Next: Hidden Neural Network (HNN)
Up: Task 5.2: Technical Description
Previous: Forward-Backward training
The performance of this algorithm was tested on the task-independent PHONEBOOK database . Recognition experiments were performed on a 600 word lexicon using log-RASTA PLP as acoustic features. We defined two training sets, a small one (9,000 utterances) and a large one (19,000 utterances). Results are reported in table 5.2
Error rates on isolated word recognition with hybrid system and log-rasta plp features. Comparison between Viterbi and full forward-backward training.
|Word error rate
||Training set 1
||Training set 2