Unsupervised speaker adaptation for speaker independent acoustic to articulatory speech inversion
The Journal of the Acoustical Society of America, pp. 316-329, 2019.
Speech inversion is a well-known ill-posed problem and addition of speaker differences typically makes it even harder. Normalizing the speaker differences is essential to effectively using multi-speaker articulatory data for training a speaker independent speech inversion system. This paper explores a vocal tract length normalization (VTL...More
Full Text (Upload PDF)
PPT (Upload PPT)