| P10-2044 | class modeling rather than answer | word modeling | by expanding Eq . ( 4 ) as follows |
| H92-1080 | semi-continuous distributions . For between | word modeling | only the left context is considered |
| H92-1080 | decoder that implemented no cross | word modeling | . only be combined once . Second |
| N03-1005 | diphone classes . Using Bazzi 's OOV | word modeling | scheme , unknown words are represented |
| P14-1140 | translation information and surrounding | words modeling | context information are leveraged |
| W07-0805 | finite-duration modeling and monosyllabic | word modeling | . Wu et al. ( 1998 ) tried to |
| N03-1033 | includes the improvements in unknown | word modeling | discussed in section 3.3.9 We |
