Date
Tue, 16 Oct 2018
Time
14:30 - 15:00
Location
L5
Speaker
Vinayak Abrol
Organisation
Oxford

This work deals with exploiting the low-dimensional hierarchical structure of speech signals towards the  goal  of  improving  acoustic  modelling using deep neural networks (DNN).  To this aim the work employ tools from sparsity aware signal processing under novel frameworks to enrich  the  acoustic  information  present  in  DNN posterior features. 

Please contact us with feedback and comments about this page. Last updated on 04 Apr 2022 14:57.