ISCA Archive Interspeech 2008
ISCA Archive Interspeech 2008

Data-driven clustered hierarchical tandem system for LVCSR

Shuo-Yiin Chang, Lin-shan Lee

In tandem systems, the outputs of multi-layer perceptron (MLP) classifiers have been successfully used as features for HMM-based automatic speech recognition. In this paper, we propose a datadriven clustered hierarchical tandem system that yields improved performance on a large-vocabulary broadcast news transcription task. The complicated global learning for a large monolithic MLP classifier is divided into simpler tasks, in which hierarchical structures clustered based on the outputs of a monolithic MLP are used to alleviate phone confusion. The proposed approach yields error rate reductions of up to 16.4% over MFCC features alone.

doi: 10.21437/Interspeech.2008-447

Cite as: Chang, S.-Y., Lee, L.-s. (2008) Data-driven clustered hierarchical tandem system for LVCSR. Proc. Interspeech 2008, 2250-2253, doi: 10.21437/Interspeech.2008-447

  author={Shuo-Yiin Chang and Lin-shan Lee},
  title={{Data-driven clustered hierarchical tandem system for LVCSR}},
  booktitle={Proc. Interspeech 2008},