Fast, Compact, and High Quality LSTM-RNN Based Statistical Parametric Speech Synthesizers for Mobile Devices.
Heiga ZenYannis AgiomyrgiannakisNiels EgbertsFergus HendersonPrzemyslaw SzczepaniakPublished in: CoRR (2016)
Keyphrases
- recurrent neural networks
- mobile devices
- high quality
- long short term memory
- mobile phone
- mobile learning
- statistical methods
- higher quality
- learning activities
- neural network
- context aware
- feed forward
- ground truth
- statistical analysis
- speech recognition
- artificial neural networks
- nearest neighbor
- location aware
- statistical information
- speech signal
- location based services
- mobile applications
- audio visual
- desktop computers
- computing devices
- data driven
- mobile users
- mobile technologies
- data sets
- pattern recognition
- statistical models
- user interface
- recognition engine
- kernel density estimators