| tech,1-4-E06-1022,ak | classifiers ' performances </term> . Both <term> | classifiers | </term> perform the best when <term> conversational | #11231 Both classifiers perform the best when conversational context and utterance features are combined with speaker's gaze information. | |
| tech,1-5-E06-1022,ak | speaker 's gaze information </term> . The <term> | classifiers | </term> show little gain from information | #11250 The classifiers show little gain from information about meeting context. |
