Speech Activity Detection from Stereotactic EEG

Soroush, Pedram Zanganeh; Angrick, Miguel; Shih, Jerry J.; Schultz, Tanja; Krusienski, Dean J.

doi:10.1109/smc52423.2021.9659058

Cited by 8 publications

(19 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…6b. This is consistent with previous studies showing channels from both grey and white matter contributing to decoding models [8], [2], [50], [55], further demonstrating the relevance of deeper structures and white matter for speech decoding.…”

Section: Discussionsupporting

confidence: 93%

“…While these weights do not directly represent the spectro-temporal brain patterns associated with the decoding models, they do convey the relative contributions of spectro-temporal features to the models. As expected from previous studies, features temporally closer to the frame being decoded have a greater contribution to the models [2]. A strikingly similar pattern is observed between the weights of the overt-mouthed-imagined group across the three modes.…”

Section: Resultssupporting

confidence: 85%

“…The narrow-band power of each sEEG channel was computed in four conventional frequency bands: theta (4-8 Hz), alpha (8-12 Hz), beta (12-30 Hz), and broadband gamma (70-170 Hz). These frequency bands have been shown to be informative for speech activity detection [2], [27], [40]. The subsequent pre-processing was performed for each frequency band.…”

Section: Methodsmentioning

confidence: 99%

“…Additionally, the feature weights of the 10 decoding models (one per fold) were averaged to compare the relative contribution of each feature to the models. These weights can provide a convenient interpretation of individual feature contributions based on the non-zero classifier weights and represent the spectral and temporal contributions to speech activity detection [2].…”

Section: H Model Training and Evaluationmentioning

confidence: 99%

“…Using causal brain activity features as inputs, speech activity detection models simply classify the respective activity as occurring during intervals of speech or non-speech intent, whether overt or imagined. Recent studies using sEEG and speech activity detection modeling have successfully elucidated relevant frequency bands' relative contributions of grey and white matter over speech [2] and classified phonetic features from activity located in the superior temporal gyrus [30].…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

The Nested Hierarchy of Overt, Mouthed, and Imagined Speech Activity Evident in Intracranial Recordings

Soroush

Riès

Shih³

et al. 2022

Preprint

View full text Add to dashboard Cite

Recent studies have demonstrated that it is possible to decode and synthesize various aspects of acoustic speech directly from intracranial measurements of electrophysiological brain activity. In order to continue progressing toward the development of a practical speech neuroprosthesis for the individuals with speech impairments, better understanding and modeling of imagined speech processes are required. The present study uses intracranial brain recordings from participants that performed a speaking task with trials consisting of overt, mouthed, and imagined speech, representing various degrees of decreasing behavioral output. Speech activity detection models are constructed using spatial, spectral, and temporal brain activity features, and the features and model performances are characterized and compared across the three degrees of behavioral output. The results indicate there is a hierarchy in which the relevant channels for the lower behavioral output modes form nested subsets of the relevant channels from the higher behavioral output modes. This provides important insights for the elusive goal of developing more effective imagined speech decoding models with respect to the better-established overt speech decoding counterparts.

show abstract

Section: Discussionsupporting

confidence: 93%

Section: Resultssupporting

confidence: 85%

Section: Methodsmentioning

confidence: 99%

Section: H Model Training and Evaluationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

The Nested Hierarchy of Overt, Mouthed, and Imagined Speech Activity Evident in Intracranial Recordings

Soroush

Riès

Shih³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

Online speech synthesis using a chronically implanted brain–computer interface in an individual with ALS

Angrick,

Luo,

Rabbani

et al. 2024

Sci Rep

View full text Add to dashboard Cite

Brain–computer interfaces (BCIs) that reconstruct and synthesize speech using brain activity recorded with intracranial electrodes may pave the way toward novel communication interfaces for people who have lost their ability to speak, or who are at high risk of losing this ability, due to neurological disorders. Here, we report online synthesis of intelligible words using a chronically implanted brain-computer interface (BCI) in a man with impaired articulation due to ALS, participating in a clinical trial (ClinicalTrials.gov, NCT03567213) exploring different strategies for BCI communication. The 3-stage approach reported here relies on recurrent neural networks to identify, decode and synthesize speech from electrocorticographic (ECoG) signals acquired across motor, premotor and somatosensory cortices. We demonstrate a reliable BCI that synthesizes commands freely chosen and spoken by the participant from a vocabulary of 6 keywords previously used for decoding commands to control a communication board. Evaluation of the intelligibility of the synthesized speech indicates that 80% of the words can be correctly recognized by human listeners. Our results show that a speech-impaired individual with ALS can use a chronically implanted BCI to reliably produce synthesized words while preserving the participant’s voice profile, and provide further evidence for the stability of ECoG for speech-based BCIs.

show abstract

Speech decoding from stereo-electroencephalography (sEEG) signals using advanced deep learning methods

Wu,

Wellington,

et al. 2024

J. Neural Eng.

View full text Add to dashboard Cite

Objective. Brain–computer interfaces (BCIs) are technologies that bypass damaged or disrupted neural pathways and directly decode brain signals to perform intended actions. BCIs for speech have the potential to restore communication by decoding the intended speech directly. Many studies have demonstrated promising results using invasive micro-electrode arrays and electrocorticography. However, the use of stereo-electroencephalography (sEEG) for speech decoding has not been fully recognized. Approach. In this research, recently released sEEG data were used to decode Dutch words spoken by epileptic participants. We decoded speech waveforms from sEEG data using advanced deep-learning methods. Three methods were implemented: a linear regression method, an recurrent neural network (RNN)-based sequence-to-sequence model (RNN), and a transformer model. Main results. Our RNN and transformer models outperformed the linear regression significantly, while no significant difference was found between the two deep-learning methods. Further investigation on individual electrodes showed that the same decoding result can be obtained using only a few of the electrodes. Significance. This study demonstrated that decoding speech from sEEG signals is possible, and the location of the electrodes is critical to the decoding performance.

show abstract

Speech Activity Detection from Stereotactic EEG

Cited by 8 publications

References 22 publications

The Nested Hierarchy of Overt, Mouthed, and Imagined Speech Activity Evident in Intracranial Recordings

The Nested Hierarchy of Overt, Mouthed, and Imagined Speech Activity Evident in Intracranial Recordings

Online speech synthesis using a chronically implanted brain–computer interface in an individual with ALS

Speech decoding from stereo-electroencephalography (sEEG) signals using advanced deep learning methods

Contact Info

Product

Resources

About