Projects per year
We implement two deep architectures for the acoustic-articulatory inversion mapping problem: a deep neural network and a deep trajectory mixture density network. We find that in both cases, deep architectures produce more accurate predictions than shallow architectures and that this is due to the higher expressive capability of a deep model and not a consequence of adding more adjustable parameters. We also find that a deep trajectory mixture density network is able to obtain better inversion accuracies than smoothing the results of a deep neural network. Our best model obtained an average root mean square error of 0.885 mm on the MNGU0 test dataset.
|Title of host publication||INTERSPEECH 2012 13th Annual Conference of the International Speech Communication Association|
|Number of pages||4|
|Publication status||Published - Sep 2012|
1/02/11 → 31/07/14