Abstract
Brain-machine interfaces that directly translate attempted speech from the speech motor areas could change the lives of people with complete paralysis. However, it remains uncertain exactly how speech production is encoded in cortex. Improving this understanding could greatly improve brain-machine interface design. Specifically, it is not clear to what extent the different levels of speech production (phonemes, or speech sounds, and articulatory gestures, which describe the movements of the articulator muscles) are represented in the motor cortex. Using electrocorticographic (ECoG) electrodes on the cortical surface, we recorded neural activity from speech motor and premotor areas during speech production. We decoded both gestures and phonemes using the neural signals. Overall classification accuracy was higher for gestures than phonemes. In particular, gestures were better represented in the primary sensorimotor cortices, while phonemes were better represented in more anterior areas.
| Original language | English (US) |
|---|---|
| Title of host publication | 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2015 |
| Publisher | Institute of Electrical and Electronics Engineers Inc. |
| Pages | 5339-5342 |
| Number of pages | 4 |
| ISBN (Electronic) | 9781424492718 |
| DOIs | |
| State | Published - Nov 4 2015 |
| Event | 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2015 - Milan, Italy Duration: Aug 25 2015 → Aug 29 2015 |
Publication series
| Name | Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS |
|---|---|
| Volume | 2015-November |
| ISSN (Print) | 1557-170X |
Other
| Other | 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2015 |
|---|---|
| Country | Italy |
| City | Milan |
| Period | 8/25/15 → 8/29/15 |
Fingerprint
ASJC Scopus subject areas
- Signal Processing
- Biomedical Engineering
- Computer Vision and Pattern Recognition
- Health Informatics
Cite this
}
Decoding of articulatory gestures during word production using speech motor and premotor cortical activity. / Mugler, Emily M.; Goldrick, Matthew; Rosenow, Joshua M.; Tate, Matthew C.; Slutzky, Marc W.
2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2015. Institute of Electrical and Electronics Engineers Inc., 2015. p. 5339-5342 7319597 (Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS; Vol. 2015-November).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
TY - GEN
T1 - Decoding of articulatory gestures during word production using speech motor and premotor cortical activity
AU - Mugler, Emily M.
AU - Goldrick, Matthew
AU - Rosenow, Joshua M.
AU - Tate, Matthew C.
AU - Slutzky, Marc W.
PY - 2015/11/4
Y1 - 2015/11/4
N2 - Brain-machine interfaces that directly translate attempted speech from the speech motor areas could change the lives of people with complete paralysis. However, it remains uncertain exactly how speech production is encoded in cortex. Improving this understanding could greatly improve brain-machine interface design. Specifically, it is not clear to what extent the different levels of speech production (phonemes, or speech sounds, and articulatory gestures, which describe the movements of the articulator muscles) are represented in the motor cortex. Using electrocorticographic (ECoG) electrodes on the cortical surface, we recorded neural activity from speech motor and premotor areas during speech production. We decoded both gestures and phonemes using the neural signals. Overall classification accuracy was higher for gestures than phonemes. In particular, gestures were better represented in the primary sensorimotor cortices, while phonemes were better represented in more anterior areas.
AB - Brain-machine interfaces that directly translate attempted speech from the speech motor areas could change the lives of people with complete paralysis. However, it remains uncertain exactly how speech production is encoded in cortex. Improving this understanding could greatly improve brain-machine interface design. Specifically, it is not clear to what extent the different levels of speech production (phonemes, or speech sounds, and articulatory gestures, which describe the movements of the articulator muscles) are represented in the motor cortex. Using electrocorticographic (ECoG) electrodes on the cortical surface, we recorded neural activity from speech motor and premotor areas during speech production. We decoded both gestures and phonemes using the neural signals. Overall classification accuracy was higher for gestures than phonemes. In particular, gestures were better represented in the primary sensorimotor cortices, while phonemes were better represented in more anterior areas.
UR - http://www.scopus.com/inward/record.url?scp=84953280574&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84953280574&partnerID=8YFLogxK
U2 - 10.1109/EMBC.2015.7319597
DO - 10.1109/EMBC.2015.7319597
M3 - Conference contribution
C2 - 26737497
AN - SCOPUS:84953280574
T3 - Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS
SP - 5339
EP - 5342
BT - 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2015
PB - Institute of Electrical and Electronics Engineers Inc.
ER -