DNN-Based Speech Synthesis Using Speaker Codes.
Nobukatsu HojoYusuke IjimaHideyuki MizunoPublished in: IEICE Trans. Inf. Syst. (2018)
Keyphrases
- speech synthesis
- speech recognition
- prosodic features
- vocal tract
- text to speech
- automatic speech recognition
- hidden markov models
- speech signal
- training process
- error correction
- speaker identification
- speech corpus
- speaker recognition
- language model
- speaker dependent
- speaker adaptation
- neural network
- pattern recognition
- speaker diarization
- signal to noise ratio
- decoding algorithm
- error correcting codes
- error control
- learning algorithm
- genetic algorithm