Multi-output RNN-LSTM for multiple speaker speech synthesis and adaptation.
Santiago PascualAntonio BonafontePublished in: EUSIPCO (2016)
Keyphrases
- language model
- speech recognition
- speech synthesis
- recurrent neural networks
- speaker adaptation
- automatic speech recognition
- prosodic features
- vocal tract
- speaker identification
- nearest neighbor
- speech corpus
- long short term memory
- input data
- learning algorithm
- genetic algorithm
- machine learning
- feed forward
- hidden markov models
- pattern recognition
- neural network
- data sets
- database