Experiments in speech driven question answering

In this paper we present a system that allows users to obtain the answer to a given spoken question expressed in natural language. A large vocabulary continuous speech recognizer is used to transcribe the spoken question into text. Then, a question answering engine is used to obtain the answer to the question. Some improvements over the baseline system were proposed in order to adapt the output of the speech recognizer to the question answering engine: capitalized output from the speech recognizer and a language model for questions. System performance was evaluated using a standard question answering test suite from CLEF. Results showed that the proposed approach outperforms the baseline system both in WER and in over-all system accuracy.