ESPnet-ST-v2: Multipurpose Spoken Language Translation Toolkit
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F23%3A10475831" target="_blank" >RIV/00216208:11320/23:10475831 - isvavai.cz</a>
Result on the web
<a href="https://aclanthology.org/2023.acl-demo.38/" target="_blank" >https://aclanthology.org/2023.acl-demo.38/</a>
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
ESPnet-ST-v2: Multipurpose Spoken Language Translation Toolkit
Original language description
ESPnet-ST-v2 is a revamp of the open-source ESPnet-ST toolkit necessitated by the broadening interests of the spoken language translation community. ESPnet-ST-v2 supports 1) offline speech-to-text translation (ST), 2) simultaneous speech-to-text translation (SST), and 3) offline speech-to-speech translation (S2ST) -- each task is supported with a wide variety of approaches, differentiating ESPnet-ST-v2 from other open source spoken language translation toolkits. This toolkit offers state-of-the-art architectures such as transducers, hybrid CTC/attention, multi-decoders with searchable intermediates, time-synchronous blockwise CTC/attention, Translatotron models, and direct discrete unit models. In this paper, we describe the overall design, example models for each task, and performance benchmarking behind ESPnet-ST-v2, which is publicly available at https://github.com/espnet/espnet.
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
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 61st Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)
ISBN
978-1-941643-00-6
ISSN
—
e-ISSN
—
Number of pages
12
Pages from-to
400-411
Publisher name
Association for Computational Linguistics
Place of publication
Stroudsburg, PA, USA
Event location
Toronto, Canada
Event date
Jul 9, 2023
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—