Publication Details
Dealing with Unknowns in Continual Learning for End-to-end Automatic Speech Recognition
continual learning, multistream speech recognition, speech recognition
Learning continually from data is a task executed effortlessly by humans but
remains to be of significant challenge for machines. Moreover, when encountering
unknown test scenarios machines fail to generalize. We propose a mathematically
motivated dynamically expanding end-to-end model of independent
sequence-to-sequence components trained on different data sets that avoid
catastrophically forgetting knowledge acquired from previously seen data while
seamlessly integrating knowledge from new data. During inference, the likelihoods
of the unknown test scenario are computed using internal model activation
distributions. The inference made by each independent component is weighted by
the normalized likelihood values to obtain the final decision.
@inproceedings{BUT182527,
author="ŠŮSTEK, M. and SADHU, S. and HEŘMANSKÝ, H.",
title="Dealing with Unknowns in Continual Learning for End-to-end Automatic Speech Recognition",
booktitle="Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH",
year="2022",
journal="Proceedings of Interspeech",
volume="2022",
number="9",
pages="1046--1050",
publisher="International Speech Communication Association",
address="Incheon",
doi="10.21437/Interspeech.2022-11139",
issn="1990-9772",
url="https://www.isca-speech.org/archive/pdfs/interspeech_2022/sustek22_interspeech.pdf"
}