Dear Colleagues,

If you are interested in speech synthesis and translation, we are
organizing the *Cross-Lingual Voice Cloning Track at IWSLT 2026*. This
shared task addresses one of the most challenging areas in speech
technology, cloning a speaker's voice across different languages.

*The Challenge:* Given a small set of audio samples from a speaker in a
source language, the task is to synthesize natural-sounding speech for
unseen content in a target language, while preserving the speaker's voice
characteristics.

Why does this matter? Voice cloning is beneficial in multiple domains:

   - Speaker Standardization: Streamlining voices in speech systems
   efficiently without recording everything from scratch
   - Education: Creating age-appropriate, culturally relevant voice
   experiences
   - Accessibility: Personalizing assistive communication tools


*Important dates:*
1st April 2026 Release of blind test data
15th April 2026 System submission deadline
24th April 2026 System paper submission deadline

*Task details:* https://iwslt.org/2026/voice-cloning

If you have any questions, please feel free to contact me. Looking forward
to your participation!

Best regards,
Yasmin Moslem <https://www.linkedin.com/in/yasmin-moslem/>

Reply via email to