Combining Semantic Word Classes and Sub-Word Unit Speech Recognition for Robust OOV Detection

Axel Horndasch, Anton Batliner, Caroline Kaufhold, Elmar Nöth


Out-of-vocabulary words (OOVs) are often the main reason for the failure of tasks like automated voice searches or human-machine dialogs. This is especially true if rare but task-relevant content words, e.g. person or location names, are not in the recognizer’s vocabulary. Since applications like spoken dialog systems use the result of the speech recognizer to extract a semantic representation of a user utterance, the detection of OOVs as well as their (semantic) word class can support to manage a dialog successfully. In this paper we suggest to combine two well-known approaches in the context of OOV detection: semantic word classes and OOV models based on sub-word units. With our system, which builds upon the widely used Kaldi speech recognition toolkit, we show on two different data sets that — compared to other methods — such a combination improves OOV detection performance for open word classes at a given false alarm rate. Another result of our approach is a reduction of the word error rate (WER).


DOI: 10.21437/Interspeech.2016-1250

Cite as

Horndasch, A., Batliner, A., Kaufhold, C., Nöth, E. (2016) Combining Semantic Word Classes and Sub-Word Unit Speech Recognition for Robust OOV Detection. Proc. Interspeech 2016, 1335-1339.

Bibtex
@inproceedings{Horndasch+2016,
author={Axel Horndasch and Anton Batliner and Caroline Kaufhold and Elmar Nöth},
title={Combining Semantic Word Classes and Sub-Word Unit Speech Recognition for Robust OOV Detection},
year=2016,
booktitle={Interspeech 2016},
doi={10.21437/Interspeech.2016-1250},
url={http://dx.doi.org/10.21437/Interspeech.2016-1250},
pages={1335--1339}
}