Unsupervised topic modeling for leader detection in spoken discourse

@article{Hadsell2012UnsupervisedTM,
  title={Unsupervised topic modeling for leader detection in spoken discourse},
  author={Raia Hadsell and Zsolt Kira and Wen Wang and Kristin Precoda},
  journal={2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  year={2012},
  pages={5113-5116}
}
In this paper, we describe a method for leader detection in multi-party spoken discourse that relies on unsupervised topic modeling to segment the discourse automatically. Latent Dirichlet allocation is applied to sliding temporal windows of utterances, resulting in a topic model which captures the fluid transitions from topic to topic which occur in multi-party discourse. Further processing discretizes the continuous topic mixtures into sequential topic segments. Features are extracted from… CONTINUE READING

References

Publications referenced by this paper.
Showing 1-10 of 11 references

Detecting leadership and cohesion in spoken interactions

2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) • 2012
View 4 Excerpts
Highly Influenced

Meeting structure annotation: Data and tools

A. Gruenstein, J. Niekrasz, M. Purver
SIGdial Workshop on Discourse and Dialogue, 2005, pp. 117–127. • 2005
View 3 Excerpts
Highly Influenced

Automatic identification of speaker role and agreement/disagreement in broadcast conversation

2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) • 2011
View 2 Excerpts

Unsupervised broadcast conversation speaker role labeling

2010 IEEE International Conference on Acoustics, Speech and Signal Processing • 2010
View 2 Excerpts

A Probabilistic Model of Meetings That Combines Words and Discourse Features

IEEE Transactions on Audio, Speech, and Language Processing • 2008
View 1 Excerpt