Multi-Speaker Speech Synthesis from Electromyographic Signals by Soft Speech Unit Prediction.
Kevin ScheckTanja SchultzPublished in: ICASSP (2023)
Keyphrases
- speech synthesis
- speech recognition
- prosodic features
- vocal tract
- text to speech
- speech signal
- automatic speech recognition
- noisy environments
- speech corpus
- prediction accuracy
- speaker identification
- linear prediction
- speech recognizer
- spectral analysis
- hidden markov models
- language model
- prediction model
- speaker independent
- signal processing
- speaker dependent
- emg signals
- prediction error
- pattern recognition
- neural network
- fundamental frequency
- audio signals
- speaker recognition
- speech recognition systems