Adversarial Multi-Task Learning for Disentangling Timbre and Pitch in Singing Voice Synthesis.
Tae-Woo KimMin-Su KangGyeong-Hoon LeePublished in: CoRR (2022)
Keyphrases
- multi task learning
- acoustic features
- music information retrieval
- multi task
- multiple tasks
- learning tasks
- speaker verification
- gaussian processes
- multitask learning
- visual features
- theoretical analysis
- learning algorithm
- musical instrument
- speech signal
- learning problems
- multi label image annotation
- high order
- audio features
- transfer learning
- inductive learning
- data sets
- learning models