Paper: A Filter-Based Approach to Detect End-of-Utterances from Prosody in Dialog Systems

ACL ID N07-2012
Title A Filter-Based Approach to Detect End-of-Utterances from Prosody in Dialog Systems
Venue Human Language Technologies
Session Short Paper
Year 2007
Authors

We propose an efficient method to detect end-of-utterances from prosodic information in conversational speech. Our method is based on the application of a large set of binary and ramp filters to the energy and fundamental fre- quency signals obtained from the speech sig- nal. These filter responses, which can be com- puted very efficiently, are used as input to a learning algorithm that generates the final de- tector. Preliminary experiments using data ob- tained from conversations show that an accu- rate classifier can be trained efficiently and that good results can be obtained without requiring a speech recognition system.