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

Kód výsledku v 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>

Výsledek na webu

<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>

Jazyk výsledku

angličtina

Název v původním jazyce

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

Popis výsledku v původním jazyce

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.

Název v anglickém jazyce

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

Popis výsledku anglicky

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.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2022

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

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

ISBN

—

ISSN

1990-9772

e-ISSN

—

Počet stran výsledku

5

Strana od-do

1046-1050

Název nakladatele

International Speech Communication Association

Místo vydání

Incheon

Místo konání akce

Incheon Korea

Datum konání akce

18. 9. 2022

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—