无需外部语言模型，直接从脑电数据解码字符，准确率达23.8%。
End-to-End Intracortical Speech Decoding from Neural Activity
- 用端到端的Conformer模型直接解码皮层脑电信号。
- 无外部语言模型下字符错误率降至23.80%。
- 适合神经假体、脑机接口研发者参考。
当前高性能皮层内言语神经假体虽具低词错率，但通常依赖外部语言模型推理，导致内存、计算和延迟增加。本文研究在无外部语言模型情况下实现有意义的字符级解码是否可行。提出一种基于Conformer的端到端神经解码器，直接训练于肌萎缩侧索硬化症（ALS）患者皮层记录数据。在未见验证数据上，系统在无外部语言模型条件下达到23.80%的字符错误率（CER）。分析表明，性能波动主要由跨会话信号退化引起，主要错误源于错误的词边界分割。结果证明，在完全端到端框架下实现有效字符级解码是可行的，为下游语言处理提供强神经信号。
原文摘要 · Abstract (English)
Current high-performing intracortical speech neuroprostheses achieve low word error rates but typically rely on external language models during inference, increasing memory, computation, and latency. In this work, we investigate whether meaningful character-level decoding is achievable without such models. We propose an end-to-end Conformer-based neural decoder trained directly on intracortical recordings from a participant with amyotrophic lateral sclerosis (ALS). Without any external language model, the system achieves a character error rate (CER) of 23.80\% on held-out validation data. Analysis shows that performance variability is driven by inter-session signal degradation, while dominant errors arise from incorrect word boundary segmentation. These results demonstrate that effective character-level decoding is possible in a fully end-to-end framework, providing a strong neural signal for downstream linguistic processing.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。