| W01-1613 | classification . Different kinds of final | tone classification | can be investigated , once the |
| W01-1613 | interesting to use for the final | tone classification | , especially with respect to |
| N07-1001 | the pitch accent and boundary | tone classification | . Especially , in the case where |
| N07-1001 | best in pitch accent and boundary | tone classification | . The classification accuracies |
| N07-1001 | results on pitch accent and boundary | tone classification | . Much of the gain comes from |
| W01-1613 | perceived pitch . More sophisticated | tone classification | rules besides this preliminary |
| N07-1001 | improved pitch accent and boundary | tone classification | accuracies of 86.0 % and 93.1 |
| N10-1109 | phenomena . Here we have used ToBI | tone classifications | as an intermediate representation |
| W01-1613 | with respect to a final boundary | tone classification | . Statistically significantly |
| N06-1029 | approaches . In contrast , for the four | tone classification | task in Mandarin using two stage |
| N06-1029 | the semi-supervised framework , | tone classification | outperforms both most common |
| N10-1109 | using QCM . 5.3 Phrase-ending | Tone Classification | As in Section 5.2 , we identify |
