We use an EM algorithm to learn user models in a spoken dialog system. Our method requires automatically transcribed (with ASR) dialog corpora, plus a model of transcription error...
We explore online technical support of open source software by a study of postings to discussion boards. Our results indicate that there are several types of detail that are requi...
The output of a speech recognition system is not always ideal for subsequent downstream processing, in part because speakers themselves often make mistakes. A system would accompl...
: Voice user interfaces (VUIs) have become very common for telephone based applications, e.g. call centers and value-added services. Though there are advantages for further fields ...
Our paper focuses on the gain which can be achieved on human transcription of spontaneous and prepared speech, by using the assistance of an ASR system. This experiment has shown ...