Decision Tree-Based Triphones are Robust and Practical for Mandarin Speech Recognition
Fung, Pascale N.
Cheung, Percy Chi Shun
|Source||EUROSPEECH 99, Budapest, Hungary , September 1999|
|Summary||In large-vocabulary, speaker-independent speech recognition systems, modeling of vocabulary words by subword units is mandatory. This paper studies the use of triphone units for Mandarin speech recognition compared to biphone and context-independent phonetic units. In order to solve unseen triphones in speech recognition, decision-tree based clustering is used in triphone units. This method achieves high recognition performance with limited training data and also reduces the model training time. The robustness and effectiveness of the cross-word, tree-based triphone units have been proved by the speaker-independent continuous Manadarin speech recognition task. The training computation time reduces by about 2.3 times after trying states for triphone models, the recognition syllable accuracy increase 28.7% compared to monophone units and by 13.5% compared to biphone units.|
|Rights||We would like to give credit to International Speech Communication Association for granting us permission to repost this article.|
Files in this item: