ISCA Archive Interspeech 2008
ISCA Archive Interspeech 2008

Spoken keyword spotting via multi-lattice alignment

Hui Lin, Alex Stupakov, Jeff A. Bilmes

We propose a method for finding keywords in an audio database using a spoken query. Our method is based on performing a joint alignment between a phone lattice generated from a spoken utterance query and a second phone lattice representing a long utterance needing to be searched. We implement this joint alignment procedure in a graphical models framework. We evaluate our system on TIMIT as well as on the Switchboard conversational telephone speech (CTS) corpus. Our results show that a phone lattice representation of the spoken query achieves higher performance than using only the 1-best phone sequence representation.

doi: 10.21437/Interspeech.2008-573

Cite as: Lin, H., Stupakov, A., Bilmes, J.A. (2008) Spoken keyword spotting via multi-lattice alignment. Proc. Interspeech 2008, 2191-2194, doi: 10.21437/Interspeech.2008-573

  author={Hui Lin and Alex Stupakov and Jeff A. Bilmes},
  title={{Spoken keyword spotting via multi-lattice alignment}},
  booktitle={Proc. Interspeech 2008},