Thrilled: my PhD work “Reconstructing voice identity from noninvasive auditory cortex recordings” is now in @elife.bsky.social DNNs model human temporal voice areas & can reconstruct speaker identity from fMRI. Ty to supervisors, co authors, CERIMED & participants elifesciences.org/articles/98047
A low-dimensional voice latent space derived from deep learning captures speaker-identity representations in the temporal voice areas and supports reconstruction of voices preserving identity information.
