Automatic Human Utility Evaluation of ASR Systems: Does WER Really Predict Performance?
(2013)
Conference Proceeding
Favre, B., Cheung, K., Kazemian, S., Lee, A., Liu, Y., Munteanu, C., …Zeller, F. (2013). Automatic Human Utility Evaluation of ASR Systems: Does WER Really Predict Performance?. In Proc. Interspeech 2013 (3463-3467). https://doi.org/10.21437/Interspeech.2013-610
We propose an alternative evaluation metric to Word Error Rate (WER) for the decision audit task of meeting recordings, which exemplifies how to evaluate speech recognition within a legitimate application context. Using machine learning on an initial... Read More about Automatic Human Utility Evaluation of ASR Systems: Does WER Really Predict Performance?.