Name
Title | ||
|---|---|---|
Prosody-based automatic detection of annoyance and frustration in human-computer dialog |
Abstract | ||
|---|---|---|
We investigate the use of prosody for the detection of frustra- tion and annoyance in natural human-computer dialog. In ad- dition to prosodic features, we examine the contribution of lan- guage model information and speaking "style". Results show that a prosodic model can predict whether an utterance is neutral ver- sus "annoyed or frustrated" with an accuracy on par with that of human interlabeler agreement. Accuracy increases when discrim- inating only "frustrated" from other utterances, and when using only those utterances on which labelers originally agreed. Further- more, prosodic model accuracy degrades only slightly when using recognized versus true words. Language model features, even if based on true words, are relatively poor predictors of frustration. Finally, we find that hyperarticulation is not a good predictor of emotion; the two phenomena often occur independently. |
Year | Venue | Keywords |
|---|---|---|
2002 | INTERSPEECH | language model |
Field | DocType | Citations |
Dialog box,Prosody,Frustration,Computer science,Speech recognition,Natural language processing,Artificial intelligence,Annoyance | Conference | 170 |
PageRank | References | Authors |
16.84 | 6 | 5 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Jeremy Ang | 1 | 406 | 29.13 |
| Rajdip Dhillon | 2 | 197 | 20.61 |
| Ashley Krupski | 3 | 197 | 20.61 |
| Elizabeth Shriberg | 4 | 3057 | 325.64 |
| Andreas Stolcke | 5 | 6690 | 712.46 |