| C. Nakatani and J. Hirschberg: A Speech--First Model for Repair Identification in Spoken Language Systems, in Proceedings of the ARPA Workshop on Human Language Technology, March 1993 |
....to recover from errors in a graceful and unobstrusive way. We have developed a speech interface for repairing recognition errors by simply respeaking or spelling a misrecognized section of an utterance. While much speech repair work has focused on repairs within a single spoken utterance [19], we are concerned with the interactive repair of errorful recognizer hypotheses [20] 6.1. Identifying Errors To be able to repair an error its location has to be determined first. We pursue two strategies to identify misrecognitions as subpieces of the initial recognizer hypothesis. The ....
C. Nakatani and J. Hirschberg: A Speech--First Model for Repair Identification in Spoken Language Systems, in Proceedings of the ARPA Workshop on Human Language Technology, March 1993
....First results in this direction are described here. We have developed a speech interface for repairing recognition errors by simply respeaking or spelling a misrecognized section of an utterance. While much speech repair work has focused on repairs within a single spoken utterance (Nakatani Hirschberg 1993), we are concerned with the interactive repair of errorful recognizer hypotheses (McNair Waibel 1994) Identifying Errors To be able to repair an error, its location has to be determined first. We pursue two strategies to identify misrecognitions as subpieces of the initial recognizer ....
C. Nakatani and J. Hirschberg: A Speech--First Model for Repair Identification in Spoken Language Systems. Proc. of the ARPA Workshop on Human Language Technology, March 1993 A.-E. McNair and A. Waibel: Improving Recognizer Acceptance through Robust, Natural Speech Repair. Proc.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC