2 |
VoxPopuli: A Large-Scale Multilingual Speech Corpus for Representation Learning, Semi-Supervised Learning and Interpretation
|
|
|
|
In: https://hal.inria.fr/hal-03329290 ; 2021, ⟨10.18653/v1/2021.acl-long.80⟩ (2021)
|
|
BASE
|
|
Show details
|
|
3 |
Lightweight Adapter Tuning for Multilingual Speech Translation
|
|
|
|
In: The Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (ACL-IJCNLP 2021) ; https://hal.archives-ouvertes.fr/hal-03294912 ; The Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (ACL-IJCNLP 2021), Aug 2021, Bangkok (Virtual), Thailand (2021)
|
|
BASE
|
|
Show details
|
|
4 |
FST: the FAIR Speech Translation System for the IWSLT21 Multilingual Shared Task ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
VoxPopuli: A Large-Scale Multilingual Speech Corpus for Representation Learning, Semi-Supervised Learning and Interpretation ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
Lightweight Adapter Tuning for Multilingual Speech Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
Pay Better Attention to Attention: Head Selection in Multilingual and Multi-Domain Sequence Modeling ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
Improving Speech Translation by Understanding and Learning from the Auxiliary Text Translation Task ...
|
|
|
|
BASE
|
|
Show details
|
|
9 |
Lightweight Adapter Tuning for Multilingual Speech Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
10 |
Multilingual Speech Translation from Efficient Finetuning of Pretrained Models ...
|
|
|
|
BASE
|
|
Show details
|
|
11 |
VoxPopuli: A Large-Scale Multilingual Speech Corpus for Representation Learning, Semi-Supervised Learning and Interpretation ...
|
|
|
|
BASE
|
|
Show details
|
|
13 |
Dual-decoder Transformer for Joint Automatic Speech Recognition and Multilingual Speech Translation
|
|
|
|
In: COLING 2020 (long paper) ; https://hal.archives-ouvertes.fr/hal-02991564 ; COLING 2020 (long paper), Dec 2020, Virtual, Spain (2020)
|
|
BASE
|
|
Show details
|
|
14 |
Dual-decoder Transformer for Joint Automatic Speech Recognition and Multilingual Speech Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
15 |
CoVoST: A Diverse Multilingual Speech-To-Text Translation Corpus ...
|
|
|
|
BASE
|
|
Show details
|
|
16 |
CoVoST 2 and Massively Multilingual Speech-to-Text Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
17 |
Multilingual Speech Translation with Efficient Finetuning of Pretrained Models ...
|
|
|
|
BASE
|
|
Show details
|
|
18 |
Dual-decoder Transformer for Joint Automatic Speech Recognition and Multilingual Speech Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
19 |
Dual-decoder Transformer for Joint Automatic Speech Recognition and Multilingual Speech Translation ...
|
|
|
|
Abstract:
We introduce dual-decoder Transformer, a new model architecture that jointly performs auto- matic speech recognition (ASR) and multilingual speech translation (ST). Our models are based on the original Transformer architecture (Vaswani et al., 2017) but consist of two decoders, each responsible for one task (ASR or ST). Our major contribution lies in how these decoders interact with each other: one decoder can attend to different information sources from the other via a dual-attention mechanism. We propose two variants of these architectures corresponding to two different levels of dependencies between the decoders, called the parallel and cross dual decoder Transformers, respectively. Extensive experiments on the MuST-C dataset show that our models outperform the previously reported highest translation performance in the multilingual settings, and outperform as well bilingual one-to-one results. Furthermore, our parallel models demon- strate no trade-off between ASR and ST compared to the vanilla multi-task ...
|
|
Keyword:
Dual-decoder Transformer, multilingual speech translation
|
|
URL: https://dx.doi.org/10.5281/zenodo.4563217 https://zenodo.org/record/4563217
|
|
BASE
|
|
Hide details
|
|
20 |
Dual-decoder Transformer for Joint Automatic Speech Recognition and Multilingual Speech Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|