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