Figure 8From: Phoneme and Sentence-Level Ensembles for Speech RecognitionGeneralisation performance on the hold-out set in terms of word error rate after training with segmentation information. Results are shown for both boosting and bagging, using three different methods for decoding. Single-path and multistream. Results are shown for three different methods single-stream (single), and state-locked multistream using either a weighted product (wprod) or weighted sum (wsum) combination.Back to article page