Name
Abstract | ||
|---|---|---|
With the aim of constructing a model for predicting the next speaker and the start of the next utterance in multi-party meetings, we focus on the timing structure of the eye contact between the speaker, the listener, and the next speaker: who looks at whom first, who looks away first, and when the eye contact happens. We analyze the differences in the timing structure for the listener and next speaker in turn-changing and turn-keeping. The results of analysis show that the listeners in turn-keeping tend to look at the speaker more often first before the speaker looks at the listeners than the next speaker in turn-changing looks at the speaker first before the speaker looks at the next speaker when the eye contact with the speaker happens. The listeners in turn-keeping tend to look away from the speaker more often later after the speaker looks away from the listener than listeners and the next speaker in turn-changing looks away from the speaker later when the eye contact with the speaker happens. In addition, the interval between the end of eye contact, the end of the speaker's utterance, and the start of next speaker's utterance is different between the listener in turn-keeping, the listener in turn-changing, and the next speaker in turn-changing. |
Year | DOI | Venue |
|---|---|---|
2014 | 10.1145/2666642.2666648 | GazeIn@ICMI |
Keywords | Field | DocType |
timing structure,human information processing,discourse,eye contact,next-speaker prediction,multi-party meetings,gaze behavior | Computer science,Utterance,Speech recognition,Speaker recognition,Speaker diarisation,Eye contact | Conference |
Citations | PageRank | References |
1 | 0.37 | 7 |
Authors | ||
4 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Ryo Ishii | 1 | 155 | 16.59 |
| Kazuhiro Otsuka | 2 | 619 | 54.15 |
| Shiro Kumano | 3 | 149 | 16.82 |
| Junji Yamato | 4 | 1120 | 165.72 |