@t0m1ab: Heading to ICML 2026 in Seoul next week with @romfbr31 to present Hibiki-Zero[https://kyutai.org/blog/2026-02-12-hibiki…
Summary
Kyutai presents Hibiki-Zero, a real-time speech-to-speech translation model, at ICML 2026 in Seoul, with an oral presentation scheduled for July 8.
View Cached Full Text
Cached at: 06/30/26, 05:51 PM
Heading to ICML 2026 in Seoul next week with @romfbr31 to present Hibiki-Zero🇫🇷🇬🇧🇵🇹🇪🇸🇩🇪[https://t.co/D7gadZ36Ib], Kyutai’s latest real-time speech translation model. I’ll be giving an oral presentation on July 8 at 10:30 AM KST. Feel free to join if you’d like to learn more!💬 https://t.co/B0JzvUGNSq
Simultaneous Speech-to-Speech Translation Without Aligned Data
Source: https://kyutai.org/blog/2026-02-12-hibiki-zero/ Kyutai is funded by Iliad Group, CMA CGM Group and Schmidt Sciences. Many thanks to our generous donors.
Similar Articles
@sainingxie: see you at ICML in Seoul and the AMI × SBVA mixer on thursday evening! looking forward to meeting everyone :)
Saining Xie announces his attendance at ICML in Seoul and invites people to the AMI Labs × SBVA mixer on Thursday evening, a networking event for AI researchers and investors.
@tom_doerr: Zero-shot voice cloning for 30 languages https://github.com/sunnyxrxrx/X-Voice…
X-Voice is a flow-matching-based multilingual text-to-speech system that enables zero-shot voice cloning across 30 languages, with open-source code, model, and demo available.
@Thom_Wolf: Most people should probably update their priors on the state of open-source speech-to-speech. It's honestly kind of min…
Thom Wolf and Cerebras released a fully open-source realtime voice demo with models and code, showcasing state-of-the-art speech-to-speech capabilities.
@zijianwang30: At @icmlconf this week and excited to host the 5th @DL4Code this Friday! We have an amazing lineup of speakers: - @Diyi…
Zijian Wang announces hosting the 5th DL4Code workshop at ICML this Friday with an impressive speaker lineup and mentions two past interns presenting their papers at the main conference.
NAVER LABS Europe Submission to the Instruction-following 2026 Short Track
This paper describes NAVER LABS Europe's submission to the IWSLT 2026 instruction-following short track, improving upon their previous winning system by using a new speech projector (SpeechMapper) trained solely on ASR data and augmenting training with a synthetic SQA dataset (fakACL). The resulting system ties for first place in the constrained track while using a weaker LLM backbone.