JHU IWSLT 2024 Dialectal and Low-resource System Description

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F25%3APXAQ5NK5" target="_blank" >RIV/00216208:11320/25:PXAQ5NK5 - isvavai.cz</a>

Result on the web

<a href="https://www.scopus.com/inward/record.uri?eid=2-s2.0-85204370217&partnerID=40&md5=805772f42861eabf1f8ee49cb9e8c57b" target="_blank" >https://www.scopus.com/inward/record.uri?eid=2-s2.0-85204370217&partnerID=40&md5=805772f42861eabf1f8ee49cb9e8c57b</a>

DOI - Digital Object Identifier

—

Result language

angličtina

Original language name

JHU IWSLT 2024 Dialectal and Low-resource System Description

Original language description

Johns Hopkins University (JHU) submitted systems for all eight language pairs in the 2024 Low-Resource Language Track. The main effort of this work revolves around fine-tuning large and publicly available models in three proposed systems: i) end-to-end speech translation (ST) fine-tuning of SEAMLESSM4T v2; ii) ST fine-tuning of Whisper; iii) a cascaded system involving automatic speech recognition with fine-tuned Whisper and machine translation with NLLB. On top of systems above, we conduct a comparative analysis of different training paradigms, such as intra-distillation of NLLB, joint training and curriculum learning of SEAMLESSM4T v2, and multi-task learning and pseudo-translation with Whisper. Our results show that the best-performing approach differs by language pairs, but that i) fine-tuned SEAMLESSM4T v2 tends to perform best for source languages on which it was pre-trained, ii) multitask training helps Whisper fine-tuning, iii) cascaded systems with Whisper and NLLB tend to outperform Whisper alone, and iv) intra-distillation helps NLLB fine-tuning. ©2024 Association for Computational Linguistics.

Czech name

—

Czech description

—

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)

Project

—

Continuities

—

Publication year

2024

Confidentiality

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

Article name in the collection

IWSLT - Int. Conf. Spok. Lang. Transl., Proc. Conf.

ISBN

979-889176141-4

ISSN

—

e-ISSN

—

Number of pages

14

Pages from-to

188-201

Publisher name

Association for Computational Linguistics (ACL)

Place of publication

—

Event location

Hybrid, Bangkok

Event date

Jan 1, 2025

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

—