Enhanced Virtual Singers Generation by Incorporating Singing Dynamics to Personalized Text-to-speech-to-singing.
Kantapon KaewtipFernando VillavicencioFang-Yu KuoMark HarvillaIris OuyangPierre LanchantinPublished in: ICASSP (2019)
Keyphrases
- text to speech
- music information retrieval
- augmented reality
- programming tool
- speech synthesis
- prosodic features
- virtual world
- virtual reality
- audio features
- e learning
- dynamic model
- user modeling
- text to speech synthesis
- english text
- word processing
- virtual environment
- context aware
- multi modal
- life long
- pattern recognition