Towards a Speech BCI Using ECoG

Leuthardt, Eric C.; Cunningham, John P.; Barbour, Dennis L.

doi:10.1007/978-3-642-36083-1_10

Cited by 5 publications

(2 citation statements)

References 85 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Brain-computer interfaces (BCI) can be used to restore communication in several different ways (see [1,2] for reviews). However, communicative BCIs using primarily evoked potentials have not approached the rate or success of natural human communication [3]. One approach that could provide higher throughput is to classify and decode neural signals related to speech production [4], but research in this field has failed to approach the efficiency of speech.…”

Section: Introductionmentioning

confidence: 99%

Direct classification of all American English phonemes using signals from functional speech motor cortex

et al. 2014

View full text Add to dashboard Cite

Although brain-computer interfaces (BCIs) can be used in several different ways to restore communication, communicative BCI has not approached the rate or success of natural human speech. Electrocorticography (ECoG) has precise spatiotemporal resolution that enables recording of brain activity that is distributed over a wide area of cortex, such as during speech production. In this study, we investigated words that span the entire set of phonemes in the General American accent using ECoG with 4 subjects. We classified phonemes with up to 36% accuracy when classifying all phonemes and up to 63% accuracy for a single phoneme. Further, misclassified phonemes follow articulation organization described in phonology literature, aiding classification of whole words. Precise temporal alignment to phoneme onset was crucial for classification success. We identified specific spatiotemporal features that aid classification, which could guide future applications. Word identification was equivalent to information transfer rates as high as 3.0 bits/s (33.6 words/min), supporting pursuit of speech articulation for BCI control.

show abstract

Section: Introductionmentioning

confidence: 99%

Direct classification of all American English phonemes using signals from functional speech motor cortex

et al. 2014

View full text Add to dashboard Cite

show abstract

“…This is time consuming with an average synthesis rate of 1 Word/Minute [10] and hence not suitable for spontaneous conversations in daily life. Recently, ECoG, which measures electric potentials directly from the brain surface [11], has also been used for decoding continuous spoken speech from the cortical surface [12]. However, it is invasive in nature and hence can not be used for data collection from healthy subjects.…”

Section: Introductionmentioning

confidence: 99%

Determining the Optimal Number of MEG Trials: A Machine Learning and Speech Decoding Perspective

Dash

Ferrari

Malik

et al. 2018

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Advancing the knowledge about neural speech mechanisms is critical for developing next-generation, faster brain computer interface to assist in speech communication for the patients with severe neurological conditions (e.g., locked-in syndrome). Among current neuroimaging techniques, Magnetoencephalography (MEG) provides direct representation for the large-scale neural dynamics of underlying cognitive processes based on its optimal spatiotemporal resolution. However, the MEG measured neural signals are smaller in magnitude compared to the background noise and hence, MEG usually suffers from a low signal-to-noise ratio (SNR) at the single-trial level. To overcome this limitation, it is common to record many trials of the same event-task and use the time-locked average signal for analysis, which can be very time consuming. In this study, we investigated the effect of the number of MEG recording trials required for speech decoding using a machine learning algorithm. We used a wavelet filter for generating the denoised neural features to train an Artificial Neural Network (ANN) for speech decoding. We found that wavelet based denoising increased the SNR of the neural signal prior to analysis and facilitated accurate speech decoding performance using as few as 40 single-trials. This study may open up the possibility of limiting MEG trials for other task evoked studies as well.

show abstract

BrainTalk—An EEG Motor Imagery BCI for Giving Non-speaking People a Voice: A Position Paper

Talukdar

Shougrakpam

2021

Proceedings of the International Conference on Computing and Communication Systems

View full text Add to dashboard Cite

Towards a Speech BCI Using ECoG

Cited by 5 publications

References 85 publications

Direct classification of all American English phonemes using signals from functional speech motor cortex

Direct classification of all American English phonemes using signals from functional speech motor cortex

Determining the Optimal Number of MEG Trials: A Machine Learning and Speech Decoding Perspective

BrainTalk—An EEG Motor Imagery BCI for Giving Non-speaking People a Voice: A Position Paper

Contact Info

Product

Resources

About