Connectionist Temporal Classification: Labelling Unsegmented Sequence Data with Recurrent Neural Networks
Graves et al., 2006, Connectionist Temporal Classification (Proceedings of the 23rd International Conference on Machine Learning (ICML 2006))
Subscriber deck — free during early access
2 cards in “5.3 Experimental Results” · whole deck
5.3 Experimental Results
- How did CTC compare with HMM and hybrid systems on TIMIT?Label error rates: context-independent HMM 38.85%, context-dependent HMM 35.21%, BLSTM/HMM hybrid 33.84%, hybrid with weighted error 31.57%, CTC best path 31.47%, CTC prefix search 30.51%.
- Graves et al., 2006, Connectionist Temporal Classification (Proceedings of the 23rd International Conference on Machine Learning (ICML 2006)), §5.3, p. 375
- Why didn’t CTC need the weighted error heuristic that helped the hybrid?The hybrid gave long and short phonemes equal weight by scaling its framewise error. CTC’s objective depends only on the label sequence, not on durations or segmentation.
- Graves et al., 2006, Connectionist Temporal Classification (Proceedings of the 23rd International Conference on Machine Learning (ICML 2006)), §5.3, p. 375
Source
- Alex Graves, Santiago Fernández, Faustino Gomez and Jürgen Schmidhuber. 2006. Connectionist Temporal Classification: Labelling Unsegmented Sequence Data with Recurrent Neural Networks. In Proceedings of the 23rd International Conference on Machine Learning (ICML 2006), pp. 369–376. doi:10.1145/1143844.1143891