1. |
- Alickovic, Emina, et al.
(author)
-
Predicting EEG Responses to Attended Speech via Deep Neural Networks for Speech
- 2023
-
In: 2023 45TH ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE & BIOLOGY SOCIETY, EMBC. - : IEEE. - 9798350324471 - 9798350324488
-
Conference paper (peer-reviewed)abstract
- Attending to the speech stream of interest in multi-talker environments can be a challenging task, particularly for listeners with hearing impairment. Research suggests that neural responses assessed with electroencephalography (EEG) are modulated by listener's auditory attention, revealing selective neural tracking (NT) of the attended speech. NT methods mostly rely on hand-engineered acoustic and linguistic speech features to predict the neural response. Only recently, deep neural network (DNN) models without specific linguistic information have been used to extract speech features for NT, demonstrating that speech features in hierarchical DNN layers can predict neural responses throughout the auditory pathway. In this study, we go one step further to investigate the suitability of similar DNN models for speech to predict neural responses to competing speech observed in EEG. We recorded EEG data using a 64-channel acquisition system from 17 listeners with normal hearing instructed to attend to one of two competing talkers. Our data revealed that EEG responses are significantly better predicted by DNN-extracted speech features than by hand-engineered acoustic features. Furthermore, analysis of hierarchical DNN layers showed that early layers yielded the highest predictions. Moreover, we found a significant increase in auditory attention classification accuracies with the use of DNN-extracted speech features over the use of hand-engineered acoustic features. These findings open a new avenue for development of new NT measures to evaluate and further advance hearing technology.
|
|
2. |
- Gizzi, Leonardo, et al.
(author)
-
Experimental muscle pain impairs the synergistic modular control of neck muscles
- 2015
-
In: PLoS ONE. - : Public Library of Science (PLoS). - 1932-6203 .- 1932-6203. ; 10:9, s. 1-19
-
Journal article (peer-reviewed)abstract
- A motor task can be performed via different patterns of muscle activation that show regularities that can be factorized in combinations of a reduced number of muscle groupings (also referred to as motor modules, or muscle synergies). In this study we evaluate whether an acute noxious stimulus induces a change in the way motor modules are combined to generate movement by neck muscles. The neck region was selected as it is a region with potentially high muscular redundancy. We used the motor modules framework to assess the redistribution of muscular activity of 12 muscles (6 per side) in the neck region of 8 healthy individuals engaged in a head and neck aiming task, in non-painful conditions (baseline, isotonic saline injection, post pain) and after the injection of hypertonic saline into the right splenius capitis muscle. The kinematics of the task was similar in the painful and control conditions. A general decrease of activity was noted for the injected muscle during the painful condition together with an increase or decrease of the activity of the other muscles. Subjects did not adopt shared control strategies (motor modules inter subject similarity at baseline 0.73±0.14); the motor modules recorded during the painful condition could not be used to reconstruct the activation patterns of the control conditions, and the painful stimulus triggered a subject-specific redistribution of muscular activation (i.e., in some subjects the activity of a given muscle increased, whereas in other subjects it decreased with pain). Alterations of afferent input (i.e., painful stimulus) influenced motor control at a multi muscular level, but not kinematic output. These findings provide new insights into the motor adaptation to pain.
|
|
3. |
- Halvorsen, Marie, et al.
(author)
-
SHORT- AND LONG-TERM EFFECTS OF EXERCISE ON NECK MUSCLE FUNCTION IN CERVICAL RADICULOPATHY: A RANDOMIZED CLINICAL TRIAL
- 2016
-
In: Journal of Rehabilitation Medicine. - : FOUNDATION REHABILITATION INFORMATION. - 1650-1977 .- 1651-2081. ; 48:8, s. 696-704
-
Journal article (peer-reviewed)abstract
- Objective: To compare short-and long-term changes in neck muscle endurance, electromyography measures of neck muscle activation and fatigue and ratings of fatigue and pain after neck-specific training or physical activity in people with cervical radiculopathy. Design: Randomized clinical trial. Subjects/patients: Seventy-five patients with cervical radiculopathy. Methods: Patients underwent neck-specific training in combination with a cognitive behavioural approach or prescribed physical activity over a period of 14 weeks. Immediately after the intervention and 12 months later, surface electromyography was recorded from neck flexor and extensor muscles during neck endurance tests. Time to task failure, amplitude and median frequency of the electromyography signal, and subjective fatigue and pain ratings were analysed in 50 patients who completed at least one follow-up. Results: A significant increase in neck flexor endurance time was observed for both groups at 14 weeks compared with baseline and this was maintained at the 12-month follow-up (pamp;lt;0.005). No change was identified for the slope of the median frequency. For the neck-specific training group, splenius capitis was less active during neck flexion at both follow-ups (pamp;lt;0.01), indicating reduced muscle co-activation. Conclusion: Both specific and general exercise increased neck flexor endurance, but neck-specific training only reduced co-activation of antagonist muscles during sustained neck flexion.
|
|