Decoding Neural Activity of Imagined Speech

Post by Elisa Guma

The takeaway

The accurate detection of low-frequency neural activity, unique to imagined speech, may aid in the creation of brain-computer interfaces used to help individuals with speech production deficits communicate.

What's the science?

Using brain-computer interface technology to decode neural features of overt or imagined speech may enable communication in real-time for individuals suffering from serious or complete speech production. While progress has been made in decoding overt speech, decoding imagined speech has been more challenging due to weaker and more variable neural signals. This week in Nature Communications, Proix and colleagues investigate the neural activity associated with overt and imagined speech production.

How did they do it?

Electrocorticographic (ECoG) recordings were acquired from individuals with refractory epilepsy who were implanted with a subdural electrode array as part of the standard pre-surgical evaluation process. While electrocorticographic recordings were being acquired, participants were asked to listen to or read multiple words or syllables (ex: ‘ba’, ‘da’, ‘ga’), after which they were instructed to either imagine hearing the word or syllable, imagine saying the word or syllable, or repeating the word or syllable out loud.

First, electrodes were localized to a patient’s pre-implant structural MRI such that the location of each electrode could be associated with a specific brain region. The signal was then transformed such that a power could be assigned to each recording in one of 4 known frequencies ranging from low to high: theta, low-beta, low-gamma bands, and broadband high-frequency activity. For each power spectrum, the authors investigated the association with either listened, overt, or imagined speech, and specific brain regions. Finally, the authors aimed to decode overt and imagined speech by training a specific classifier for each binary classification between distinct words or syllables.

What did they find?

The authors found that overt and imagined speech engaged a large part of the left hemispheric language network including the sensory and motor regions, with more prominent involvement of the superior temporal gyrus for overt speech, potentially attributable to the auditory feedback due to hearing oneself speak. The power spectrum differences between overt and imagined speech were sufficiently reliable to accurately classify which task the participants were engaged in. Broadband high-frequency activity was most associated with overt speech decoding. Neural activity at both low- and high- frequency power could be used to decode imagined speech with equivalent or even higher performance than overt speech. These data suggest that low-frequency power may be critical for decoding imagined speech, that the process of decoding overt and imagined speech may be quite different, and that brain-computer trained on one type of speech production may not be applicable to the other.  

What's the impact?

This study examined neural activity associated with the production of overt or imagined speech and found crucial differences in their oscillatory patterns and neuroanatomical origin. Low-frequency power and cross-frequency dynamics may hold key information for decoding imagined speech. A better understanding of the underlying neural activity of imagined speech may inform more accurate brain-machine interfaces, which could greatly benefit those suffering from severe speech production deficits.  

The Benefits of Mindfulness for Athletes

in ,

Post by Shireen Parimoo

The mindfulness era

Sports performance requires as much mental toughness and perseverance as it does physical fitness and conditioning. In addition to physical conditioning, (elite) athletes must develop considerable mental fortitude and discipline, contributing to their performance in competitions. Some important mental skills that athletes develop include motivation, arousal regulation, recovery, the ability to cope with training demands and competition pressure, and the ability to focus on both the present moment and on future goals.

We know that physical fitness can be improved by following exercise programs and regimens, but how do athletes train their minds? Athletes often perform psychological skills training to supplement their physical training, which can include working on techniques like self-talk, goal setting, and imagery. For example, self-talk can reduce performance-related anxiety and increase self-confidence and motivation, both of which may then benefit performance. More recently, mindfulness meditation has become a popular practice among athletes and non-athletes alike. Mindfulness refers to a state of awareness of our thoughts and feelings (i.e., inner experiences) in the present moment. It is characterized by attention to the present moment, lack of reactivity and judgment, and increased acceptance of our inner experiences. Practicing mindfulness meditation has numerous psychological and cognitive benefits, such as reductions in depressive symptoms, anxiety, and stress, as well as improvements in attentional focus and emotion regulation.

There are two main approaches to researching mindfulness:

1.     Relating dispositional or trait mindfulness (e.g., as an individual, how well are they able to stay focused on the present moment?) to other psychological and performance-related outcomes.

2.     Mindfulness-based interventions. In this approach, psychological and performance outcomes are measured before and after an intervention during which participants learn about mindfulness concepts and mindfulness techniques like emotion acceptance.  

Do athletes benefit from mindfulness?

Across a variety of sports, research shows that individuals high in trait mindfulness are more likely to experience the flow state. Flow is a state of intense focus characterized by complete immersion in the task at hand that is accompanied by high levels of clarity, control over the task, ease and enjoyment of the task, and a sense of time flying by. More commonly, flow is what we call “being in the zone” during a task. Athletes who score high on trait mindfulness also tend to have better concentration, higher goal clarity, and an increased sense of control than those lower on trait mindfulness. Experiencing the flow state, in turn, is often associated with better performance.

Trait mindfulness has also been associated with a better ability to cope with sports-related challenges such as training demands, self-confidence and motivation, and performance-related worries. One of the reasons that trait mindfulness results in better coping skills is that mindfulness helps in the regulation of emotion and allows people to avoid ruminating on negative thoughts. Thus, higher mindfulness likely prevents athletes from being distracted by negative thoughts and provides more room for them to focus on their goal, which might then prevent them from faltering under pressure.

In line with this idea, trait mindfulness is related to higher self-reported sports performance and lower competition-related anxiety. Interestingly,  researchers have found that competition-related anxiety negatively impacts performance, but only in those who were low in mindfulness. As performance- and sports-related worries are likely pervasive among athletes, higher mindfulness may prevent those worries from interfering with performance.

Is mindfulness training effective?

Mindfulness-based interventions show promise in facilitating performance outcomes, likely by influencing both physiological and psychological variables. On a holistic level, mindfulness training has been shown to improve the well-being of athletes, along with reductions in burnout and improvements in sleep quality. Mindfulness also has a positive effect on physiological measures like salivary cortisol levels (a marker of stress) and resting heart rate (a measure of fitness).

On a psychological level, mindfulness training can lead to more frequent flow states, better attentional control, and fewer performance-related worries. In fact, one study showed that the impact of an 8-week-long mindfulness program reduced cortisol levels of elite athletes by also reducing their competition-related anxiety. Athletes who practiced mindfulness for four weeks also became better equipped at handling failures. Lastly, the impact of mindfulness on actual sports performance is currently unclear. According to a recent meta-analysis, mindfulness interventions improve performance in precision sports like dart throwing and shooting, but not in sports like running and cycling. Other work indicates that both subjective and objective measures of performance show improvements following mindfulness training, such as longer time to exhaustion on an endurance test. By and large, however, the impact of mindfulness training on objective performance outcomes is mixed and more research is needed to identify how different types and durations of mindfulness programs might benefit performance in various sports.

References +

Aherne et al. The effect of mindfulness training on athletes’ flow: An initial investigation. The Sport Psychologist (2011).

Birrer et al. Mindfulness to enhance athletic performance: Theoretical considerations and possible impact mechanisms. Mindfulness (2012).

Birrer et al. Helping athletes flourish using mindfulness and acceptance approaches – an introduction and mini review. Sport & Exercise Medicine (2021).

Buhlmayer et al. Effects of mindfulness practice on performance-relevant parameters and performance outcomes in sports: A meta-analytical review. Sports Medicine (2017).

Cathcart et al. Mindfulness and flow in elite athletes. Journal of Clinical Sport Psychology (2014).

De Petrillo et al. Mindfulness for long-distance runners: An open trial using mindful sport performance enhancement. Journal of Clinical Sport Psychology (2009).

Hamilton et al. Effects of a mindfulness intervention on sports-anxiety, pessimism, and flow in competitive cyclists. Applied Psychology: Health and Well-Being (2016).

Josefsson et al. Mindfulness mechanisms in sports: Mediating effects of rumination and emotion regulation on sport-specific coping. Mindfulness (2017).

Kee & Wang. Relationships between mindfulness, flow dispositions, and mental skills adoption: A cluster analytic approach. Psychology of Sport and Exercise (2008).

Mehrsafar et al. The effects of mindfulness training on competition-induced anxiety and salivary stress markers in elite Wushu athletes: A pilot study. Physiology & Behavior (2019).

Nien et al. Mindfulness training enhances endurance performance and executive functions in athletes: An event-related potential study. Neural Plasticity (2020).

Detecting Fake Videos With AI and Human Judgement

Post by Lina Teichmann

The takeaway

Videos manipulated with neural networks can make it very difficult to distinguish fiction from reality. These ‘deepfakes’ can be used to spread false information, thereby posing a serious challenge to society. Combining artificial intelligence (AI) models and human judgment results in superior performance when detecting deepfakes in comparison to models or human judgment alone.

What's the science?

Machine-manipulated videos called ‘deepfakes’ can have harmful consequences when undetected. Leading AI models can be used to detect fake videos, however, in a large competition on deepfake detection, the leading model achieved an accuracy of only 65%, with chance level being at 50%. This week in PNAS, Groh and colleagues examined how humans, AI models, and the combination of the two perform in deepfake detection. They investigated the error patterns and specific strengths and weaknesses of AI models and large groups of humans when distinguishing between real and fake videos.

How did they do it?

The authors ran two separate experiments. In Experiment 1, a deepfake video was shown alongside the authentic video and participants had to indicate which one was fake. In Experiment 2, participants viewed one video and had to indicate how confident they were that the video was real or fake. In this experiment, participants could also see the AI model’s prediction and update their confidence rating accordingly. Both experiments included random manipulations to evoke a specific emotion and to obstruct facial features in the video. These manipulations were used to test whether incidental emotion has an effect on deepfake detection and whether specialized face processing abilities in humans influence their performance.

What did they find?

The leading AI model could correctly identify 80% of a test set of videos as either real or fake. This was similar to the participants’ response averaged per video, however, there was some variance between individuals. While the overall accuracy between the human crowd and the model was similar, the types of mistakes they made differed. When participants had access to the model predictions, they outperformed both the model and the participants who did not access model predictions. However, inaccurate model predictions had a negative impact on humans’ ability to detect deepfakes. There was some evidence that eliciting anger in participants lowered the ability to detect deepfake videos, highlighting why deepfake videos in social media may be even more problematic. The results also show that face processing is critical for people to distinguish fake from real videos.

What's the impact?

The emergence of neural networks in computer vision has led to many new opportunities, such as improving medical diagnoses and enhancing accuracy in forensic examinations. On the flipside, neural networks are able to generate pictures and videos that look authentic but are fake. Classifying machine-manipulated videos as fake is critical in fighting the spread of misinformation. Overall, this study highlights that groups of humans are just as capable in detecting deepfakes as leading AI models. Groh and colleagues illuminate how we can best combine the strengths of AI models and humans to flag deepfakes and ultimately overcome a massive challenge for society at large.