A Unified Speaker Adaptation Method for Speech Synthesis using Transcribed and Untranscribed Speech with Backpropagation.
Hieu-Thi LuongJunichi YamagishiPublished in: CoRR (2019)
Keyphrases
- back propagation
- speech synthesis
- speech recognition
- training algorithm
- neural network
- bp neural network
- feed forward neural networks
- neural nets
- multilayer perceptron neural network
- text to speech
- artificial neural networks
- maximum likelihood
- probabilistic model
- knowledge base
- information retrieval
- prosodic features
- speaker adaptation
- speech corpus
- machine learning