Data Efficient Voice Cloning for Neural Singing Synthesis
This work addresses the need for data-efficient voice cloning in singing synthesis, which is incremental as it adapts existing methods to a new domain.
The paper tackled the problem of creating singing synthesis voices from small datasets by adapting a voice cloning technique from text-to-speech, achieving effective adaptation to new voices with limited data as validated through listening tests.
There are many use cases in singing synthesis where creating voices from small amounts of data is desirable. In text-to-speech there have been several promising results that apply voice cloning techniques to modern deep learning based models. In this work, we adapt one such technique to the case of singing synthesis. By leveraging data from many speakers to first create a multispeaker model, small amounts of target data can then efficiently adapt the model to new unseen voices. We evaluate the system using listening tests across a number of different use cases, languages and kinds of data.