Word embedding for recurrent neural network based TTS synthesis

57 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.

A Survey on Neural Speech Synthesis (2021, methodology): “Self-supervised pretraining methods can be leveraged to enhance the language understanding or speech generation capabilities [51, 368, 433, 78].”
Mixed-Phoneme BERT: Improving BERT with Mixed Phoneme and Sup-Phoneme Representations for Text to Speech (2022, background): “Recently, leveraging contextual representations learned from unlabeled text data to improve the TTS model has become a rising topic [10,15–18], which is also the focus of our paper.”
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].”
Acoustic Word Embeddings for End-to-End Speech Synthesis (2021, methodology): “[7] trains a word language model to obtain linguistic word embeddings and then uses them as part of the input features.”
Unsupervised Learning for Expressive Speech Synthesis (2017, methodology): “To name a few, [37] use word embeddings to substitute TOBI and POS tags in RNN-based synthesis achieving significant system improvement.”