Biology subjects

Bertrand, A.

Publications and source records attributed to Bertrand, A..

29 records · Page 2Linked to original sources

bioRxiv2020

Fast EEG-based decoding of the directional focus of auditory attention using common spatial patterns

ObjectiveNoise reduction algorithms in current hearing devices lack information about the sound source a user attends to when multiple sources are present. To resolve this issue, they can be complemented with auditory attention decoding (AAD) algorithms, which decode the attention using electroencephalography (EEG) sensors. State-of-the-art AAD algorithms employ a stimulus reconstruction approach, in which the envelope of the attended source is reconstructed from the EEG and correlated with the envelopes of the individual sources. This approach, however, performs poorly on short signal segments, while longer segments yield impractically long detection delays when the user switches attention. MethodsWe propose decoding the directional focus of attention using filterbank common spatial pattern filters (FB-CSP) as an alternative AAD paradigm, which does not require access to the clean source envelopes. ResultsThe proposed FB-CSP approach outperforms both the stimulus reconstruction approach on short signal segments, as well as a convolutional neural network approach on the same task. We achieve a high accuracy (80% for 1 s windows and 70% for quasi-instantaneous decisions), which is sufficient to reach minimal expected switch durations below 4 s. We also demonstrate that the decoder can adapt to unlabeled data from an unseen subject and works with only a subset of EEG channels located around the ear to emulate a wearable EEG setup. ConclusionThe proposed FB-CSP method provides fast and accurate decoding of the directional focus of auditory attention. SignificanceThe high accuracy on very short data segments is a major step forward towards practical neuro-steered hearing devices.

neuroscience↗

bioRxiv2020

EEG-informed speaker extraction from noisy recordings in neuro-steered hearing aids: linear versus deep learning methods

ObjectiveA hearing aids noise reduction algorithm cannot infer to which speaker the user intends to listen to. Auditory attention decoding (AAD) algorithms allow to infer this information from neural signals, which leads to the concept of neuro-steered hearing aids. We aim to evaluate and demonstrate the feasibility of AAD-supported speech enhancement in challenging noisy conditions based on electroencephalography (EEG) recordings. ApproachThe AAD performance with a linear versus a deep neural network (DNN) based speaker separation was evaluated for same-gender speaker mixtures using 3 different speaker positions and 3 different noise conditions. Main resultsAAD results based on the linear approach were found to be at least on par and sometimes even better than pure DNN-based approaches in terms of AAD accuracy in all tested conditions. However, when using the DNN to support a linear data-driven beamformer, a performance improvement over the purely linear approach was obtained in the most challenging scenarios. The use of multiple microphones was also found to improve speaker separation and AAD performance over single-microphone systems. SignificanceRecent proof-of-concept studies in this context each focus on a different method in a different experimental setting, which makes it hard to compare them. Furthermore, they are tested in highly idealized experimental conditions, which are still far from a realistic hearing aid setting. This work provides a systematic comparison of a linear and non-linear neuro-steered speech enhancement model, as well as a more realistic validation in challenging conditions.

bioengineering↗

bioRxiv2019

Optimal number and placement of EEG electrodes for measurement of neural tracking of speech

Measurement of neural tracking of natural running speech from the electroencephalogram (EEG) is an increasingly popular method in auditory neuroscience and has applications in audiology. The method involves decoding the envelope of the speech signal from the EEG signal, and calculating the correlation with the envelope of the audio stream that was presented to the subject. Typically EEG systems with 64 or more electrodes are used. However, in practical applications, set-ups with fewer electrodes are required. Here, we determine the optimal number of electrodes, and the best position to place a limited number of electrodes on the scalp. We propose a channel selection strategy based on an utility metric, which allows a quick quantitative assessment of the influence of a channel (or a group of channels) on the reconstruction error. We consider two use cases: a subject-specific case, where the optimal number and position of the electrodes is determined for each subject individually, and a subject-independent case, where the electrodes are placed at the same positions (in the 10-20 system) for all the subjects. We evaluated our approach using 64-channel EEG data from 90 subjects. In the subject-specific case we found that the correlation between actual and reconstructed envelope first increased with decreasing number of electrodes, with an optimum at around 20 electrodes, yielding 29% higher correlations using the optimal number of electrodes compared to all electrodes. This means that our strategy of removing electrodes can be used to improve the correlation metric in high-density EEG recordings. In the subject-independent case, we obtained a stable decoding performance when decreasing from 64 to 22 channels. When the number of channels was further decreased, the correlation decreased. For a maximal decrease in correlation of 10%, 32 well-placed electrodes were sufficient in 91% of the subjects.

neuroscience↗

bioRxiv2019

An Interpretable Performance Metric for Auditory Attention Decoding Algorithms in a Context of Neuro-Steered Gain Control

In a multi-speaker scenario, a hearing aid lacks information on which speaker the user intends to attend, and therefore it often mistakenly treats the latter as noise while enhancing an interfering speaker. Recently, it has been shown that it is possible to decode the attended speaker from the brain activity, e.g., recorded by electroencephalography sensors. While numerous of these auditory attention decoding (AAD) algorithms appeared in the literature, their performance is generally evaluated in a non-uniform manner. Furthermore, AAD algorithms typically introduce a trade-off between the AAD accuracy and the time needed to make an AAD decision, which hampers an objective benchmarking as it remains unclear which point in each algorithms trade-off space is the optimal one in a context of neuro-steered gain control. To this end, we present an interpretable performance metric to evaluate AAD algorithms, based on an adaptive gain control system, steered by AAD decisions. Such a system can be modeled as a Markov chain, from which the minimal expected switch duration (MESD) can be calculated and interpreted as the expected time required to switch the operation of the hearing aid after an attention switch of the user, thereby resolving the trade-off between AAD accuracy and decision time. Furthermore, we show that the MESD calculation provides an automatic and theoretically founded procedure to optimize the number of gain levels and decision time in an AAD-based adaptive gain control system.

neuroscience↗

bioRxiv2019

SHYBRID: A graphical tool for generating hybrid ground-truth spiking data for evaluating spike sorting performance

Spike sorting is the process of retrieving the spike times of individual neurons that are present in an extracellular neural recording. Over the last decades, many spike sorting algorithms have been published. In an effort to guide a user towards a specific spike sorting algorithm, given a specific recording setting (i.e., brain region and recording device), we provide an open-source graphical tool for the generation of hybrid ground-truth data in Python. Hybrid ground-truth data is a data-driven modelling paradigm in which spikes from a single unit are moved to a different location on the recording probe, thereby generating a virtual unit of which the spike times are known. The tool enables a user to efficiently generate hybrid ground-truth datasets and make informed decisions between spike sorting algorithms, fine-tune the algorithm parameters towards the used recording setting, or get a deeper understanding of those algorithms.

neuroscience↗

bioRxiv2019

Analysis of miniaturization effects and channel selection strategies for EEG sensor networks with application to auditory attention detection

ObjectiveConcealable, miniaturized electroencephalo-graphy ( mini-EEG) recording devices are crucial enablers towards long-term ambulatory EEG monitoring. However, the resulting miniaturization limits the inter-electrode distance and the scalp area that can be covered by a single device. The concept of wireless EEG sensor networks (WESNs) attempts to overcome this limitation by placing a multitude of these mini-EEG devices at various scalp locations. We investigate whether optimizing the WESN topology can compensate for miniaturization effects in an auditory attention detection (AAD) paradigm.\n\nMethodsStarting from standard full-cap high-density EEG data, we emulate several candidate mini-EEG sensor nodes which locally collect EEG data with embedded electrodes separated by short distances. We propose a greedy group-utility based channel selection strategy to select a subset of these candidate nodes, to form a WESN. We compare the AAD performance of this WESN with the performance obtained using long-distance EEG recordings.\n\nResultsThe AAD performance using short-distance EEG measurements is comparable to using an equal number of long-distance EEG measurements if in both cases the optimal electrode positions are selected. A significant increase in performance was found when using nodes with three electrodes over nodes with two electrodes.\n\nConclusionWhen the nodes are optimally placed, WESNs do not significantly suffer from EEG miniaturization effects in the case of AAD.\n\nSignificanceWESN-like platforms allow to achieve similar AAD performance as with long-distance EEG recordings, while adhering to the stringent miniaturization constraints for ambulatory EEG. Their applicability in an AAD task is important for the design of neuro-steered auditory prostheses.

neuroscience↗

bioRxiv2019

Stimulus-aware spatial filtering for single-trial neural response and temporal response function estimation in high-density EEG with applications in auditory research

Objective. Neural responses recorded using electroencephalography (EEG) and magnetoencephalography (MEG) can be used to study how our brain functions, as well as for various promising brain computer interface (BCI) applications. However, a common problem is the low signal to noise ratio (SNR) which makes it challenging to estimate task-related neural responses or the temporal response function (TRF) describing the linear relationship between the stimulus and the neural response, particularly over short data windows. To address these, we present an algorithm that takes advantage of the multi-channel nature of the recordings, and knowledge of the presented stimulus, to achieve a joint noise reduction and dimensionality reduction using spatial filtering. Methods. Forward modeling is used to project the stimulus onto the electrode space. The second-order statistics of this estimated desired signal and the raw neural data are used to estimate spatial filters that maximize the SNR of the neural response, based on a generalized eigenvalue decomposition. Main Results. 1. For synthesized EEG data, over a range of SNRs, our filtering resulted in significantly better TRF estimates from 20 s trials, compared to unfiltered EEG data. 2. On a dataset from 28 subjects who listened to a single-talker stimulus, our method resulted in correlations between predicted neural responses and the original EEG data that were significantly higher compared to standard approaches. 3. On a dataset of 16 subjects attending to 1 speaker in a two-speaker scenario, our method resulted in attention decoding accuracies which were higher compared to existing forward modelling methods. Significance. Our algorithm presents a data-driven way to denoise and reduce dimensionality of neural data, thus aiding further analysis, by utilizing the knowledge of the stimulus. The method is computationally efficient, and does not require repeated trials, thereby relieving experiment design from the necessity of presenting repeated stimuli to the subjects.

neuroscience↗

bioRxiv2018

EEG-based detection of the attended speaker and the locus of auditory attention with convolutional neural networks

In a multi-speaker scenario, the human auditory system is able to attend to one particular speaker of interest and ignore the others. It has been demonstrated that it is possible to use electroencephalography (EEG) signals to infer to which speaker someone is attending by relating the neural activity to the speech signals. However, classifying auditory attention within a short time interval remains the main challenge. We present a convolutional neural network-based approach to extract the locus of auditory attention (left/right) without knowledge of the speech envelopes. Our results show that it is possible to decode the locus of attention within 1 to 2 s, with a median accuracy of around 81%. These results are promising for neuro-steered noise suppression in hearing aids, in particular in scenarios where per-speaker envelopes are unavailable.

neuroscience↗

bioRxiv2018

Bootstrapping EEG-based auditory attention detection systems: boundary conditions for background noise and speaker positions

ObjectiveA listeners neural responses can be decoded to identify the speaker the person is attending to in a cocktail party environment. Such auditory attention detection methods have the potential to provide noise suppression algorithms in hearing devices with information about the listeners attention. A challenge is the effect of noise and other acoustic conditions that can reduce the attention detection accuracy. Specifically, noise can impact the ability of the person to segregate the sound sources and perform selective attention, as well as the external signal processing necessary to decode the attention effectively. The aim of this work is to systematically analyze the effect of noise level and speaker position on attention decoding accuracy.\n\nApproach28 subjects participated in the experiment. Auditory stimuli consisted of stories narrated by different speakers from 2 different locations, along with surrounding multi-talker background babble. EEG signals of the subjects were recorded while they focused on one story and ignored the other. The strength of the babble noise as well as the spatial separation between the two speakers were varied between presentations. Spatio-temporal decoders were trained for each subject, and applied to decode attention of the subjects from every 30s segment of data. Behavioral speech recognition thresholds were obtained for the different speaker separations.\n\nMain resultsBoth the background noise level and the angular separation between speakers affected attention decoding accuracy. Remarkably, attention decoding performance was seen to increase with the inclusion of moderate background noise (versus no noise), while across the different noise conditions performance dropped significantly with increasing noise level. We also observed that decoding accuracy improved with increasing speaker separation, exhibiting the advantage of spatial release from masking. Furthermore, the effect of speaker separation on the decoding accuracy became stronger when the background noise level increased. A significant correlation between speech intelligibility and attention decoding accuracy was found across conditions.\n\nSignificanceThis work shows how the background noise level and relative positions of competing talkers impact attention decoding accuracy. It indicates in which circumstances a neuro-steered noise suppression system may need to operate, in function of acoustic conditions. It also indicates the boundary conditions for the operation of EEG-based attention detection systems in neuro-steered hearing prostheses.\n\nIndex TermsAuditory attention detection, EEG processing, neuro-steered auditory prostheses, brain-computer interface, cocktail party, acoustic conditions.\n\nThe work is funded by KU Leuven Special Research Fund C14/16/057 and OT/14/119, FWO project nrs. 1.5.123.16N and G0A4918N, the ERC (637424) under the European Unions Horizon 2020 research and innovation programme, and a research gift of Starkey Hearing Technologies. The scientific responsibility is assumed by its authors.

bioengineering↗

bioRxiv2018

Reproducible evaluation of classification methods in Alzheimer’s disease: framework and application to MRI and PET data

A large number of papers have introduced novel machine learning and feature extraction methods for automatic classification of Alzheimers disease (AD). However, while the vast majority of these works use the public dataset ADNI for evaluation, they are difficult to reproduce because different key components of the validation are often not readily available. These components include selected participants and input data, image preprocessing and cross-validation procedures. The performance of the different approaches is also difficult to compare objectively. In particular, it is often difficult to assess which part of the method (e.g. preprocessing, feature extraction or classification algorithms) provides a real improvement, if any. In the present paper, we propose a framework for reproducible and objective classification experiments in AD using three publicly available datasets (ADNI, AIBL and OASIS). The framework comprises: i) automatic conversion of the three datasets into a standard format (BIDS); ii) a modular set of preprocessing pipelines, feature extraction and classification methods, together with an evaluation framework, that provide a baseline for benchmarking the different components. We demonstrate the use of the framework for a large-scale evaluation on 1960 participants using T1 MRI and FDG PET data. In this evaluation, we assess the influence of different modalities, preprocessing, feature types (regional or voxel-based features), classifiers, training set sizes and datasets. Performances were in line with the state-of-the-art. FDG PET outperformed T1 MRI for all classification tasks. No difference in performance was found for the use of different atlases, image smoothing, partial volume correction of FDG PET images, or feature type. Linear SVM and L2-logistic regression resulted in similar performance and both outperformed random forests. The classification performance increased along with the number of subjects used for training. Classifiers trained on ADNI generalized well to AIBL and OASIS, performing better than the classifiers trained and tested on each of these datasets independently. All the code of the framework and the experiments is publicly available.

neuroscience↗

bioRxiv2017

Online detection of auditory attention with mobile EEG: closing the loop with neurofeedback

Auditory attention detection (AAD) is promising for use in auditory-assistive devices to detect to which sound the user is attending. Being able to train subjects in achieving high AAD performance would greatly increase its application potential. In order to do so an acceptable temporal resolution and online implementation are essential prerequisites. Consequently, users of an online AAD can be presented with feedback about their performance. Here we describe two studies that investigate the effects of online AAD with feedback. In the first study, we implemented a fully automated closed-loop system that allows for user-friendly recording environments. Subjects were presented online with visual feedback on their ongoing AAD performance. Following these results we implemented a longitudinal case study in which two subjects were presented with AAD sessions during four weeks. The results prove the feasibility of a fully working online (neuro)feedback system for AAD decoding. The detected changes in AAD for the feedback subject during and after training suggest that changes in AAD may be achieved via training. This is early evidence of such training effects and needs to be confirmed in future studies to evaluate training of AAD in more detail. Finally, the large number of sessions allowed to examine the correlation between the stimuli (i.e. acoustic stories) and AAD performance which was found to be significant. Future studies are suggested to evaluate their acoustic stimuli with care to prevent spurious associations.

neuroscience↗