Li Sheng /listen/ speech recognition assist. prof. @cs_lisheng
◆2025 new faculty of Science Tokyo
◆Speech tech+multilingual+multimodal+security
◆Welcome collaboration, discussion
CV: https://t.co/naL0tJB3sIscholar.google.com/citations?user… JapanJoined January 2013
Just dropped more ASR model on HF!
• Tiny (27M params) monolingual ASR for Arabic, Chinese, Japanese, Korean, Ukrainian & Vietnamese
• Beats Whisper Tiny with 48% lower error rates
• Outperforms 9× larger Whisper Small, rivals 28× bigger Whisper Medium
• Runs 5–15×…
Microsoft just released VibeVoice-7B on Hugging Face.
Explore their latest 7B parameter model for advanced voice AI.
It's now available for the community to discover and use.
huggingface.co/microsoft/Vibe…
Advanced Robotics誌で去年 Best Survey Paper Awardをもらった「世界モデルの認知発達ロボティクスにおける展望論文」がGoogle Scholar でちょうど100 citationになってた。キリ番。
tandfonline.com/doi/full/10.10…
If you missed my keynote at INTERSPEECH-2025 (or would like to see it again), it’s now available online at interspeech2025.org/recordings - my bit is Keynote 1 and it starts at 1:05:30
While expanding more evaluation metrics in VERSA (github.com/wavlab-speech/…), we’ve been thinking bigger -> a unified, fast, and effective solution for evaluating them all at once.
Meet UniVERSA at Tue, 14:10-14:30
📍 A12O3 – Speech Assessment (Presented by @shinjiw_at_cmu )
🚀 Big update: Open ASR goes multilingual!
We’re kicking off with 🇩🇪🇫🇷🇮🇹🇪🇸🇵🇹 — German, French, Italian, Spanish & Portuguese.
English ASR has reached a strong level of maturity, so we’re exploring new languages 🌍
More languages coming soon… Which one should we add next?
160 Followers 142 FollowingAssistant Prof @ SAI, SJTU.
I am interested in speech signal processing, robust speech recognition, and self-supervised speech pretraining.
106 Followers 126 FollowingISCA Postdoc & Early Career Researcher Advisory Committee ---
We work in speech (industry and academia) and we're recruiting new members!
237 Followers 218 FollowingNPU SWE @ https://t.co/UFACb13lcx //
Previously @ MARG (Music and Audio Research Group), Seoul National University. Opinions are my own.
2K Followers 46 FollowingLearn how to build AI Agents & sell them to local businesses 💸 Founder of @getoutbox_ai Learn how to build AI Agents for FREE 👉 https://t.co/q9zPwllLOC
318 Followers 227 FollowingWorking on LLM/VLM Tool Learning and Reasoning at Tsinghua and Bytedance, reading at least one paper a day — The future will not invent itself.
297 Followers 326 FollowingPrincipal Scientist at Qatar Computing Research Institute, Hamad Bin Khalifa University
Senior Member of IEEE and ACM
Past: UC Berkeley, Koç University
6K Followers 344 FollowingQatar Computing Research Institute. Artificial Intelligence- Data Analytics-Social Computing-Cyber Security-Arabic Language Technologies.@QatarFoundation Member
560 Followers 1 FollowingSharing daily personal notes on selected interesting Embodied AI papers, blogs and talks | Maintained by @yilun_chen_ | Opinions are my own.
722 Followers 112 FollowingThe official Twitter account for the Department of Electrical and Computer Engineering at the University of Wisconsin-Madison
121K Followers 639 FollowingMila Scientific Director. Ex @Google DeepMind & Twitter Cortex. Father of 4. // Directeur scientifique à Mila. Ex @Google DeepMind & Twitter Cortex. Père de 4.
826 Followers 755 FollowingAssociate Professor: Humanities & Social Sciences - author, educator
international academic mobility| sociolinguistics| digitalization of HE
1K Followers 1K FollowingLecturer of NLP @SheffieldNLP, previous Research Fellow @UCL, PhD @TerrierTeam Glasgow Uni. Research interests in Conversational AI, RAG and topics of NLP & IR.