Dealing with Unknowns in Continual Learning for End-to-end Automatic Speech Recognition
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F22%3APU147440" target="_blank" >RIV/00216305:26230/22:PU147440 - isvavai.cz</a>
Result on the web
<a href="https://www.isca-speech.org/archive/pdfs/interspeech_2022/sustek22_interspeech.pdf" target="_blank" >https://www.isca-speech.org/archive/pdfs/interspeech_2022/sustek22_interspeech.pdf</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.21437/Interspeech.2022-11139" target="_blank" >10.21437/Interspeech.2022-11139</a>
Alternative languages
Result language
angličtina
Original language name
Dealing with Unknowns in Continual Learning for End-to-end Automatic Speech Recognition
Original language description
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.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
—
Continuities
S - Specificky vyzkum na vysokych skolach
Others
Publication year
2022
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
ISBN
—
ISSN
1990-9772
e-ISSN
—
Number of pages
5
Pages from-to
1046-1050
Publisher name
International Speech Communication Association
Place of publication
Incheon
Event location
Incheon Korea
Event date
Sep 18, 2022
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—