| N03-3007 | have investigated for the word | fragment detection task | . These prosodic features have |
| N03-3007 | each glottal cycle . For our word | fragment detection task | , we investigate the following |
| N03-3007 | precision and recall for this | fragment detection task | are 74.3 % and 70.1 % respectively |
| E03-3001 | to our model , as opposed to a | fragment detection task | in a real application where no |
| E03-3001 | valuable source in learning the | fragment detection task | . For the RIPPER algorithm we |
