Paper: Predicting Automatic Speech Recognition Performance Using Prosodic Cues

ACL ID A00-2029
Title Predicting Automatic Speech Recognition Performance Using Prosodic Cues
Venue Annual Conference of the North American Chapter of the Association for Computational Linguistics
Session Main Conference
Year 2000
Authors

In spoken dialogue systems, it is important for a system to know how likely a speech recognition hy- pothesis is to be correct, so it can reprompt for fresh input, or, in cases where many errors have occurred, change its interaction strategy or switch the caller to a human attendant. We have discov- ered prosodic features which more accurately predict when a recognition hypothesis contains a word error than the acoustic confidence score thresholds tradi- tionally used in automatic speech recognition. We present analytic results indicating that there are sig- nificant prosodic differences between correctly and incorrectly recognized turns in the TOOT train in- formation corpus. We then present machine learn- ing results showing how the use of prosodic features to automatically predict corre...