Distant Speech Recognition On Chime 4 Real
Metrics
Word Error Rate (WER)
Results
Performance results of various models on this benchmark
| Paper Title | ||
|---|---|---|
| HMM-TDNN(LFMMI) + LSTMLM + NN-GEV | 2.74 | Building state-of-the-art distant speech recognition using the CHiME-4 challenge with a setup of speech enhancement baseline |
| Complex Spectral Mapping + WRBN + Utterance-Wise Dropout + Iterative Speaker Adaptation | 1.99 | - |
0 of 2 row(s) selected.