Result Details

Dealing with Unknowns in Continual Learning for End-to-end Automatic Speech Recognition

ŠŮSTEK, M.; SADHU, S.; HEŘMANSKÝ, H. Dealing with Unknowns in Continual Learning for End-to-end Automatic Speech Recognition. In Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. Proceedings of Interspeech. Incheon: International Speech Communication Association, 2022. no. 9, p. 1046-1050. ISSN: 1990-9772.
Type
conference paper
Language
English
Authors
Abstract

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.

Keywords

continual learning, multistream speech recognition, speech recognition

URL
Published
2022
Pages
1046–1050
Journal
Proceedings of Interspeech, vol. 2022, no. 9, ISSN 1990-9772
Proceedings
Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
Conference
Interspeech Conference
Publisher
International Speech Communication Association
Place
Incheon
DOI
UT WoS
000900724501045
EID Scopus
BibTeX
@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"
}
Projects
Spolehlivé, bezpečné a efektivní počítačové systémy, BUT, Vnitřní projekty VUT, FIT-S-20-6427, start: 2020-03-01, end: 2023-02-28, completed
Research groups
Departments
Back to top