ISCA Archive Interspeech 2013
ISCA Archive Interspeech 2013

Efficient speech transcription through respeaking

Matthias Sperber, Graham Neubig, Christian Fügen, Satoshi Nakamura, Alex Waibel

We propose a method for efficient off-line speech transcription through respeaking. Speech is segmented into smaller utterances using an initial automatic transcript. Respeaking is performed segment by segment, while confidence filtering helps save supervision effort. We conduct detailed experiments comparing speaking vs. typing, sequential vs. confidence-ordered supervision, and examine the effect of the respeaking word error rate on correction efficiency. Our results demonstrate that the proposed method can not only outperform typing in terms of correction efficiency, but is also much less demanding for the respeakers than traditional respeaking methods, consequently helping to keep costs down. Annotation and Classification of Political Advertisements


doi: 10.21437/Interspeech.2013-294

Cite as: Sperber, M., Neubig, G., Fügen, C., Nakamura, S., Waibel, A. (2013) Efficient speech transcription through respeaking. Proc. Interspeech 2013, 1087-1091, doi: 10.21437/Interspeech.2013-294

@inproceedings{sperber13_interspeech,
  author={Matthias Sperber and Graham Neubig and Christian Fügen and Satoshi Nakamura and Alex Waibel},
  title={{Efficient speech transcription through respeaking}},
  year=2013,
  booktitle={Proc. Interspeech 2013},
  pages={1087--1091},
  doi={10.21437/Interspeech.2013-294}
}