Table 3 WER (%) of the baseline models for all languages
From: Advanced recurrent network-based hybrid acoustic models for low resource speech recognition
Model | WER | Â | |||||
|---|---|---|---|---|---|---|---|
| Â | 101 Cantonese | 104 Pashto | 107 Vietnamese | 202 Swahili | 204 Tamil | 302 Kazakh | 404 Georgian |
DNN-fbank | 44.8 | 51.2 | 53.1 | 46.2 | 66.7 | 54.1 | 50.5 |
LSTM-fbank | 40.7 | 50.5 | 47.8 | 42.5 | 65 | 52.9 | 48.9 |
DNN-MBN | 36.1 | 44.2 | 44.7 | 38.9 | 61.3 | 48.8 | 45 |
LSTM-MBN | 35.7 | 44.9 | 45 | 39.6 | 61.3 | 49 | 45.2 |