A Unified Deep Neural Network for Speaker and Language Recognition

no code implementations • 3 Apr 2015 • Fred Richardson, Douglas Reynolds, Najim Dehak

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.

Domain Adaptation Speaker Recognition

Discriminative Keyword Selection Using Support Vector Machines

no code implementations • NeurIPS 2007 • Fred Richardson, William M. Campbell

A natural technique for determining these characteristics is to first convert the input speech into a sequence of tokens such as words, phones, etc.

feature selection