Detail publikačního výsledku

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

ŠŮSTEK, M.; SADHU, S.; HEŘMANSKÝ, H.

Originální název

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

Anglický název

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

Druh

Stať ve sborníku v databázi WoS či Scopus

Originální abstrakt

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.

Anglický abstrakt

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.

Klíčová slova

continual learning, multistream speech recognition, speech recognition

Klíčová slova v angličtině

continual learning, multistream speech recognition, speech recognition

Autoři

ŠŮSTEK, M.; SADHU, S.; HEŘMANSKÝ, H.

Rok RIV

2023

Vydáno

01.09.2022

Nakladatel

International Speech Communication Association

Místo

Incheon

Kniha

Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH

ISSN

1990-9772

Periodikum

Proceedings of Interspeech

Svazek

2022

Číslo

9

Stát

Francouzská republika

Strany od

1046

Strany do

1050

Strany počet

5

URL

https://www.isca-speech.org/archive/pdfs/interspeech_2022/sustek22_interspeech.pdf

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"
}