eduzhai > Applied Sciences > Engineering >

Speaker conditioned acoustic-to-articulatory inversion using x-vectors

  • Save

... pages left unread,continue reading

Document pages: 5 pages

Abstract: Speech production involves the movement of various articulators, includingtongue, jaw, and lips. Estimating the movement of the articulators from theacoustics of speech is known as acoustic-to-articulatory inversion (AAI).Recently, it has been shown that instead of training AAI in a speaker specificmanner, pooling the acoustic-articulatory data from multiple speakers isbeneficial. Further, additional conditioning with speaker specific informationby one-hot encoding at the input of AAI along with acoustic features benefitsthe AAI performance in a closed-set speaker train and test condition. In thiswork, we carry out an experimental study on the benefit of using x-vectors forproviding speaker specific information to condition AAI. Experiments with 30speakers have shown that the AAI performance benefits from the use of x-vectorsin a closed set seen speaker condition. Further, x-vectors also generalizeswell for unseen speaker evaluation.

Please select stars to rate!


0 comments Sign in to leave a comment.

    Data loading, please wait...