In this presentation, we introduce several research
topics related with the keyword spotting system on
broadcast news. The system searches the keyword
speech in online broadcast news and extracts the
articles including the keyword(s). To obtain a stable
recognition performance, the system uses several
speech processing techniques such as utterance
verification, out-of-vocabulary rejection, audio
classification, and noise reduction. We will show an
overall configuration for our system and report
technical advances as well as some experimental
results. We also describe future works for the system
improvements and the application for further
complicate spoken documents like interviews or
movies.