Miguel Angrick, Maarten Ottenhoff, Lorenz Diener, Darius Ivucic, Gabriel Ivucic, Sophocles Goulis, Jeremy Saal, Albert Colon, Louis Wagner, Dean Krusienski, Pieter Kubben, Tanja Schultz, Christian Herff
Reference:
Real-time synthesis of imagined speech processes from minimally invasive recordings of neural activity (Miguel Angrick, Maarten Ottenhoff, Lorenz Diener, Darius Ivucic, Gabriel Ivucic, Sophocles Goulis, Jeremy Saal, Albert Colon, Louis Wagner, Dean Krusienski, Pieter Kubben, Tanja Schultz, Christian Herff), in Nature Communications Biology, volume 4, number 1, pages 1–10, December 2021
Bibtex Entry:
@article{angrick2021real,
title = {Real-time synthesis of imagined speech processes from minimally invasive
recordings of neural activity},
author = {Angrick, Miguel and Ottenhoff, Maarten and Diener, Lorenz and Ivucic, Darius and
Ivucic, Gabriel and Goulis, Sophocles and Saal, Jeremy and Colon, Albert and Wagner, Louis and
Krusienski, Dean and Kubben, Pieter and Schultz, Tanja and Herff, Christian},
year = 2021,
month = dec,
journal = {Nature Communications Biology},
publisher = {Nature Publishing Group},
volume = 4,
number = 1,
pages = {1--10},
video = {https://www.youtube.com/watch?v=2m8bUYZP-Eo},
doi = {10.1101/2020.12.11.421149},
abstract = {Speech neuroprosthetics aim to provide a natural communication channel to
individuals who are unable to speak due to physical or neurological impairments. Real-time
synthesis of acoustic speech directly from measured neural activity could enable natural
conversations and notably improve quality of life, particularly for individuals who have
severely limited means of communication. Recent advances in decoding approaches have led to high
quality reconstructions of acoustic speech from invasively measured neural activity. However,
most prior research utilizes data collected during open-loop experiments of articulated speech,
which might not directly translate to imagined speech processes. Here, we present an approach
that synthesizes audible speech in real-time for both imagined and whispered speech conditions.
Using a participant implanted with stereotactic depth electrodes, we were able to reliably
generate audible speech in real-time. The decoding models rely predominately on frontal activity
suggesting that speech processes have similar representations when vocalized, whispered, or
imagined. While reconstructed audio is not yet intelligible, our real-time synthesis approach
represents an essential step towards investigating how patients will learn to operate a
closed-loop speech neuroprosthesis based on imagined speech},
url = {https://halcy.de/cites/pdf/angrick2021real.pdf},
}