Speaker and language factorization in DNN-based TTS synthesis.
Yuchen FanYao QianFrank K. SoongLei HePublished in: ICASSP (2016)
Keyphrases
- text to speech
- prosodic features
- language learning
- functional programs
- programming language
- natural language
- speech synthesis
- audio visual
- speech recognition
- matrix factorization
- training process
- singular value decomposition
- database systems
- neural network
- automatic speech recognition
- language processing
- object oriented programming
- speaker identification
- program synthesis
- least squares