic context with a deep neural network for text-to-speech synthesis

By Heng Lu, Simon King, Oliver Watts. 2013

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.

1. Xu Tan
2. Wei-Ning Hsu
3. Junichi Yamagishi
4. Yu Zhang
5. Heiga Zen
6. Xin Eric Wang
7. Yu-An Chung
8. Tao Qin

Citations in the corpus

• Semi-supervised Training for Improving Data Efficiency in End-to-end Speech Synthesis (2018, background): “There exists previous work studying the application of unsupervised and weakly supervised learning for TTS [4, 5, 6, 7].”
• Unidirectional long short-term memory recurrent neural network with recurrent output layer for low-latency speech synthesis (2015, background): “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] [5] [6] [7].”
• TTS synthesis with bidirectional LSTM based recurrent neural networks (2014, methodology): “[5] employed phone, letter and Vector Space Model (VSM) based binary or continuous features as input features, and frame or state for output predictions in DNN based synthesis.”
• Deep neural networks employing Multi-Task Learning and stacked bottleneck features for speech synthesis (2015, methodology): “The second problem – frame-by-frame independence – arises in many SPSS systems where predicted values for consecutive acoustic states or frames are conditionally independent of one another given their linguistic contexts.”
• Unsupervised Learning for Expressive Speech Synthesis (2017, methodology): “(2015); Zen and Senior (2014), or Lu et al. (2013), this latter one adding semantic vector representations as a linguistic input feature.”
• Word embedding for recurrent neural network based TTS synthesis (2015, background): “[16] has tested DNN based TTS system with vector space representation and its result is not very positive.”
• Deep mixture density networks for acoustic modeling in statistical parametric speech synthesis (2014, background): “DNN-based acoustic models offer an efficient and distributed representation of complex dependencies between linguistic and acoustic features and have shown the potential to produce naturally-sounding synthesized speech [13, 15].”
• Spoofing and countermeasures for speaker verification: A survey (2015, background): “In addition to the four major approaches, inspired by advances in deep neural network (DNN)-based speech recognition (Hinton et al., 2012), new data-driven, DNN-based approaches have also been actively investigated (Zen et al., 2013; Ling et al., 2013; Lu et al., 2013; Qian et al., 2014).”
• Phonological vocoding using artificial neural networks (2015, background): “Index Terms— Parametric vocoding, low bit rate speech coding, phonology.”
• 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].”
• Investigating gated recurrent neural networks for speech synthesis (2016, unknown): “In [4, 5, 6, 7, 8], feed-forward neural networks are employed to map a linguistic representation derived from input text directly to acoustic features.”
• Merlin: An Open Source Neural Network Speech Synthesis System (2016, background): “Deep feedforward neural networks (DNNs) as a deep conditional model are the model popular model in the literature to map linguistic features to acoustic features directly [17, 18, 19, 20, 21].”