Conference paper Open Access
Potapczyk, Tomasz; Przybysz, Pawel; Chochowski, Marcin; Szumaczuk, Artur
This paper describes the submission to IWSLT 2019 End- to-End speech translation task by Samsung R&D Institute, Poland. We decided to focus on end-to-end English to German TED lectures translation and did not provide any submission for other speech tasks. We used a slightly altered Transformer architecture with standard convolutional layer preparing the audio input to Transformer en- coder. Additionally, we propose an audio segmentation al- gorithm maximizing BLEU score on tst2015 test set.
Name | Size | |
---|---|---|
IWSLT2019_paper_31.pdf
md5:236e612f3383a1ec298769550370d411 |
104.9 kB | Download |
All versions | This version | |
---|---|---|
Views | 565 | 565 |
Downloads | 429 | 429 |
Data volume | 45.0 MB | 45.0 MB |
Unique views | 503 | 503 |
Unique downloads | 396 | 396 |