Fast, Compact, and High Quality LSTM-RNN Based Statistical Parametric Speech Synthesizers for Mobile Devices.
Heiga ZenYannis AgiomyrgiannakisNiels EgbertsFergus HendersonPrzemyslaw SzczepaniakPublished in: INTERSPEECH (2016)
Keyphrases
- recurrent neural networks
- mobile devices
- high quality
- long short term memory
- nearest neighbor
- neural network
- audio visual
- speech recognition
- data driven
- mobile learning
- context aware
- learning activities
- statistical analysis
- mobile phone
- ground truth
- statistical models
- kernel density estimators
- feed forward
- wifi
- computing devices
- text to speech
- spoken language
- mobile users
- mobile applications
- statistical information
- automatic speech recognition
- mobile environments
- smart phones
- noisy environments
- linear prediction
- statistical methods
- low quality
- embedded devices
- location based services
- tablet computers