English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

This paper presents techniques and findings for improving the performance oflow-resource speech to text translation (ST). We conducted experiments on bothsimulated and real-low resource setups, on language pairs English - Portuguese,and Tamasheq - French respectively. Using the encoder-decoder framework for ST,our results show that a multilingual automatic speech recognition system actsas a good initialization under low-resource scenarios. Furthermore, using theCTC as an additional objective for translation during training and decodinghelps to reorder the internal representations and improves the finaltranslation. Through our experiments, we try to identify various factors(initializations, objectives, and hyper-parameters) that contribute the mostfor improvements in low-resource setups. With only 300 hours of pre-trainingdata, our model achieved 7.3 BLEU score on Tamasheq - French data,outperforming prior published works from IWSLT 2022 by 1.6 points.

Strategies for improving low resource speech to text translation relying on pre-trained ASR models