Parameter Generation Algorithms for Text-To-Speech Synthesis with Recurrent Neural Networks
By Viacheslav Klimkov, Alexis Moinet, Adam Nadolski, Thomas Drugman. 2018
5 citations recorded by the source corpus.
Recurrent Neural Networks (RNN) have recently proved to be effective in acoustic modeling for TTS. Various techniques such as the Maximum Likelihood Parameter Generation (MLPG) algorithm have been naturally inherited from the HMM-based speech synthesis framework. This paper investigates in which situations parameter generation and variance restoration approaches help for RNN-based TTS. We explore how their performance is affected by various factors such as the choice of the loss function, the application of regularization methods and the amount of training data. We propose an efficient way to calculate MLPG using a convolutional kernel. Our results show that the use of the L1 loss with proper regularization outperforms any system built with the conventional L2 loss and does not require to apply MLPG (which is necessary otherwise). We did not observe perceptual improvements when embedding MLPG into the acoustic model. Finally, we show that variance restoration approaches are important for cepstral features but only yield minor perceptual gains for the prediction of F0.
Subfields: Artificial Intelligence, Signal Processing
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Mingbo Ma
- Liang Huang
- Junkun Chen
- Renjie Zheng
- Richard He Bai
- Xintong Li
- Daniel Quernheim
- Mingxuan Wang
In Signal Processing
Citations in the corpus
- A3T: Alignment-Aware Acoustic and Text Pretraining for Speech Synthesis and Editing (2022, positive): “5(e), which conforms to the previous finding (Klimkov et al., 2018) that L1 loss is better than L2 loss for speech synthesis.”