<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=iso-8859-1">
<style type="text/css" style="display:none;"> P {margin-top:0;margin-bottom:0;} </style>
</head>
<body dir="ltr">
<div style="font-family: Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);" class="elementToProof">
<br>
</div>
<div id="divRplyFwdMsg" dir="ltr">
<div> </div>
</div>
<div dir="ltr">
<table align="center" width="600" style="font-family: Arial, sans-serif; font-size: medium; color: rgb(0, 0, 0);">
<tbody>
<tr>
<td>
<div><img alt="Dissertation Defense Announcement at the Cullen College of Engineering" width="600" height="174" id="x_imageSelected0" src="https://www.egr.uh.edu/sites/www.egr.uh.edu/files/enews/2022/images/thesis1.png"></div>
<table align="center">
<tbody>
<tr>
<td align="center" style="padding:40px 20px 10px">
<div style="font-size: 24px; line-height: 28px; color: rgb(200, 16, 46);"><strong>CONTINUOUS AND DISCRETE DECODING OF OVERT SPEECH WITH ELECTROENCEPHALOGRAPHY<br>
</strong></div>
<div style="margin:30px 0px; line-height:20px">
<div style="font-size:18px; margin-bottom:5px"><strong>Alexander Robert Craik</strong></div>
<div style="font-size:14px">
<p style="margin-top: 0px; margin-bottom: 0px;font-family:Arial,Helvetica,sans-serif; line-height:22px; margin:0px 0px 5px">
August 1st, 2023; 1:00 PM - 3:00 PM (CST)<br>
Location: E413 Eng Bld 2<br>
Zoom:<span> </span><a href="https://urldefense.com/v3/__https://uh-edu-cougarnet.zoom.us/j/95524641587?pwd=bkhtRlNxL3E3SnZCTU1oSFNHcHJNQT09__;!!LkSTlj0I!A60F_KqVuVaaECnYYXcNoXd-Ii2Ad-UspztC-9huT8O70yI987ryPpC3Ta4P-J6RzX_y8O4kqRGpgrjGwfzkW0M$" data-auth="NotApplicable" class="" data-loopstyle="linkonly" style="color: rgb(200, 16, 46);">https://uh-edu-cougarnet.zoom.us/j/95524641587?pwd=bkhtRlNxL3E3SnZCTU1oSFNHcHJNQT09</a></p>
</div>
</div>
<div style="font-size:14px; line-height:20px">
<p style="margin-top: 0px; margin-bottom: 0px;font-family:Arial,Helvetica,sans-serif; line-height:22px; margin:0px 0px 5px">
<strong>Committee Chair:</strong><br>
Jose L. Contreras-Vidal, Ph.D.<br>
</p>
</div>
<div style="font-size:14px; line-height:20px">
<p style="margin-top: 0px; margin-bottom: 0px;font-family:Arial,Helvetica,sans-serif; line-height:22px; margin:0px 0px 20px">
<strong>Committee Members:</strong><br>
Heather Dial, Ph.D. | Saurabh Prasad, Ph.D. | Cameron Buckner, Ph.D. | Hien Nguyen, Ph.D.</p>
</div>
</td>
</tr>
<tr>
<td style="padding:0px 20px 20px">
<p style="font-family: Arial, Helvetica, sans-serif; font-size: 16px; line-height: 22px; margin: 15px 0px; color: rgb(200, 16, 46);">
<strong>Abstract</strong></p>
<p style="margin-top: 0px; margin-bottom: 0px;font-family:Arial,Helvetica,sans-serif; font-size:14px; line-height:22px; margin:15px 0px">
Neurological disorders affecting speech production impair the quality of life for over 7 million individuals in the US. Traditional speech interfaces like eye-tracking devices and P300 spellers are slow and unnatural for these patients. An alternative solution,
speech Brain-Computer Interfaces (BCIs), directly decodes speech characteristics, offering a more natural communication mechanism. This research explores the feasibility of decoding speech features using non-invasive EEG. Nine neurologically intact participants
were equipped with a 63-channel EEG system with additional sensors to eliminate eye artifacts. Participants read aloud sentences displayed on a screen selected for phonetic similarity to the English language. Pre-processing techniques, including filtering,
line noise removal, and eye artifact removal, were applied prior to assessment of methods for the removal of facial electromyography (EMG) contamination. Four Blind Source Separation cleaning methods, including Canonical Correlation Analysis, Independent Component
Analysis, and two-stage EMG removal methods employing Ensemble Empirical Mode Decomposition, were evaluated. Three implementations of these methods were selected for further decoding analysis based on signal characteristic metrics and their correlation with
decoding performance. Deep learning models, including Convolutional Neural Networks and Recurrent Neural Networks with/without attention modules, were optimized with a focus on minimizing trainable parameters and utilizing small input window sizes. These models
were employed for discrete and continuous speech decoding tasks, achieving above-chance participant-independent decoding performance for discrete classes and continuous characteristics of the produced audio signal. A frequency sub-band analysis highlighted
the significance of certain frequency bands (delta, theta, and gamma) for decoding performance, and a perturbation analysis identified crucial channels. Assessed channel selection methods did not significantly improve performance, but they still outperformed
chance levels, suggesting high-density EEG systems might not be warranted for speech BCIs. Transfer learning demonstrated the possibility of utilizing common speech neural correlates, reducing data collection requirements from individual participants. The
successful classification of continuously-produced phonemes and regression of acoustic characteristics signify progress in non-invasive speech BCI development. This research presents promising steps towards developing a universal non-invasive speech BCI control
signal, offering opportunities for commercial applications as a replacement for task-specific protocols. Improved speech BCIs hold the potential to improve the overall quality of life of individuals living with neurological speech disorders.</p>
</td>
</tr>
</tbody>
</table>
</td>
</tr>
<tr>
<td><img alt="Engineered For What's Next" width="600" height="82" src="https://www.egr.uh.edu/sites/www.egr.uh.edu/files/enews/2022/images/dissertation2.png"></td>
</tr>
</tbody>
</table>
<div class="x_elementToProof" style="font-family: Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
<br>
</div>
<div class="x_elementToProof">
<div style="font-family: Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
<br>
</div>
<div id="x_Signature">
<div style="font-family: Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0); background-color: rgb(255, 255, 255);">
<br>
</div>
<div id="x_divtagdefaultwrapper" dir="ltr" style="font-size: 12pt; font-family: Calibri, Helvetica, sans-serif; color: rgb(0, 0, 0);">
<div class="x_BodyFragment"><font size="2"></font></div>
</div>
</div>
</div>
</div>
</body>
</html>