Metric learning produces a joint embedding space for monophonic vocal and mixed music tracks of the same singer using synthetic mashup training data.
Through data generation using music mashup, we were able to train an embedding model to out- put a joint representation for singing voice from tracks re- gardless of their domain
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SD 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Learning a Joint Embedding Space of Monophonic and Mixed Music Signals for Singing Voice
Metric learning produces a joint embedding space for monophonic vocal and mixed music tracks of the same singer using synthetic mashup training data.