Predicting Barge-in Utterance Errors by using Implicitly-Supervised ASR Accuracy and Barge-in Rate per User.
Kazunori KomataniAlexander I. RudnickyPublished in: ACL/IJCNLP (2) (2009)
Keyphrases
- speech recognition
- computational cost
- error analysis
- user interface
- user preferences
- estimation error
- true positive rate
- high accuracy
- error rate
- user experience
- user queries
- prediction accuracy
- collaborative filtering
- classification accuracy
- supervised learning
- user satisfaction
- highly accurate
- feature selection
- human users
- unsupervised learning
- user interaction
- data sets
- active learning
- website
- supervised classification
- social networks
- automatic speech recognition
- learning algorithm