Modeling Irregular Voice in End-to-End Speech Synthesis via Speaker Adaptation.
Ali Raheem MandeelMohammed Salah Al-RadhiTamás Gábor CsapóPublished in: SpeD (2023)
Keyphrases
- end to end
- speech synthesis
- speech recognition
- text to speech
- speaker adaptation
- vocal tract
- prosodic features
- speech recognizer
- speaker independent
- congestion control
- admission control
- internet protocol
- hidden markov models
- pattern recognition
- scalable video
- application layer
- automatic speech recognition
- speech recognition systems
- real world
- neural network
- transport layer
- multimedia