Publication Details
Out-of-Vocabulary Words Detection with Attention and CTC Alignments in an End-to-End ASR System
Vydana Hari Krishna
Burget Lukáš, doc. Ing., Ph.D. (DCGM)
Černocký Jan, prof. Dr. Ing. (DCGM)
Speech recognition, Out-of-vocabulary, OOV, Attention, CTC, End-to-end
This work explores the effectiveness of detecting positions of out-of-vocabulary
words (OOVs) in a decoded utterance using attention weights and CTC per-frame
outputs of an end-to-end system predicting word sequences. We show that the
end-to-end approach can be effective for the task of OOV detection. CTC
alignments are shown to provide better temporal information about the positions
of OOV words than attention, and therefore are more suitable for the task. The
detected positions of OOV occurrences are utilized for the recurrent OOV recovery
task in which probabilistic representations of the pronunciations of the detected
OOVs are clustered in order to find repeating words. Improved detection results
are shown to correlate with better performance of the recovery of recurrent
OOVs.
@inproceedings{BUT175843,
author="Ekaterina {Egorova} and Hari Krishna {Vydana} and Lukáš {Burget} and Jan {Černocký}",
title="Out-of-Vocabulary Words Detection with Attention and CTC Alignments in an End-to-End ASR System",
booktitle="Proceedings Interspeech 2021",
year="2021",
journal="Proceedings of Interspeech",
volume="2021",
number="8",
pages="2901--2905",
publisher="International Speech Communication Association",
address="Brno",
doi="10.21437/Interspeech.2021-1756",
issn="1990-9772",
url="https://www.isca-speech.org/archive/interspeech_2021/egorova21_interspeech.html"
}