This paper discusses the challenges and proposes a solution to performing information retrieval on the Web using Chinese natural language speech query. The main contribution of this research is in devising a divide-and-conquer strategy to alleviate the speech recognition errors. It uses the query model to facilitate the extraction of main core semantic string (CSS) from the Chinese natural language speech query. It then breaks the CSS into basic components corresponding to phrases, and uses a multi-tier strategy to map the basic components to known phrases in order to further eliminate the errors. .
