13th Annual Conference of the International Speech Communication Association

Portland, OR, USA
September 9-13, 2012

Improving Discriminative Training for Robust Acoustic Models in Large Vocabulary Continuous Speech Recognition

Janne Pylkkönen, Mikko Kurimo

Department of Information and Computer Science, Aalto University, Finland

This paper studies the robustness of discriminatively trained acoustic models for large vocabulary continuous speech recognition. Popular discriminative criteria maximum mutual information (MMI), minimum phone error (MPE), and minimum phone frame error (MPFE), are used in the experiments, which include realistic mismatched conditions from Finnish Speecon corpus and English Wall Street Journal corpus. A simple regularization method for discriminative training is proposed and it is shown to improve the robustness of acoustic models gaining consistent improvements in noisy conditions.

Index Terms: speech recognition, discriminative training, robustness

Full Paper

Bibliographic reference.  Pylkkönen, Janne / Kurimo, Mikko (2012): "Improving discriminative training for robust acoustic models in large vocabulary continuous speech recognition", In INTERSPEECH-2012, 1211-1214.