One Year of Contender: What Have We Learned about Assessing and Tuning Industrial Spoken Dialog Systems?

David Suendermann, Roberto Pieraccini

Abstract: A lot. Since inception of Contender, a machine learning method tailored for computer-assisted decision making in industrial spoken dialog systems, it was rolled out in over 200 instances throughout our applications processing nearly 40 million calls. The net effect of this data-driven method is a significantly increased system performance gaining about 100,000 additional automated calls every month.