Home >

news Help

Publication Information


Title
Japanese: 
English:Transformer-Based Estimation of Spoken Sentences Using Electrocorticography 
Author
Japanese: Shuji Komeiji, Kai Shigemi, Takumi Mitsuhashi, Yasushi Iimura, Hiroharu Suzuki, Hidenori Sugano, 篠田 浩一, 田中 聡久.  
English: Shuji Komeiji, Kai Shigemi, Takumi Mitsuhashi, Yasushi Iimura, Hiroharu Suzuki, Hidenori Sugano, Koichi Shinoda, Toshihisa Tanaka.  
Language English 
Journal/Book name
Japanese: 
English:ICASSP2022 
Volume, Number, Page        
Published date May 2022 
Publisher
Japanese: 
English:IEEE 
Conference name
Japanese: 
English:2022 IEEE International Conference on Acoustics, Speech and Signal Processing 
Conference site
Japanese: 
English: 
Official URL https://ieeexplore.ieee.org/document/9747443
 
DOI https://doi.org/10.1109/ICASSP43922.2022.9747443
Abstract 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.

©2007 Tokyo Institute of Technology All rights reserved.