SpeechT: Findings of the First Mentorship in Speech Translation
This is an incremental report on mentorship activities in speech translation, primarily for researchers and practitioners in the field.
The paper details the first mentorship in speech translation, where participants tackled speech translation by exploring data augmentation and comparing end-to-end and cascaded systems across multiple languages, but no concrete results or numbers are reported.
This work presents the details and findings of the first mentorship in speech translation (SpeechT), which took place in December 2024 and January 2025. To fulfil the mentorship requirements, the participants engaged in key activities, including data preparation, modelling, and advanced research. The participants explored data augmentation techniques and compared end-to-end and cascaded speech translation systems. The projects covered various languages other than English, including Arabic, Bengali, Galician, Indonesian, Japanese, and Spanish.