Professor, Department of Electrical and Computer Engineering. UW-Madison.
Two spoken sentences are never identical, even if they contain the same textual material. Basic to the study of how speakers differ is the ability to (automatically) parse the sentences and align the relevant utterances, to locate the times when the phonemes of one speaker align with the (same) phonemes …
This talk introduces a way to conduct audio morphings by imposing a constraint that can be used to smoothly connect two different audio spectra. The method exploits a formal analogy between the two spatial dimensions of Laplace’s partial differential equation and the two dimensions (time and frequency) of a spectrogram. …