Speech-Based Retrieval Using Semantic Co-Occurrence Filtering

In this paper we demonstrate that speech recognition can be effectively applied to information retrieval (IR) applications. Our system exploits the fact that the intended words of a spoken query tend to co-occur in text documents in close proximity whereas word combinations that are the result of recognition errors are usually not semantically correlated and thus do not appear together. Termed "Semantic Co-occurrence Filtering" this enables the system to simultaneously disambiguate word hypotheses and find relevant text for retrieval. The system is built by integrating standard IR and speech recognition techniques. An evaluation of the system is preseated and we discuss several refinements to the functionality.

• Type: Conference
• Year: 1994
• Where: NAACL
• Authors: Julian Kupiec, Don Kimber, Vijay Balasubramanian
• Keywords: NAACL 1994, NAACL 2007, Speech Recognition, Speech Recognition Techniques, Spoken Query Tend