An Investigation of DNN-Based Speech Synthesis Using Speaker Codes.
Nobukatsu HojoYusuke IjimaHideyuki MizunoPublished in: INTERSPEECH (2016)
Keyphrases
- speech synthesis
- speech recognition
- prosodic features
- vocal tract
- text to speech
- speaker identification
- automatic speech recognition
- hidden markov models
- speaker dependent
- speaker verification
- error correction
- speech signal
- pattern recognition
- noisy environments
- language model
- logical operations
- information retrieval
- speaker diarization
- error correcting codes
- error correcting
- error control
- training process
- speaker adaptation
- data sets
- speech corpus