Estimating probability of correctness for ASR N-Best lists

Jason Williams and Suhrid Balakrishnan

SIGDIAL Workshop on Discourse and Dialogue (SIGDIAL 2009)
Queen Mary University of London, September 11-12, 2009


For a spoken dialog system to make good use of a speech recognition N-Best list, it is essential to know how much trust to place in each entry. This paper presents a method for assigning a probability of correctness to each of the items on the N-Best list, and to the hypothesis that the correct answer is not on the list. We find that a multinomial logistic regression model yields meaningful, useful probabilities across different tasks and operating conditions.