Speaker Representations for Speaker Adaptation in Multiple Speakers' BLSTM-RNN-Based Speech Synthesis.
Yi ZhaoDaisuke SaitoNobuaki MinematsuPublished in: INTERSPEECH (2016)
Keyphrases
- speech recognition
- speech synthesis
- speaker adaptation
- speaker dependent
- vocal tract
- speaker independent
- automatic speech recognition
- speech recognizer
- prosodic features
- hidden markov models
- language model
- speech signal
- speaker identification
- nearest neighbor
- recurrent neural networks
- maximum likelihood
- noisy environments
- pattern recognition
- speaker recognition
- speech recognition systems
- neural network
- multi modal
- image processing
- feature selection
- machine learning