Kaylo Littlejohn
@KayloLittlejohn
PhD student @Berkeley_AI | Senior ML Engineer @Roblox | Brain-to-Voice & Brain-to-Avatar | AI · NLP · Speech
1/n) Our latest work is out today in @NatureNeuro! We developed a streaming “brain-to-voice” neuroprosthesis which restores naturalistic, fluent, intelligible speech to a person who has paralysis. nature.com/articles/s4159…
Work led by BAIR students @KayloLittlejohn and @CheolJunCho advised by BAIR faculty @GopalaSpeech "...made it possible to synthesize brain signals into speech in close to real-time." dailycal.org/news/campus/re… via @dailycal
This is a truly exceptional result. An instantaneous brain-to-voice synthesizer with paralinguistic features like prosody. Congratulations @Maitreyee_W @BrainGateTeam on the monumental achievement!
Our brain-to-voice synthesis brain-computer interface paper was published in @Nature today! This neuroprosthesis synthesized the voice of a man with ALS instantaneously, enabling him to ‘speak’ flexibly and modulate the prosody of his BCI-voice. 1/7 Paper: rdcu.be/eqH3C
being good at ML systems helps you run more experiments. being good at ML theory helps you run less experiments
Excited to build on pioneering work from @WillettNeuro, @SergeyStavisky, and Eddie Chang labs showing 3–4x faster communication (60–80 words per minute) to approach natural speech speed!
Humans just saw a *new* color—literally outside the known visual spectrum. BAIR faculty and visual computing expert Ren Ng and collaborators made it possible with the Oz Vision System. 🌈👁️ Newly published in @ScienceAdvances: science.org/doi/10.1126/sc… popsci.com/health/new-col…
Scientists have developed a device that can translate thoughts about speech into spoken words in real time. Although it’s still experimental, they hope the brain-computer interface could someday help give voice to those unable to speak.
A brain-reading implant that translates neural signals into audible speech has allowed a woman with paralysis to hear what she intends to say nearly instantly go.nature.com/4iNk8l0
Today's "DeepSeek selloff" in the stock market -- attributed to DeepSeek V3/R1 disrupting the tech ecosystem -- is another sign that the application layer is a great place to be. The foundation model layer being hyper-competitive is great for people building applications.
Huge thanks to everyone who has shared the wonderful journey with us for LLM Agents MOOC Fall 2024, with ~15K registered learners, & 2500+ developers participating in LLM Agents MOOC hackathon! Join us for Advanced LLM Agents MOOC: llmagents-learning.org/sp25, starting Jan 27, 2025
Today we released Meta Spirit LM — our first open source multimodal language model that freely mixes text and speech. Many existing AI voice experiences today use ASR to techniques to process speech before synthesizing with an LLM to generate text — but these approaches…
Interested in speech neuroprostheses? Come to the #SfN24 minisymposium organized by @HerffC and I. We have a fantastic lineup chosen to survey the many directions this field can go in: different recording modalities, languages, and behaviors (e.g. attempted vs. imagined speech).