Encoding Speaker-Specific Latent Speech Feature for Speech Synthesis.
Jungil KongJunmo LeeJeongmin KimBeomjeong KimJihoon ParkDohee KongChangheon LeeSangjin KimPublished in: CoRR (2023)
Keyphrases
- neural network
- speech synthesis
- speech recognition
- prosodic features
- vocal tract
- text to speech
- pattern recognition
- speech corpus
- automatic speech recognition
- speech signal
- speaker identification
- hidden markov models
- speech recognizer
- domain specific
- cepstral coefficients
- speaker dependent
- speaker recognition
- language model
- speaker independent
- feature vectors
- data mining