Description
ClariNet is an end-to-end text-to-speech architecture. Unlike previous TTS systems which use text-to-spectogram models with a separate waveform synthesizer (vocoder), ClariNet is a text-to-wave architecture that is fully convolutional and can be trained from scratch. In ClariNet, the WaveNet module is conditioned on the hidden states instead of the mel-spectogram. The architecture is otherwise based on Deep Voice 3.
Papers Using This Method
Clarinet: A Music Retrieval System2022-10-23Learning from a Complementary-label Source Domain: Theory and Algorithms2020-08-04Clarinet: A One-step Approach Towards Budget-friendly Unsupervised Domain Adaptation2020-07-29Multi-Speaker End-to-End Speech Synthesis2019-07-09Non-Autoregressive Neural Text-to-Speech2019-05-21Neural source-filter waveform models for statistical parametric speech synthesis2019-04-27ClariNet: Parallel Wave Generation in End-to-End Text-to-Speech2018-07-19