Transcribing against time

Abstract

We investigate the problem of manually correcting errors from an automatic speech transcript in a cost-sensitive fashion. This is done by specifying a fixed time budget, and then automatically choosing location and size of segments for correction such that the number of corrected errors is maximized. The core components, as suggested by previous research [1… (More)
DOI: 10.1016/j.specom.2017.07.006

Topics

13 Figures and Tables

Cite this paper

@article{Sperber2017TranscribingAT, title={Transcribing against time}, author={Matthias Sperber and Graham Neubig and Jan Niehues and Satoshi Nakamura and Alexander H. Waibel}, journal={Speech Communication}, year={2017}, volume={93}, pages={20-30} }