A Unified Deep Neural Network for Speaker and Language Recognition

04/03/2015
by   Fred Richardson, et al.
0

Learned feature representations and sub-phoneme posteriors from Deep Neural Networks (DNNs) have been used separately to produce significant performance gains for speaker and language recognition tasks. In this work we show how these gains are possible using a single DNN for both speaker and language recognition. The unified DNN approach is shown to yield substantial performance improvements on the the 2013 Domain Adaptation Challenge speaker recognition task (55 2011 Language Recognition Evaluation (48 condition).

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset