Improved spoken term detection using support vector machines based on lattice context consistency

Hung-yi Lee, Tsung-wei Tu, Chia-Ping Chen, Chao-Yu Huang, Lin-Shan LeeICASSP 2011 · OpenReview

Abstract

We propose an improved spoken term detection approach that uses support vector machines trained with lattice context consistency. The basic idea is that the same term usually have similar context, while quite different context usually implies the terms are different. Support vector machine can be trained using query context feature vectors obtained from the lattice to estimate better scores for ranking, and significant improvements can be obtained. This process can be performed iteratively and integrated with the pseudo relevance feedback in acoustic feature space proposed previously, both offering further improvements.
BibTeX
@inproceedings{lee2011improved,
  author = {Hung-yi Lee and Tsung-wei Tu and Chia-Ping Chen and Chao-Yu Huang and Lin-Shan Lee},
  title = {{Improved spoken term detection using support vector machines based on lattice context consistency}},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
  year = {2011},
  url = {https://openreview.net/forum?id=GnKmxOIbpMl},
}

Loading related content...

Figure