计算机科学
变压器
解码方法
语音识别
编码器
皮质电图
判决
短语
口语
短时记忆
人工智能
自然语言处理
模式识别(心理学)
脑电图
电压
算法
工程类
心理学
循环神经网络
电气工程
精神科
操作系统
人工神经网络
作者
Shuji Komeiji,Kai Shigemi,Takumi Mitsuhashi,Yasushi Iimura,Hiroharu Suzuki,Hidenori Sugano,Koichi Sairyo,Toshihisa Tanaka
标识
DOI:10.1109/icassp43922.2022.9747443
摘要
Invasive brain–machine interfaces (BMIs) are a promising neurotechnological venture for achieving direct speech communication from a human brain, but it faces many challenges. In this paper, we measured the invasive electrocorticogram (ECoG) signals from seven participating epilepsy patients as they spoke a sentence consisting of multiple phrases. A Transformer encoder was incorporated into a "sequence-to-sequence" model to decode spoken sentences from the ECoG. The decoding test revealed that the use of the Transformer model achieved a minimum phrase error rate (PER) of 16.4%, and the median (±standard deviation) across seven participants was 31.3% (±10.0%). Moreover, the proposed model with the Transformer achieved significantly better decoding accuracy than a conventional long short-term memory model.
科研通智能强力驱动
Strongly Powered by AbleSci AI