Its always helpful if we can predict how well a recognition system can perform for different tasks and evaluate the quality of different acoustic models. This paper presents a way to compute the acoustic similarity between words of a recognition task from the statistic models directly based on 2 kinds of definitions of the acoustic distance between recogniton units. Its applications for command and control task complexity prediction and acoustic model evaluation are discussed. The experimental results shows its a useful measurement.
Cite as: Shen, L., Fu, G., Chai, H., Qin, Y. (2000) The measurement of acoustic similarity and its applications. Proc. 6th International Conference on Spoken Language Processing (ICSLP 2000), vol. 4, 576-579
@inproceedings{shen00_icslp,
author={Liqin Shen and Guokang Fu and Haixin Chai and Yong Qin},
title={{The measurement of acoustic similarity and its applications}},
year=2000,
booktitle={Proc. 6th International Conference on Spoken Language Processing (ICSLP 2000)},
pages={vol. 4, 576-579}
}