A Comparison of Expressive Speech Synthesis Approaches based on Neural Network
Authors:
Open Access
- 19 October 2018
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 15-20
Abstract
No abstract availableKeywords
Funding Information
- the national key Research and Development Program of China (2017YFB1002102)
- The National Natural Science Foundation of China (61571363)
This publication has 13 references indexed in Scilit:
- On line emotion detection using retrainable deep neural networks2016
- Multi-Language Multi-Speaker Acoustic Modeling for LSTM-RNN Based Statistical Parametric Speech Synthesis2016
- Speaker Representations for Speaker Adaptation in Multiple Speakers’ BLSTM-RNN-Based Speech Synthesis2016
- An Investigation of DNN-Based Speech Synthesis Using Speaker Codes2016
- Deep Learning for Acoustic Modeling in Parametric Speech Generation: A systematic review of existing techniques and future trendsIEEE Signal Processing Magazine, 2015
- Multi-speaker modeling and speaker adaptation for DNN-based TTS synthesis2015
- Deep neural networks employing Multi-Task Learning and stacked bottleneck features for speech synthesis2015
- On the training aspects of Deep Neural Network (DNN) for parametric TTS synthesis2014
- Restructuring speech representations using a pitch-adaptive time–frequency smoothing and an instantaneous-frequency-based F0 extraction: Possible role of a repetitive structure in soundsSpeech Communication, 1999
- Long Short-Term MemoryNeural Computation, 1997