We present a system to enable efficient, collaborative human correction of ASR transcripts, designed to operate in real-time situations, for example, when post-editing live captions generated for news broadcasts. In the system, confusion networks derived from ASR lattices are used to highlight low-confident words and present alternatives to the user for quick correction. The system uses a client-server architecture, whereby information about each manual edit is posted to the server. Such information can be used to dynamically update the one-best ASR output for all utterances currently in the editing pipeline. We propose to make updates in three different ways; by finding a new one-best path through an existing ASR lattice consistent with the correction received; by identifying further instances of out-of-vocabulary terms entered by the user; and by adapting the language model on the fly. Updates are received asynchronously by the client.
Cite as: Bell, P., Fainberg, J., Lai, C., Sinclair, M. (2017) A System for Real Time Collaborative Transcription Correction. Proc. Interspeech 2017, 817-818
@inproceedings{bell17_interspeech,
author={Peter Bell and Joachim Fainberg and Catherine Lai and Mark Sinclair},
title={{A System for Real Time Collaborative Transcription Correction}},
year=2017,
booktitle={Proc. Interspeech 2017},
pages={817--818}
}