Neural Network Language Modeling with Letter-based Features and Importance Sampling
Open paper
Benchmark
Model
Rank
Results
speech-recognition-on-librispeech-test-clean
tdnn + chain + rnnlm rescoring
–
Word Error Rate (WER): 3.06
speech-recognition-on-librispeech-test-other
tdnn + chain + rnnlm rescoring
–
Word Error Rate (WER): 7.63
Rank counts only results with a code link.