Taming recognition errors with a multimodal interface 论文

摘要

The article focuses on restoring speech-recognition errors by using a multimodal interface. Speech-recognition errors may be results of various factors like diverse speaker styles or speech in noisy field settings. The author argues that multimodal architectures combining speech and pen input can reduce speech recognition errors. The recognition rate degrades whenever a user's speech style departs in some way from the training data on which a recognizer was developed. A different approach to resolving the impasse created by recognition errors is to design a more flexible multimodal interface incorporating speech as one of its input options. One motivation for developing multimodal systems has been their potential for expanding the accessibility of computing to more diverse and non-specialist users while promoting new forms of computing not available in the past. Multimodal systems comprehend to this trend, and permit users to alternate modes and switch between modalities as needed during the changing conditions of mobile use.