Detecting Levels of Interest from Spoken Dialog with Multistream Prediction Feedback and Similarity Based Hierarchical Fusion Learning

@inproceedings{Wang2011DetectingLO,
  title={Detecting Levels of Interest from Spoken Dialog with Multistream Prediction Feedback and Similarity Based Hierarchical Fusion Learning},
  author={William Yang Wang and Julia Hirschberg},
  booktitle={SIGDIAL Conference},
  year={2011}
}
Detecting levels of interest from speakers is a new problem in Spoken Dialog Understanding with significant impact on real world business applications. Previous work has focused on the analysis of traditional acoustic signals and shallow lexical features. In this paper, we present a novel hierarchical fusion learning model that takes feedback from previous multistream predictions of prominent seed samples into account and uses a mean cosine similarity measure to learn rules that improve… CONTINUE READING
Highly Cited
This paper has 19 citations. REVIEW CITATIONS

Citations

Publications citing this paper.
Showing 1-10 of 15 extracted citations

References

Publications referenced by this paper.
Showing 1-10 of 32 references

The DARPA Speech Recognition Research Database: Specifications and Status

  • Fisher, M. William, Doddington, R. George, Goudie-Marshall, M. Kathleen
  • DARPA Workshop on Speech Recognition.
  • 1986
Highly Influential
3 Excerpts

Similar Papers

Loading similar papers…