Dual-decoder Transformer

Reported on 4 benchmarks across 1 task · 1 paper · 4 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Natural Language Processing4 results

Speech-to-Text TranslationonMuST-C EN->FR
Case-sensitive sacreBLEU· 2020-11-02
33.45
SOTA
Dual-decoder Transformer for Joint Automatic Speech Recognition and Multilingual Speech Translation arXiv:2011.00747
Speech-to-Text TranslationonMuST-C EN->DE
Case-sensitive sacreBLEU· 2020-11-02
23.63
best: 28.88 (Task Modulation + Multitask Learning(ASR/MT) + Data Augmentation)
SOTA
Dual-decoder Transformer for Joint Automatic Speech Recognition and Multilingual Speech Translation arXiv:2011.00747
Speech-to-Text TranslationonMuST-C
SacreBLEU· 2020-11-02
25.62
best: 26.61 (Transformer with Adapters)
SOTA
Dual-decoder Transformer for Joint Automatic Speech Recognition and Multilingual Speech Translation arXiv:2011.00747
Speech-to-Text TranslationonMuST-C EN->ES
Case-sensitive sacreBLEU· 2020-11-02
28.12
best: 28.73 (Transformer with Adapters)
SOTA
Dual-decoder Transformer for Joint Automatic Speech Recognition and Multilingual Speech Translation arXiv:2011.00747