Erratum to: A limited-size ensemble of homogeneous CNN/LSTMs for high-performance word classification

In the original publication of the article 'A limited-size ensemble of homogeneous CNN/LSTMs for high-performance word classification, Neural Computing and Applications 33, DOI:10.1007/s00521-020-05612-0' in Table 11 and Fig. 9, there were errors in calculation of the weighted average of the word-accuracy values. The correct figure and table are provided here. The weighted averages turned out to be slightly higher than in the original article. These weighted-average rates are dominated by the large KdK data set and are not the focus of the interpretation of the results: The differences within the individual data sets are more important to understand the effects of the conditions, i.e., dictionary size and ensemble application. Therefore, the miscalculation has no effect on the Discussion section of the original article.

Table 11.csv contains the corresponding formulas and the relevant values for calculating the weighted average of the word accuracy % on the RIMES, KdK and GW data sets, using the dual-state word-beam search applying the Concise dictionary and the Extra-separator label-coding scheme, for the two CTC methods and single vs ensemble voting. Averaging was carried out over sets.

Fig9.png shows the comparison of the effect of the two label-coding schemes (Plain vs Extra-separator) and dictionary application on the single architecture and ensemble voting on the RIMES, KdK, and GW data sets showing the weighted average word accuracy taking test-set sizes into account. Averaging was done over sets. Fig9.csv contains the formulas and relevant values for figure 9.