| Popis: |
Automatic spoken language translation has finally entered widespread use. Still emerging, however, are speech-translation systems directed at various demanding and socially significant use cases. Because speech-recognition and -translation technologies remain error-prone, speech-translation output is often below the threshold of usability when accuracy is essential; and present use is still largely restricted to areas like social networking or travel in which no representation concerning accuracy is demanded. This chapter, while recognizing the importance of continued improvements in speech-recognition and -translation accuracy per se, aims to support the conviction that the path toward widespread use of socially substantial spoken language translation can be shortened by emphasizing reliability (accountability and user confidence) and customization (tight adaptation for the targeted use case). Examined here are several socially significant speech-translation systems which aim to meet those requirements, with focus upon current systems in (1) healthcare and (2) presentations for education, academic conferences, and government. |
