@inproceedings{4cbe9cdad1e04f769a9d47d713cd79b3,
title = "Error prediction in spoken dialog: From signal-to-noise ratio to semantic confidence scores",
abstract = "Spoken dialog systems aim to interpret meanings of users' utterances and respond to them accordingly. The users' utterances are first recognized by an automatic speech recognizer (ASR) and the intents of the users are extracted by the spoken language understanding (SLU) unit. Both ASR and SLU are noisy and in general their noise statistics are not correlated. Our goal is to exploit the signal-noise information and ASR lattice-based and semantic confidence scores for SLU error prediction and prevention of these by rejecting erroneous utterances, or asking confirmation questions. In our experiments, we have shown up to 80% relative decrease in the error rate of the accepted utterances collected using the AT&T How May I Help You{\texttrademark} Spoken Dialog System used for customer care.",
author = "Dilek Hakkani-T{\"u}r and Gokhan Tur and Giuseppe Riccardi and Kim, {Hong Kook}",
year = "2005",
doi = "10.1109/ICASSP.2005.1415295",
language = "English (US)",
isbn = "0780388747",
series = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "I1041--I1044",
booktitle = "2005 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP '05 - Proceedings - Image and Multidimensional Signal Processing Multimedia Signal Processing",
address = "United States",
note = "2005 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP '05 ; Conference date: 18-03-2005 Through 23-03-2005",
}