[Retracted] Application of Discriminative Training Algorithm Based on the Improved Gaussian Mixture Model in English Translation Evaluation

Table 5

Confusion matrix for number of 2-second speech tests.

	Recognition result
	Japanese	Chinese	German	French
Japanese	0.5578	0.0938	0.2263	0.1221
Chinese	0.080	0.6612	0.229	0.0298
German	0.0779	0.2335	0.5321	0.1565
French	0.09	0.05	0.2111	0.6489