Vowel Imagery Decoding toward Silent Speech BCI Using Extreme Learning Machine with Electroencephalogram

Min, Beomjun; Kim, Jong-In; Park, Hyeong-jun; Lee, Boreom

doi:10.1155/2016/2618265

Cited by 70 publications

(44 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the presented work, we have used a SVM classification on CSP extracted features from EEG data corresponding to VIm. A cross-validation accuracy of above 95% is shown among individual participants and close to 89% across average of the 17 participants compared to other studies showing accuracy around 75% classifying VInt [19]. These accuracy scores are quite impressive considering no pre-processing was performed to prime the data; no artifact removal, frequency filtration or noise reduction.…”

Section: Discussionmentioning

confidence: 52%

See 1 more Smart Citation

Vocal Imagery vs Intention: Viability of Vocal-Based EEG-BCI Paradigms

Kristensen

Subhi

Puthusserypady

2020

IEEE Trans. Neural Syst. Rehabil. Eng.

View full text Add to dashboard Cite

 Users may download and print one copy of any publication from the public portal for the purpose of private study or research.  You may not further distribute the material or use it for any profit-making activity or commercial gain  You may freely distribute the URL identifying the publication in the public portal If you believe that this document breaches copyright please contact us providing details, and we will remove access to the work immediately and investigate your claim.

show abstract

Section: Discussionmentioning

confidence: 52%

“…In 2016, Min et. al., have proposed a vowel (/a/, /e/, /i/, /o/, and /u/) imagery decoding towards developing a silent speech BCI using extreme learning machine with a single-trial EEG [19]. In the same year, Yoshimura et.…”

Section: Introductionmentioning

confidence: 99%

Vocal Imagery vs Intention: Viability of Vocal-Based EEG-BCI Paradigms

Kristensen

Subhi

Puthusserypady

2020

IEEE Trans. Neural Syst. Rehabil. Eng.

View full text Add to dashboard Cite

show abstract

“…Most of the researchers, including Zhao and Rudzicz ( 2015 ), Min et al ( 2016 ), Nguyen et al ( 2017 ), Koizumi et al ( 2018 ), and Sereshkeh et al ( 2017a ) have used a 64-electrode EEG system with a sampling rate of 1 KHz for acquiring the EEG data corresponding to imagined speech. In the case of the work reported by Deng et al ( 2010 ) and Brigham and Kumar ( 2010 ), 128-electrode EEG data has been recorded at a sampling rate of 1 KHz.…”

Section: Data Acquisitionmentioning

confidence: 99%

“…Three methods have been primarily followed by researchers to cue the participant as to what the prompt is and when to start imagining speaking the prompt. These are (1) auditory (Brigham and Kumar, 2010 ; Deng et al, 2010 ; Min et al, 2016 ; Koizumi et al, 2018 ); (2) visual (Wang et al, 2014 ; Sereshkeh et al, 2017a ; Jahangiri et al, 2018 ; Koizumi et al, 2018 ); and (3) a combination of auditory and visual cues (Zhao and Rudzicz, 2015 ; Coretto et al, 2017 ; Nguyen et al, 2017 ; Watanabe et al, 2020 ). Although somatosensory cues have been used for motor imagery (Panachakel et al, 2020b ), no such work has been reported for speech imagery.…”

Section: Data Acquisitionmentioning

confidence: 99%

Decoding Covert Speech From EEG-A Comprehensive Review

Panachakel

Ramakrishnan

2021

Front. Neurosci.

View full text Add to dashboard Cite

Over the past decade, many researchers have come up with different implementations of systems for decoding covert or imagined speech from EEG (electroencephalogram). They differ from each other in several aspects, from data acquisition to machine learning algorithms, due to which, a comparison between different implementations is often difficult. This review article puts together all the relevant works published in the last decade on decoding imagined speech from EEG into a single framework. Every important aspect of designing such a system, such as selection of words to be imagined, number of electrodes to be recorded, temporal and spatial filtering, feature extraction and classifier are reviewed. This helps a researcher to compare the relative merits and demerits of the different approaches and choose the one that is most optimal. Speech being the most natural form of communication which human beings acquire even without formal education, imagined speech is an ideal choice of prompt for evoking brain activity patterns for a BCI (brain-computer interface) system, although the research on developing real-time (online) speech imagery based BCI systems is still in its infancy. Covert speech based BCI can help people with disabilities to improve their quality of life. It can also be used for covert communication in environments that do not support vocal communication. This paper also discusses some future directions, which will aid the deployment of speech imagery based BCI for practical applications, rather than only for laboratory experiments.

show abstract

“…To leverage the temporal dynamics of the MEG signal, we extracted four feature sets at each time point across all the sensors to train the LSTM-RNN deep learning algorithm for continuous temporal prediction of 'Speech' vs. 'Non-Speech'. The first three features were the 'absolute magnitude', 'root-mean-square' (RMS), and 'standard deviation' which have been shown to be effective in previous studies [7,[26][27][28]. The 4th feature was the index of the most active sensor, i.e., the sensor with maximum magnitude value among all sensors at each time point.…”

Section: Feature Extractionmentioning

confidence: 99%

NeuroVAD: Real-Time Voice Activity Detection from Non-Invasive Neuromagnetic Signals

Dash

Ferrari

Dutta

et al. 2020

Sensors

View full text Add to dashboard Cite

Neural speech decoding-driven brain-computer interface (BCI) or speech-BCI is a novel paradigm for exploring communication restoration for locked-in (fully paralyzed but aware) patients. Speech-BCIs aim to map a direct transformation from neural signals to text or speech, which has the potential for a higher communication rate than the current BCIs. Although recent progress has demonstrated the potential of speech-BCIs from either invasive or non-invasive neural signals, the majority of the systems developed so far still assume knowing the onset and offset of the speech utterances within the continuous neural recordings. This lack of real-time voice/speech activity detection (VAD) is a current obstacle for future applications of neural speech decoding wherein BCI users can have a continuous conversation with other speakers. To address this issue, in this study, we attempted to automatically detect the voice/speech activity directly from the neural signals recorded using magnetoencephalography (MEG). First, we classified the whole segments of pre-speech, speech, and post-speech in the neural signals using a support vector machine (SVM). Second, for continuous prediction, we used a long short-term memory-recurrent neural network (LSTM-RNN) to efficiently decode the voice activity at each time point via its sequential pattern-learning mechanism. Experimental results demonstrated the possibility of real-time VAD directly from the non-invasive neural signals with about 88% accuracy.

show abstract

Vowel Imagery Decoding toward Silent Speech BCI Using Extreme Learning Machine with Electroencephalogram

Cited by 70 publications

References 47 publications

Vocal Imagery vs Intention: Viability of Vocal-Based EEG-BCI Paradigms

Vocal Imagery vs Intention: Viability of Vocal-Based EEG-BCI Paradigms

Decoding Covert Speech From EEG-A Comprehensive Review

NeuroVAD: Real-Time Voice Activity Detection from Non-Invasive Neuromagnetic Signals

Contact Info

Product

Resources

About