Journal of Big Data

Table 6 V-RNN classification accuracies and F-measures of error type classification obtained based on generic versus semi-generic and non-generic features

From: Evaluation of the effectiveness and efficiency of state-of-the-art features and models for automatic speech recognition error detection

Feature set	Accuracy (%)	F-measure (%)
Feature set	Accuracy (%)	Correct	Substitution	Insertion	Average
Non-generic	84.77	91.28	61.51	00.32	83.40
Semi-generic	84.20	91.02	58.82	04.21	82.80
Generic	81.34	89.20	43.84	00.00	78.51
All	85.10	91.58	57.81	04.10	83.05

Back to article page