Today's speech recognition systems are able to recognize arbitrary sentences over a large but finite vocabulary. However, many important speech recognition tasks feature an open, constantly changing vocabulary. (E.g. broadcast news transcription, translation of political debates, etc. Ideally, a system designed for such open vocabulary tasks would be able to recognize arbitrary, even previously unseen words. To some extent this can be achieved by using sub-lexical language models. We demonstrate that, by using a simple flat hybrid model, we can significantly improve a well-optimized state-of-the-art speech recognition system over a wide range of out-of-vocabulary rates.
Cite as: Bisani, M., Ney, H. (2005) Open vocabulary speech recognition with flat hybrid models. Proc. Interspeech 2005, 725-728, doi: 10.21437/Interspeech.2005-11
@inproceedings{bisani05_interspeech,
author={Maximilian Bisani and Hermann Ney},
title={{Open vocabulary speech recognition with flat hybrid models}},
year=2005,
booktitle={Proc. Interspeech 2005},
pages={725--728},
doi={10.21437/Interspeech.2005-11}
}