Learning Backchannel Prediction Model from Parasocial Consensus Sampling: A Subjective Evaluation (bibtex)
by Huang, Lixing, Morency, Louis-Philippe and Gratch, Jonathan
Abstract:
Backchannel feedback is an important kind of nonverbal feedback within face-to-face interaction that signals a person's interest, attention and willingness to keep listening. Learning to predict when to give such feedback is one of the keys to creating natural and realistic virtual humans. Prediction models are traditionally learned from large corpora of annotated face-to-face interactions, but this approach has several limitations. Previously, we proposed a novel data collection method, Parasocial Consensus Sampling, which addresses these limitations. In this paper, we show that data collected in this manner can produce effective learned models. A subjective evaluation shows that the virtual human driven by the resulting probabilistic model significantly outperforms a previously published rule-based agent in terms of rapport, perceived accuracy and naturalness, and it is even better than the virtual human driven by real listeners' behavior in some cases.
Reference:
Learning Backchannel Prediction Model from Parasocial Consensus Sampling: A Subjective Evaluation (Huang, Lixing, Morency, Louis-Philippe and Gratch, Jonathan), In The 10th International Conference on Intelligent Virtual Agents (IVA 2010), 2010.
Bibtex Entry:
@inproceedings{huang_learning_2010,
	address = {Philadelphia, PA},
	title = {Learning {Backchannel} {Prediction} {Model} from {Parasocial} {Consensus} {Sampling}: {A} {Subjective} {Evaluation}},
	url = {http://ict.usc.edu/pubs/Learning%20Backchannel%20Prediction%20Model%20from%20Parasocial%20Consensus%20Sampling-%20A%20Subjective%20Evaluation.pdf},
	abstract = {Backchannel feedback is an important kind of nonverbal feedback within face-to-face interaction that signals a person's interest, attention and willingness to keep listening. Learning to predict when to give such feedback is one of the keys to creating natural and realistic virtual humans. Prediction models are traditionally learned from large corpora of annotated face-to-face interactions, but this approach has several limitations. Previously, we proposed a novel data collection method, Parasocial Consensus Sampling, which addresses these limitations. In this paper, we show that data collected in this manner can produce effective learned models. A subjective evaluation shows that the virtual human driven by the resulting probabilistic model significantly outperforms a previously published rule-based agent in terms of rapport, perceived accuracy and naturalness, and it is even better than the virtual human driven by real listeners' behavior in some cases.},
	booktitle = {The 10th {International} {Conference} on {Intelligent} {Virtual} {Agents} ({IVA} 2010)},
	author = {Huang, Lixing and Morency, Louis-Philippe and Gratch, Jonathan},
	month = sep,
	year = {2010},
	keywords = {Virtual Humans}
}
Powered by bibtexbrowser