Combining Multilingual Resources and Models to Develop State-of-the-Art E2E ASR for Swedish
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F46747885%3A24220%2F23%3A00011571" target="_blank" >RIV/46747885:24220/23:00011571 - isvavai.cz</a>
Result on the web
<a href="https://www.isca-archive.org/interspeech_2023/mateju23_interspeech.html" target="_blank" >https://www.isca-archive.org/interspeech_2023/mateju23_interspeech.html</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.21437/Interspeech.2023-737" target="_blank" >10.21437/Interspeech.2023-737</a>
Alternative languages
Result language
angličtina
Original language name
Combining Multilingual Resources and Models to Develop State-of-the-Art E2E ASR for Swedish
Original language description
In terms of automatic speech recognition (ASR), Swedish belongs to the group of less-resourced languages, as publicly available training data is limited to a few hundred hours of mostly read speech. To acquire larger amounts of more realistic data, we investigate the existing multilingual approaches, and also propose two new ones, which combine Swedish with previously created Norwegian data and models. We use them for efficient automatic harvesting of spoken Swedish from broadcast, parliament, YouTube, and audiobook archives. The combined models significantly speed up the harvesting process and improve the final Swedish end-to-end (E2E) ASR system. We evaluate it on datasets covering various applications and domains; they provide performance better than the state-of-the-art commercial cloud services. We have made all of our test datasets publicly available for future comparative experiments.
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
<a href="/en/project/TO01000027" target="_blank" >TO01000027: NORDTRANS - Technology for automatic speech transcription in selected Nordic languages</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>S - Specificky vyzkum na vysokych skolach
Others
Publication year
2023
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
2308-457X
e-ISSN
—
Number of pages
5
Pages from-to
3252 - 3256
Publisher name
ISCA
Place of publication
Dublin
Event location
Dublin, Irsko
Event date
Jan 1, 2023
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—