Unsupervised learning for text-to-speech synthesis

55 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.

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].”
Unsupervised Learning For Sequence-to-sequence Text-to-speech For Low-resource Languages (2020, background): “Some studied introducing distributional textual or linguistic information into TTS within the traditional TTS paradigm [13–15].”
Word embedding for recurrent neural network based TTS synthesis (2015, background): “However, it should be noted that vector space representation is a byproduct of singular value decomposition of a matrix of an information retrieval task [17], while word embedding discussed in this paper are all trained using neural”
Combining a vector space representation of linguistic context with a deep neural network for text-to-speech synthesis (2013, methodology): “[15] describes in detail our approach to the unsupervised construction of representations for context modelling in TTS – here we just give a brief summary of how this approach works.”
Unsupervised Learning for Expressive Speech Synthesis (2017, unknown): “Some suggestions to approach this problem were made for instance in [11, 39, 7, 23], where data was clustered by different criteria to select training data and similar ideas.”