AppTek Achieves Top Ranking at the International Workshop in Spoken Language Translation's (IWSLT) 2021 Evaluation Campaign
AppTek entered the competition to measure the performance of its end-to-end SLT system against other leading platforms developed by corporate and academic science teams around the world.
- AppTek entered the competition to measure the performance of its end-to-end SLT system against other leading platforms developed by corporate and academic science teams around the world.
- For the first time in company history, AppTek's direct speech translation system outperformed our alternative cascaded approach," said Evgeny Matusov, Lead Science Architect, Machine Translation, at AppTek.
- Spoken language translation has traditionally been performed through cascaded approaches whereby a speech transcript is first created by an automatic speech recognition system and then translated using an MT system.
- AppTek scientists Parnia Bahar and Patrick Wilken will present the details of AppTek's submission at this year's online IWSLT conference on August 5-6, 2021.