From Speaker Verification to Multispeaker Speech Synthesis, Deep Transfer with Feedback Constraint.
Zexin CaiChuxiong ZhangMing LiPublished in: INTERSPEECH (2020)
Keyphrases
- prosodic features
- speech synthesis
- speaker verification
- speech recognition
- text to speech
- noisy environments
- speaker recognition
- vocal tract
- audio visual
- language identification
- hidden markov models
- speech signal
- automatic speech recognition
- speaker identification
- emotion recognition
- genetic algorithm
- multilayer perceptron
- language model
- image data
- high dimensional
- pattern recognition