A TV news retrieval system with interactive query function

Abstract

The paper describes a system which can automatically classify TV news articles using a keyword spotting technique and can also answer queries from users interactively. The keyword spotting technique can extract a keyword sequence with their probabilities and the extracted keywords are attached to the article for retrieval. The TV news article can be classified into topics such as politics, economy, science and so on by integrating acoustic keyword probability and topic contribution probability of the keyword, which is the probability of how a keyword contributes to classify the article. TV news is retrieved by speech including the keywords attached to the articles. The system is also installed with a query-answering function that can answer user queries of unfamiliar words included in TV news speech.