Skip to main content

Advertisement

Table 4 Recognition results in the first pass obtained on the BNSI evaluation set

From: Context-dependent factored language models

Vocabulary size WER [%]
  Good-Turing Knesser-Ney
  Bigram Trigram Bigram Trigram
60K 33.89 30.73 33.84 30.95
100K 31.27 28.08 31.24 28.36
200K 29.70 26.27 29.78 26.53
300K 29.22 25.64 29.28 25.87