Brain2Qwerty v2, 39% WER 달성 — 비침습적 BCI가 마침내 수술을 능가할 수 있을까?
meta의 fair lab이 meg 뇌 신호에서 음성을 디코딩하는 데 39%의 단어 오류율을 기록한 모델 brain2qwerty v2를 공개했습니다. 이로써 위험한 수술 없이 비침습적 브레인-컴퓨터 인터페이스가 임상 적용에 한 걸음 더 가까워졌습니다.
meta released brain2qwerty v2, a model that achieves a 39% word error rate (wer) by decoding continuous brain signals from magnetoencephalography (meg) data without requiring invasive surgery. the system, trained on 10 times more data than its predecessor, uses a deep learning pipeline and a fine-tuned qwen3 language model to convert motor cortex activity into coherent sentences, achieving perfect decoding in 28% of attempts for the best participant. while the model significantly outperforms previous versions in semantic accuracy, its reliance on a language model causes it to hallucinate grammatically correct but factually incorrect sentences when signal data is weak, resulting in a higher character error rate than raw encoders. this research signals a shift toward using scalable software and larger datasets to solve the 'last mile' problem in non-invasive bci, potentially removing the need for high-risk surgical implants for speech restoration.