Good to see that authors/maintainers of AI models are beginning to think about attribution. But it seems like this will be a hard problem to solve. For example, say my voice was part of the training data set, to what degree can I lay claim to the newly created voices? Also, will there be some sort of grading/ranking (e.g. it could be argued that some of the voices used in the training set are more desirable than others, and therefore their "owners" deserve better fees etc.)?