Zobrazeno 1 - 10
of 18
pro vyhledávání: '"Marco Gaido"'
Publikováno v:
IJCoL, Vol 8, Iss 1 (2022)
Direct speech-to-text translation (ST) is an emerging approach that consists in performing the ST task with a single neural model. Although this paradigm comes with the promise to outperform the traditional pipeline systems, its rise is still limited
Externí odkaz:
https://doaj.org/article/73cc755e6d584e2fbd696424b645dc6f
Publikováno v:
Transactions of the Association for Computational Linguistics, Vol 9, Pp 845-874 (2021)
AbstractMachine translation (MT) technology has facilitated our daily tasks by providing accessible shortcuts for gathering, processing, and communicating information. However, it can suffer from biases that harm users and society at large. As a rela
Externí odkaz:
https://doaj.org/article/ebea9608538e4b829ead431e045f7af0
The primary goal of this FBK's systems submission to the IWSLT 2022 offline and simultaneous speech translation tasks is to reduce model training costs without sacrificing translation quality. As such, we first question the need of ASR pre-training,
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d842d6756bf8a2002ebfde10ae47c6b6
http://arxiv.org/abs/2205.02629
http://arxiv.org/abs/2205.02629
Gender bias is largely recognized as a problematic phenomenon affecting language technologies, with recent studies underscoring that it might surface differently across languages. However, most of current evaluation practices adopt a word-level focus
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4abf1eacbd8e92fab55df8e3ce048480
Publikováno v:
Proceedings of the 4th Workshop on Gender Bias in Natural Language Processing (GeBNLP).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e4e39e48c7abaacde20a4643df090e0a
https://doi.org/10.18653/v1/2022.gebnlp-1.12
https://doi.org/10.18653/v1/2022.gebnlp-1.12
Publikováno v:
IWSLT
Speech translation (ST) has lately received growing interest for the generation of subtitles without the need for an intermediate source language transcription and timing (i.e. captions). However, the joint generation of source captions and target su
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9e0b30888667671eca73a0078b36807f
http://arxiv.org/abs/2107.06246
http://arxiv.org/abs/2107.06246
Publikováno v:
IWSLT
This paper describes FBK's system submission to the IWSLT 2021 Offline Speech Translation task. We participated with a direct model, which is a Transformer-based architecture trained to translate English speech audio data into German texts. The train
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6a6bd47e798e17429ab55420aedc85ec
http://arxiv.org/abs/2106.12607
http://arxiv.org/abs/2106.12607
Publikováno v:
Università degli di Trento-IRIS
Scopus-Elsevier
EACL
Scopus-Elsevier
EACL
Previous studies demonstrated that a dynamic phone-informed compression of the input audio is beneficial for speech translation (ST). However, they required a dedicated model for phone recognition and did not test this solution for direct ST, in whic
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5649981242a11a730e9599d9fb1ab161
http://arxiv.org/abs/2102.01578
http://arxiv.org/abs/2102.01578
Publikováno v:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing.
Automatic translation systems are known to struggle with rare words. Among these, named entities (NEs) and domain-specific terms are crucial, since errors in their translation can lead to severe meaning distortions. Despite their importance, previous
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::db50b34a61e5496b671bf4e32c4a0ae1
https://doi.org/10.18653/v1/2021.emnlp-main.128
https://doi.org/10.18653/v1/2021.emnlp-main.128
Transformer-based models have gained increasing popularity achieving state-of-the-art performance in many research fields including speech translation. However, Transformer's quadratic complexity with respect to the input sequence length prevents its
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f406774dac5a083b82cd5697653e3ccb