Subspace techniques for task-independent EEG person identification
01 Jul 2019-Vol. 2019, pp 4545-4548
TL;DR: Novel modifications are proposed for both i-vector and x-vector frameworks to project person-specific signatures from multi-channel EEG into a subspace that enhances the biometric information and suppresses other nuisance factors.
Abstract: There has been a growing interest in studying electroencephalography signals (EEG) as a possible biometric. The brain signals captured by EEG are rich and carry information related to the individual, tasks being performed, mental state, and other channel/measurement noise due to session variability and artifacts. To effectively extract person-specific signatures present in EEG, it is necessary to define a subspace that enhances the biometric information and suppresses other nuisance factors. i-vector and x-vector are state-of-art subspace techniques used in speaker recognition. In this paper, novel modifications are proposed for both frameworks to project person-specific signatures from multi-channel EEG into a subspace. The modified i-vector and x-vector systems outperform baseline i-vector and x-vector systems with an absolute improvement of 10.5% and 15.9%, respectively.
Citations
More filters
TL;DR: In this article, a deep learning approach using siamese convolutional neural networks is employed to extract, from the considered EEG recordings, subject-specific template representations, and an extensive set of experimental tests, performed on a multi-session database comprising EEG data acquired from 45 subjects while performing six different tasks, are employed to evaluate whether it is actually possible to verify the identity of a subject using brain signals, regardless the performed mental task.
14 citations
Proceedings Article•
21 Jan 2022
TL;DR: This work extensively compare multiple state-of-the-art models and signal feature extractors in a real-time seizure detection framework suitable for real-world application, using various evaluation metrics including a new one to evaluate more practical aspects of seizure detection models.
Abstract: Electroencephalogram (EEG) is an important diagnostic test that physicians use to record brain activity and detect seizures by monitoring the signals. There have been several attempts to detect seizures and abnormalities in EEG signals with modern deep learning models to reduce the clinical burden. However, they cannot be fairly compared against each other as they were tested in distinct experimental settings. Also, some of them are not trained in real-time seizure detection tasks, making it hard for on-device applications. In this work, for the first time, we extensively compare multiple state-of-the-art models and signal feature extractors in a real-time seizure detection framework suitable for real-world application, using various evaluation metrics including a new one we propose to evaluate more practical aspects of seizure detection models.
4 citations
TL;DR: In this article, a subspace-based text-independent speaker recognition method was proposed to model biometric signatures independent of task/condition by normalizing the associated variance. But, the proposed method assumes that biometric information is present in the entire EEG signal and accumulate statistics across time in a high dimensional space.
Abstract: Electroencephalography (EEG) signals are promising as alternatives to other biometrics owing to their protection against spoofing. Previous studies have focused on capturing individual variability by analyzing task/condition-specific EEG. This work attempts to model biometric signatures independent of task/condition by normalizing the associated variance. Toward this goal, the paper extends ideas from subspace-based text-independent speaker recognition and proposes novel modifications for modeling multi-channel EEG data. The proposed techniques assume that biometric information is present in the entire EEG signal and accumulate statistics across time in a high dimensional space. These high dimensional statistics are then projected to a lower dimensional space where the biometric information is preserved. The lower dimensional embeddings obtained using the proposed approach are shown to be task-independent. The best subspace system identifies individuals with accuracies of 86.4% and 35.9% on datasets with 30 and 920 subjects, respectively, using just nine EEG channels. The paper also provides insights into the subspace model’s scalability to unseen tasks and individuals during training and the number of channels needed for subspace modeling.
4 citations
TL;DR: This work attempts to model biometric signatures independent of task/condition by normalizing the associated variance by extending ideas from subspace-based text-independent speaker recognition and proposing novel modifications for modeling multi-channel EEG data.
Abstract: Electroencephalography (EEG) signals are promising as alternatives to other biometrics owing to their protection against spoofing. Previous studies have focused on capturing individual variability by analyzing task/condition-specific EEG. This work attempts to model biometric signatures independent of task/condition by normalizing the associated variance. Toward this goal, the paper extends ideas from subspace-based text-independent speaker recognition and proposes novel modifications for modeling multi-channel EEG data. The proposed techniques assume that biometric information is present in the entire EEG signal and accumulate statistics across time in a high dimensional space. These high dimensional statistics are then projected to a lower dimensional space where the biometric information is preserved. The lower dimensional embeddings obtained using the proposed approach are shown to be task-independent. The best subspace system identifies individuals with accuracies of 86.4% and 35.9% on datasets with 30 and 920 subjects, respectively, using just nine EEG channels. The paper also provides insights into the subspace model's scalability to unseen tasks and individuals during training and the number of channels needed for subspace modeling.
4 citations
Cites background or methods or result from "Subspace techniques for task-indepe..."
...In [9], only preliminary results were discussed with no inter-task or inter-subject analysis....
[...]
...In [9], these subspace systems were modified to process information from multiple channels by concatenating channel-wise statistics at an intermediate processing level....
[...]
...i -vector and x-vector subspace context, the proposed modification in [9] is better than the direct early and late fusion techniques to model the data from different models....
[...]
...• This paper builds upon subspace systems introduced in [9] and proposes a novel system that combines the i -vector and the x-vector representations....
[...]
...systems proposed in [9] using two datasets....
[...]
05 Dec 2020
TL;DR: In this paper, a neural network system using the time-delay neural network to model temporal information and long short-term memory (LSTM) layer to model spatial information is proposed.
Abstract: Automatic detection of seizures from EEG signals is an important problem of interest for clinical institutions. EEG is a temporal signal collected from multiple spatial sources around the scalp. Efficient modeling of both temporal and spatial information is important to identify the seizures using EEG. In this paper, we propose a neural network system using the time-delay neural network to model temporal information (TDNN) and long short term memory (LSTM) layer to model spatial information. On the development subset of Temple University seizure dataset, the proposed system achieved a sensitivity of 23.32 % with 11.13 false alarms in 24 hours.
3 citations
References
More filters
TL;DR: Issues such as solving SVM optimization problems theoretical convergence multiclass classification probability estimates and parameter selection are discussed in detail.
Abstract: LIBSVM is a library for Support Vector Machines (SVMs). We have been actively developing this package since the year 2000. The goal is to help users to easily apply SVM to their applications. LIBSVM has gained wide popularity in machine learning and many other areas. In this article, we present all implementation details of LIBSVM. Issues such as solving SVM optimization problems theoretical convergence multiclass classification probability estimates and parameter selection are discussed in detail.
40,826 citations
"Subspace techniques for task-indepe..." refers methods in this paper
...LDA is computed over these embeddings, and a one-vs-all SVM classifier [15] is built using a cosine kernel to predict the person IDs....
[...]
...Finally, a one-vsall support vector machine (SVM) [15] with a cosine kernel is trained to predict the class labels....
[...]
TL;DR: The major elements of MIT Lincoln Laboratory's Gaussian mixture model (GMM)-based speaker verification system used successfully in several NIST Speaker Recognition Evaluations (SREs) are described.
4,673 citations
"Subspace techniques for task-indepe..." refers methods in this paper
...Universal background model-Gaussian mixture model (UBM-GMM) [9] systems have been widely used for EEG person identification [5], [10]–[13]....
[...]
...This configuration was fine-tuned for the UBM-GMM system in [5]....
[...]
...During testing, Top-C scoring is used to determine the identity of the EEG segment [9]....
[...]
TL;DR: An extension of the previous work which proposes a new speaker representation for speaker verification, a new low-dimensional speaker- and channel-dependent space is defined using a simple factor analysis, named the total variability space because it models both speaker and channel variabilities.
Abstract: This paper presents an extension of our previous work which proposes a new speaker representation for speaker verification. In this modeling, a new low-dimensional speaker- and channel-dependent space is defined using a simple factor analysis. This space is named the total variability space because it models both speaker and channel variabilities. Two speaker verification systems are proposed which use this new representation. The first system is a support vector machine-based system that uses the cosine kernel to estimate the similarity between the input data. The second system directly uses the cosine similarity as the final decision score. We tested three channel compensation techniques in the total variability space, which are within-class covariance normalization (WCCN), linear discriminate analysis (LDA), and nuisance attribute projection (NAP). We found that the best results are obtained when LDA is followed by WCCN. We achieved an equal error rate (EER) of 1.12% and MinDCF of 0.0094 using the cosine distance scoring on the male English trials of the core condition of the NIST 2008 Speaker Recognition Evaluation dataset. We also obtained 4% absolute EER improvement for both-gender trials on the 10 s-10 s condition compared to the classical joint factor analysis scoring.
3,526 citations
15 Apr 2018
TL;DR: This paper uses data augmentation, consisting of added noise and reverberation, as an inexpensive method to multiply the amount of training data and improve robustness of deep neural network embeddings for speaker recognition.
Abstract: In this paper, we use data augmentation to improve performance of deep neural network (DNN) embeddings for speaker recognition. The DNN, which is trained to discriminate between speakers, maps variable-length utterances to fixed-dimensional embeddings that we call x-vectors. Prior studies have found that embeddings leverage large-scale training datasets better than i-vectors. However, it can be challenging to collect substantial quantities of labeled data for training. We use data augmentation, consisting of added noise and reverberation, as an inexpensive method to multiply the amount of training data and improve robustness. The x-vectors are compared with i-vector baselines on Speakers in the Wild and NIST SRE 2016 Cantonese. We find that while augmentation is beneficial in the PLDA classifier, it is not helpful in the i-vector extractor. However, the x-vector DNN effectively exploits data augmentation, due to its supervised training. As a result, the x-vectors achieve superior performance on the evaluation datasets.
2,300 citations
"Subspace techniques for task-indepe..." refers background or methods in this paper
...Similarly, x-vector is a deep neural network (DNN) based speaker recognition approach proposed in [7]....
[...]
...The network is trained using the crossentropy error function similar to [7]....
[...]
...and x-vector based signal representations [6], [7] to EEG biometrics....
[...]
...x-vector is a DNN based state-of-the-art speaker recognition technique [7]....
[...]
01 Jun 2018
TL;DR: This paper investigates which configuration and which parameters lead to the best performance of an i-vectors/PLDA based speaker verification system and presents at the end some preliminary experiments in which the utterances comprised in the CSTR VCTK corpus were used besides utterances from MIT-MDSVC for training the total variability covariance matrix and the underlying PLDA matrices.
Abstract: It is known that the performance of the i-vectors/PLDA based speaker verification systems is affected in the cases of short utterances and limited training data The performance degradation appears because the shorter the utterance, the less reliable the extracted i-vector is, and because the total variability covariance matrix and the underlying PLDA matrices need a significant amount of data to be robustly estimated Considering the “MIT Mobile Device Speaker Verification Corpus” (MIT-MDSVC) as a representative dataset for robust speaker verification tasks on limited amount of training data, this paper investigates which configuration and which parameters lead to the best performance of an i-vectors/PLDA based speaker verification The i-vectors/PLDA based system achieved good performance only when the total variability matrix and the underlying PLDA matrices were trained with data belonging to the enrolled speakers This way of training means that the system should be fully retrained when new enrolled speakers were added The performance of the system was more sensitive to the amount of training data of the underlying PLDA matrices than to the amount of training data of the total variability matrix Overall, the Equal Error Rate performance of the i-vectors/PLDA based system was around 1% below the performance of a GMM-UBM system on the chosen dataset The paper presents at the end some preliminary experiments in which the utterances comprised in the CSTR VCTK corpus were used besides utterances from MIT-MDSVC for training the total variability covariance matrix and the underlying PLDA matrices
790 citations
"Subspace techniques for task-indepe..." refers background or methods in this paper
...and x-vector based signal representations [6], [7] to EEG biometrics....
[...]
...i-vector system is one such technique proposed for speaker recognition in [6] and adopted for EEG person identification in [14]....
[...]
...The procedure for training the T -Matrix and thereby extracting ivectors can be found in [6]....
[...]