Show simple item record

dc.contributor.author
Kohler, Jonas
dc.contributor.author
Ottenhoff, Marten
dc.contributor.author
Goulis, Sophocles
dc.contributor.author
Angrick, Miguel
dc.contributor.author
Colon, Albert
dc.contributor.author
Wagner, Louis
dc.contributor.author
Tousseyn, Simon
dc.contributor.author
Kubben, Pieter L.
dc.contributor.author
Herff, Christian
dc.date.accessioned
2023-09-07T13:11:01Z
dc.date.available
2023-01-19T08:19:41Z
dc.date.available
2023-03-14T07:01:26Z
dc.date.available
2023-03-14T07:04:43Z
dc.date.available
2023-07-27T12:19:56Z
dc.date.available
2023-09-07T13:11:01Z
dc.date.issued
2022-12-09
dc.identifier.issn
2690-2664
dc.identifier.other
10.51628/001c.57524
en_US
dc.identifier.uri
http://hdl.handle.net/20.500.11850/593495
dc.identifier.doi
10.3929/ethz-b-000593495
dc.description.abstract
Speech Neuroprostheses have the potential to enable communication for people with dysarthria or anarthria. Recent advances have demonstrated high-quality text decoding and speech synthesis from electrocorticographic grids placed on the cortical surface. Here, we investigate a less invasive measurement modality in three participants, namely stereotactic EEG (sEEG) that provides sparse sampling from multiple brain regions, including subcortical regions. To evaluate whether sEEG can also be used to synthesize high-quality audio from neural recordings, we employ a recurrent encoder-decoder model based on modern deep learning methods. We find that speech can indeed be reconstructed with correlations up to 0.8 from these minimally invasive recordings, despite limited amounts of training data.
en_US
dc.format
application/pdf
en_US
dc.language.iso
en
en_US
dc.publisher
The Neurons, Behavior, Data Analysis and Theory Collective
en_US
dc.rights.uri
http://creativecommons.org/licenses/by/4.0/
dc.subject
Speech neuroprosthesis
en_US
dc.subject
Encoder-decoder
en_US
dc.subject
iEEG
en_US
dc.subject
sEEG
en_US
dc.subject
BCI
en_US
dc.subject
Attention mechanism
en_US
dc.subject
Recurrent neural network
en_US
dc.title
Synthesizing Speech from Intracranial Depth Electrodes using an Encoder-Decoder Framework
en_US
dc.type
Journal Article
dc.rights.license
Creative Commons Attribution 4.0 International
ethz.journal.title
Neurons, Behavior, Data Analysis, and Theory
ethz.journal.volume
6
en_US
ethz.journal.issue
1
en_US
ethz.pages.start
57524
en_US
ethz.size
15 p.
en_US
ethz.version.deposit
publishedVersion
en_US
ethz.publication.place
Philadelphia, PA
en_US
ethz.publication.status
published
en_US
ethz.leitzahl
ETH Zürich::00002 - ETH Zürich::00012 - Lehre und Forschung::00007 - Departemente::02150 - Dep. Informatik / Dep. of Computer Science::02661 - Institut für Maschinelles Lernen / Institute for Machine Learning::09462 - Hofmann, Thomas / Hofmann, Thomas
en_US
ethz.leitzahl.certified
ETH Zürich::00002 - ETH Zürich::00012 - Lehre und Forschung::00007 - Departemente::02150 - Dep. Informatik / Dep. of Computer Science::02661 - Institut für Maschinelles Lernen / Institute for Machine Learning::09462 - Hofmann, Thomas / Hofmann, Thomas
en_US
ethz.relation.isSupplementedBy
https://github.com/jonaskohler/stereoEEG2speech
ethz.relation.isSupplementedBy
https://osf.io/7wf6n/
ethz.date.deposited
2023-01-19T08:19:42Z
ethz.source
FORM
ethz.eth
yes
en_US
ethz.availability
Open access
en_US
ethz.rosetta.installDate
2023-03-14T07:02:13Z
ethz.rosetta.lastUpdated
2024-02-03T03:23:41Z
ethz.rosetta.versionExported
true
ethz.COinS
ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.atitle=Synthesizing%20Speech%20from%20Intracranial%20Depth%20Electrodes%20using%20an%20Encoder-Decoder%20Framework&rft.jtitle=Neurons,%20Behavior,%20Data%20Analysis,%20and%20Theory&rft.date=2022-12-09&rft.volume=6&rft.issue=1&rft.spage=57524&rft.issn=2690-2664&rft.au=Kohler,%20Jonas&Ottenhoff,%20Marten&Goulis,%20Sophocles&Angrick,%20Miguel&Colon,%20Albert&rft.genre=article&rft_id=info:doi/10.51628/001c.57524&
 Search print copy at ETH Library

Files in this item

Thumbnail

Publication type

Show simple item record