Publication Details
Out-of-Vocabulary Word Recovery Using FST-Based Subword Unit Clustering in a Hybrid ASR System
Burget Lukáš, doc. Ing., Ph.D. (DCGM)
Out-of-vocabulary Words, Robust ASR
The paper presents a new approach to extracting useful information from out-of-vocabulary (OOV) speech regions in ASR system output. The system makes use of a hybrid decoding network with both words and sub-word units. In the decoded lattices, candidates for OOV regions are identified as sub-graphs of sub-word units. To facilitate OOV word recovery, we search for recurring OOVs by clustering the detected candidate OOVs. The metrics for clustering is based on a comparison of the sub-graphs corresponding to the OOV candidates. The proposed method discovers repeating outof- vocabulary words and finds their graphemic representation more robustly than more conventional techniques taking into account only one best sub-word string hypotheses.
@inproceedings{BUT155047,
author="Ekaterina {Egorova} and Lukáš {Burget}",
title="Out-of-Vocabulary Word Recovery Using FST-Based Subword Unit Clustering in a Hybrid ASR System",
booktitle="Proceedings of ICASSP 2018",
year="2018",
pages="5919--5923",
publisher="IEEE Signal Processing Society",
address="Calgary",
doi="10.1109/ICASSP.2018.8462221",
isbn="978-1-5386-4658-8",
url="https://www.fit.vut.cz/research/publication/11725/"
}