November 2017
Intermediate to advanced
274 pages
6h 16m
English
In this section, we will look at how a BRNN provides higher accuracy results on the TIMIT Dataset for phoneme text classification.
TIMIT is a corpus of phonemically and lexically transcribed speeches of American English speakers of different sexes and dialects. Each transcribed element has been delineated in time. TIMIT was designed to further acoustic-phonetic knowledge and automatic speech recognition systems:

As can be seen from the preceding figure, the BRNN gives higher percent frames accurately as compared to MLP, both for the training set and testing set. BLSTM gives even higher accuracy.
Read now
Unlock full access