On the training of DNN-based average voice model for speech synthesis

14 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.

Deep Voice 2: Multi-Speaker Neural Text-to-Speech (2017, methodology): “DNN-based systems (e.g., Yang et al., 2016) have also been used to build average voice models, with i-vectors representing speakers as additional inputs and separate output layers for each target speaker.”
Data Efficient Voice Cloning from Noisy Samples with Domain Adversarial Training (2020, background): “Therefore, building target voice with few minutes or even few samples data, or voice cloning , has drawn many interests lately [2, 3, 4, 5].”
Controllable Emotion Transfer For End-to-End Speech Synthesis (2020, unknown): “When emotional data is limited with only a few samples, model adaptation [21–23] is often adopted on the average or neutral voice model that has been trained beforehand using a sizable set of data.”
A DNN-based Mandarin-Tibetan cross-lingual speech synthesis (2018, methodology): “for training the DNN-based acoustic models proposed in [21].”