Minimum trajectory error training for deep neural networks, combined with stacked bottleneck features

Samples to support the Interspeech 2015 submission titled above. More details can be found in our paper [PDF]. If you have any questions, please drop me an email: zhizheng.wu {at} ed.ac.uk (Zhizheng Wu)

This page contains following samples:

  1. Natural: Natural recording speech.
  2. DNN: Baseline Deep Neural Network (DNN) system.
  3. BN-DNN: DNN with stacked bottlenecks
  4. MTE-DNN: DNN using minimum trajector training criterion.
  5. MTE-BN-DNN: DNN with stacked bottlenecks and minimum trajectory training criterion.

Samples Natural DNN BN-DNN MTE-DNN MTE-BN-DNN
1
2
3
4
5
6