Research Article
Developments of Machine Learning Schemes for Dynamic Time-Wrapping-Based Speech Recognition
Table 7
Recognition results of DTW speech recognition with most-matching learning (settings of thresholds:
and
).
| Index of keywords |
Recognition rates after most-matching learning (unsupervised learning) | One time | Two times | Five times |
| Index 1 | 100% | 100% | 98% | Index 2 | 86% | 86% | 90% | Index 3 | 66% | 64% | 66% | Index 4 | 62% | 62% | 60% | Index 5 | 66% | 68% | 58% |
| Average | 76% | 76% | 74.4% |
|
|