Search

Most damage-assessment strategies for dynamic systems only distinguish between undamaged and damaged conditions without recognizing the level or type of damage or considering unseen conditions. This paper proposes a novel framework for structural health monitoring (SHM) that combines supervised and unsupervised learning techniques to assess damage using a system's structural response (e.g., the acceleration response of big infrastructures). The objective is to enhance the benefits of a supervised learning framework while addressing the challenges of working in an SHM context. The proposed framework uses a Linear Discriminant Analysis (LDA)/Probabilistic Linear Discriminant Analysis (PLDA) strategy that enables learning the distributions of known classes and the performance of probabilistic estimations on new incoming data. The methodology is developed and proposed in two versions. The first version is used in the context of controlled, conditioned monitoring or for post-damage assessment, while the second analyzes the single observational data. Both strategies are built in an automatic framework able to classify known conditions and recognize unseen damage classes, which are then used to update the classification algorithm. The proposed framework's effectiveness is first tested considering the acceleration response of a numerically simulated 12-degree-of-freedom system. Then, the methodology's practicality is validated further by adopting the experimental monitoring data of the benchmark study case of the Z24 bridge. [ABSTRACT FROM AUTHOR]

Most damage-assessment strategies for dynamic systems only distinguish between undamaged and damaged conditions without recognizing the level or type of damage or considering unseen conditions. This paper proposes a novel framework for structural health monitoring (SHM) that combines supervised and unsupervised learning techniques to assess damage using a system’s structural response (e.g., the acceleration response of big infrastructures). The objective is to enhance the benefits of a supervised learning framework while addressing the challenges of working in an SHM context. The proposed framework uses a Linear Discriminant Analysis (LDA)/Probabilistic Linear Discriminant Analysis (PLDA) strategy that enables learning the distributions of known classes and the performance of probabilistic estimations on new incoming data. The methodology is developed and proposed in two versions. The first version is used in the context of controlled, conditioned monitoring or for post-damage assessment, while the second analyzes the single observational data. Both strategies are built in an automatic framework able to classify known conditions and recognize unseen damage classes, which are then used to update the classification algorithm. The proposed framework’s effectiveness is first tested considering the acceleration response of a numerically simulated 12-degree-of-freedom system. Then, the methodology’s practicality is validated further by adopting the experimental monitoring data of the benchmark study case of the Z24 bridge.

Advances in the digital world have attracted the attention of many researchers in terms of developing digital forensics. Using machine learning methods for print source identification is one of the developing areas in the field of digital forensics. In this paper, a new method is presented for printer source identification by modeling the primary Local Binary Pattern (LBP) features in the total variable printer space and extracting the secondary features based on the joint factor analysis. Only one low‐dimensional i‐vector feature is employed for each document image without using any optical character recognition (OCR) algorithm or similar processes. This property eliminates the requirement for the majority voting algorithm and reduces the computational cost of the classification process. Furthermore, the proposed algorithm is not limited to a specific language or character set. The capabilities of the proposed method in extracting useful discriminant information from the sparse print shadow texture are revealed through simulation. The simulation results showed that the proposed algorithm obtained the accuracy of 98.48% by refining the basic features of LBP, which is comparable to the results of the state‐of‐the‐art approaches in this field. [ABSTRACT FROM AUTHOR]

This paper proposes a precise WiFi fingerprinting indoor positioning algorithm for complex pedestrian environments. We transform the disturbed received signal strength (RSS) from the original space to latent space using the improved probabilistic linear discriminant analysis (PLDA). In the latent space, Bayes rule is used to calculate the posterior probability of the similarity between the test point and the reference points, and the ${K}$ reference points with the highest posterior probability are weighted to estimate the position. Actual on-site experiments involving three floors demonstrate that the mean localization error of the proposed algorithm is 1.38 m, which outperforms the Horus algorithm by 29% under the same test conditions. In addition, by studying the variability of mean value of RSS in different pedestrian environments, the fingerprint maps in different states of personnel movement are simulated. By using which, the average localization error of the proposed algorithm increases slightly to 1.63m, while the workload required during the offline training phase is significantly reduced. [ABSTRACT FROM AUTHOR]

Fast development of modern technologies of digital processing and speech recording leads to the fact that it is necessary to take into account the potential threats from the speech replay attacks. We propose our ensemble fusion replay attack detection system. It uses constant Q cepstral coefficients as speech features and short-time mean normalization for their preprocessing. The set of binary classifiers includes multiple Gaussian mixture models based Bayesian classifier, i-vector based Gaussian Probabilistic Linear Discriminant Analysis and XGBoost tree boosting algorithm. Fusion of scores was made by modified logistic regression algorithm from BOSARIS toolbox. ASV Spoof 2017 corpus is utilized in the experiments as the main database for anti-spoofing systems evaluation. Obtained results demonstrate that the proposed system can provide substantially better performance than the baseline Gaussian mixture model classifier. The pre-processing of cepstral features is crucial for the better performance of the system. High evaluation performance can be obtained using only few algorithms in a set. The attained value of equal error rate EER=12.44% for our fusion classifier is competitive with the best results obtained during last two years. DOI 10.14258/izvasu(2018)1-19

• A series of neural adversarial learning methods are proposed for speaker recognition. • Deep learning is implemented for PLDA speaker recognition with i -vectors. • Adversarial manifold learning is proposed to build a subspace model with neighbor embeddings in latent variables. • Multiobjective learning is performed for minimax optimization. • Adversarial augmentation learning is proposed to compensate the imbalanced data problem in speaker recognition. This paper presents the adversarial learning approaches to deal with various tasks in speaker recognition based on probabilistic discriminant analysis (PLDA) which is seen as a latent variable model for reconstruction of i -vectors. The first task aims to reduce the dimension of i -vectors based on an adversarial manifold learning where the adversarial neural networks of generator and discriminator are merged to preserve neighbor embedding of i -vectors in a low-dimensional space. The generator is trained to fool the discriminator with the generated samples in latent space. A PLDA subspace model is constructed by jointly minimizing a PLDA reconstruction error, a manifold loss for neighbor embedding and an adversarial loss caused by the generator and discriminator. The second task of adversarial learning is developed to tackle the imbalanced data problem. A PLDA based generative adversarial network is trained to generate new i -vectors to balance the size of training utterances across different speakers. An adversarial augmentation learning is proposed for robust speaker recognition. In particular, the minimax optimization is performed to estimate a generator and a discriminator where the class conditional i -vectors produced by generator could not be distinguished from real i -vectors via discriminator. A multiobjective learning is realized for a specialized neural model with the cosine similarity between real and fake i -vectors as well as the regularization for Gaussianity. Experiments are conducted to show the merit of adversarial learning in subspace construction and data augmentation for PLDA-based speaker recognition. [ABSTRACT FROM AUTHOR]

Probabilistic linear discriminant analysis (PLDA) is a method used for biometric problems like speaker or face recognition that models the variability of the samples using two latent variables, one that depends on the class of the sample and another one that is assumed independent across samples and models the within-class variability. In this work, we propose a generalization of PLDA that enables joint modeling of two sample-dependent factors: the class of interest and a nuisance condition. The approach does not change the basic form of PLDA but rather modifies the training procedure to consider the dependency across samples of the latent variable that models within-class variability. While the identity of the nuisance condition is needed during training, it is not needed during testing since we propose a scoring procedure that marginalizes over the corresponding latent variable. We show results on a multilingual speaker-verification task, where the language spoken is considered a nuisance condition. The proposed joint PLDA approach leads to significant performance gains in this task for two different data sets, in particular when the training data contains mostly or only monolingual speakers. [ABSTRACT FROM AUTHOR]

Language mismatch represents one of the more difficult challenges in achieving effective speaker verification in naturalistic audio streams. The portion of bi-lingual speakers worldwide continues to grow making speaker verification for speech technology more difficult. In this study, three specific methods are proposed to address this issue. Experiments are conducted on the PRISM (Promoting Robustness in Speaker Modeling) evaluation-set. We first show that adding small amounts of multi-lingual seed data to the Probabilistic Linear Discriminant Analysis (PLDA) development set, leads to a significant relative improvement of +17.96% in system Equal Error Rate (EER). Second, we compute the eigendirections that represent the distribution of multi-lingual data added to PLDA. We show that by adding these new eigendirections as part of the Linear Discriminant Analysis (LDA), and then minimizing them to directly compensate for language mismatch, further performance gains for speaker verification are achieved. By combining both multi-lingual PLDA and this minimization step with the new set of eigendirections, we obtain a +26.03% relative improvement in EER. In practical scenarios, it is highly unlikely that multi-lingual seed data representing the languages present in the test-set would be available. Hence, in the third phase, we address such scenarios, by proposing a method for Locally Weighted Linear Discriminant Analysis (LWLDA). In this third method, we reformulate the LDA equations to incorporate a local affine transform that weighs the same speaker samples. This method effectively preserves the local intrinsic information represented by the multimodal structure of the within-speaker scatter matrix, thereby helping to improve the class discriminating ability of LDA. It also helps in extending the ability of LDA to transform the speaker i-Vectors to dimensions that are greater than the total number of speaker classes. Using LWLDA, a relative improvement of +8.54% is obtained in system EER. LWLDA provides even more gain when multi-lingual seed data is available, and improves the system peformance by relative +26.03% in terms of EER. We also compare LWLDA to the recently proposed Nearest Neighbor Non-Parametric Discriminant Analysis (NDA). We show that not only is LWLDA better than NDA in terms of system performance but is also computationally less expensive. Comparative studies on DARPA Robust Automatic Transcription of Speech (RATS) corpus also show that LWLDA consistently outperforms NDA and LDA on different evaluation conditions. Our solutions offer new directions for addressing a challenging problem which has received limited attention in the speaker recognition community. [ABSTRACT FROM AUTHOR]

This paper extends upon a previous work using Mean Shift algorithm to perform speaker clustering on i-vectors generated from short speech segments. In this paper we examine the effectiveness of probabilistic linear discriminant analysis (PLDA) scoring as the metric of the mean shift clustering algorithm in the presence of different numbers of speakers. Our proposed method, combined with k-nearest neighbors (kNN) for bandwidth estimation, yields better and more robust results in comparison to the cosine similarity with fixed neighborhood bandwidth for clustering segments of large numbers of speakers. In the case of 30 speakers, we achieved significant improvement in cluster and speaker purity with the PLDA-based mean shift algorithm compared to the cosine-based baseline system. [ABSTRACT FROM AUTHOR]

Probabilistic linear discriminant analysis (PLDA) is widely implemented in speaker verification tasks. However, PLDA has limitations owing to its assumptions. In this study, we explore how to make deep speaker embeddings suitable for PLDA in complex situations. We analyze PLDA in detail and summarize its three important properties, Gaussianity, simplicity, and domain sensitivity. For the Gaussianity, by comparing the discrimination and Gaussianity of embeddings extracted from different layers of speaker extractors with different numbers of segment-level fully connected (Fc) layers, we demonstrate that embeddings extracted from the first Fc layer of models with two segment-level Fc layers are more suitable for PLDA. Secondly, several common speaker datasets comprise multiple short-duration speech segments extracted from long speech. We find that embeddings of short speech segments extracted from the long speech are less reliable and have complex within-class distributions. By determining the weighted average of embeddings extracted from short-duration speech segments, we simplify the embeddings distribution and make the embeddings suitable for PLDA. Thirdly, PLDA is sensitive to domain mismatches. We propose data adaptation methods that work directly on raw speech to eliminate explicit mismatches, such as the codecs and the environment noise mismatches. We prove that the data adaptation methods achieve performance improvements of PLDA and show strong complementarity with backend adaptation methods. We conduct extensive experiments, using the NIST SRE CTS superset, VoxCeleb, and SRE16 as the training set, and the SRE21 set as the evaluation set mainly. The experimental results show that our methods effectively improve the overall performance of PLDA. • We investigate how to make embeddings suitable for PLDA. • We analyze the effect of the number of segment-level fully-connected layers on embeddings. • We explore the relationship between speech segment duration and embeddings. • We propose data adaptation method to eliminate the relatively explicit mismatch. [ABSTRACT FROM AUTHOR]

In this paper, we make use of hidden Markov model (HMM) state alignment information in i‐vector/probabilistic linear discriminant analysis (PLDA) framework to improve the verification performance in a text‐dependent single utterance (TDSU) task. In the TDSU task, speakers repeat a fixed utterance in both enrollment and authentication sessions. Despite Gaussian mixture models (GMMs) have been the dominant modeling technique for text‐independent applications, an HMM based method might be better suited for the TDSU task since it captures the co‐articulation information better. Recently, powerful channel compensation techniques such as joint factor analysis (JFA), i‐vectors and PLDA have been proposed for GMM based text‐independent speaker verification. In this study, we train a separate i‐vector/PLDA model for each sentence HMM state in order to utilize the alignment information of the HMM states in a TDSU task. The proposed method is tested using a multi‐channel speaker verification database. In the experiments, it is observed that HMM state based i‐vector/PLDA (i‐vector/PLDA‐HMM) provides approximately 67% relative reduction in equal error rate (EER) when compared to the i‐vector/PLDA. The proposed method also outperforms the baseline GMM and sentence HMM methods. It yields approximately 51% relative reduction in EER over the best performing sentence HMM method. [ABSTRACT FROM AUTHOR]

Previous studies have demonstrated the benefits of PLDA–SVM scoring with empirical kernel maps for i-vector/PLDA speaker verification. The method not only performs significantly better than the conventional PLDA scoring and utilizes the multiple enrollment utterances of target speakers effectively, but also opens up opportunity for adopting sparse kernel machines in PLDA-based speaker verification systems. This paper proposes taking the advantages of empirical kernel maps by incorporating them into a more advanced kernel machine called relevance vector machines (RVMs). The paper reports extensive analyses on the behaviors of RVMs and provides insight into the properties of RVMs and their applications in i-vector/PLDA speaker verification. Results on NIST 2012 SRE demonstrate that PLDA–RVM outperforms the conventional PLDA and that it achieves a comparable performance as PLDA–SVM. Results also show that PLDA–RVM is much sparser than PLDA–SVM. [ABSTRACT FROM AUTHOR]

• Intelligibility assessment of dysarthric speech using UA and TORGO databases. • Different frame-level features are extracted in from temporal, spectral, and cepstral domains. • Temporal encoding and Fisher vector encoding techniques are used to convert frame-level features to utterance level features. • Probabilistic linear discriminant analysis (PLDA) and artificial neural network (ANN) classifiers are used for the intelligibility assessment of dysarthric speech. • Fisher vector encoding performance is superior to temporal encoding and ANN performance is superior to PLDA. Neuromuscular disorders can lead to dysarthria. Dysarthria is a speech disorder that mainly affects the human motor speech system. It often results in reduced speech intelligibility. Speech intelligibility is one of the parameters to assess the severity of dysarthria. The intelligibility of speech decreases as the severity increases. Automatic speech intelligibility assessment could be reliable and cost-effective compared to the conventional methods which need experienced speech pathologists. Automatic intelligibility assessment includes feature extraction and classification. Features extracted from spectral and cepstral domains are investigated for use in intelligibility assessment. Frame level features are extracted from different signal representations in spectral and cepstral domains. Fisher vector encoding and temporal encoding that uses descriptive statistics are applied to convert frame level features into utterance level. These features are fed to PLDA and ANN classifiers for intelligibility assessment. Overall, the performance of Fisher vector encoding is found to be superior compared to temporal encoding. In all features, the performance of ANN is better in assessing the intelligibility levels compared to PLDA as expected. The STFT, as well as harmonics in spectral domain and CQCC in the cepstral domain, performed well for intelligibility assessment of unseen data of TORGO database. [ABSTRACT FROM AUTHOR]

In this letter, we propose a new acoustic modeling approach for automatic speech recognition based on probabilistic linear discriminant analysis (PLDA), which is used to model the state density function for the standard hidden Markov models (HMMs). Unlike the conventional Gaussian mixture models (GMMs) where the correlations are weakly modelled by using the diagonal covariance matrices, PLDA captures the correlations of feature vector in subspaces without vastly expanding the model. It also allows the usage of high dimensional feature input, and therefore is more flexible to make use of different type of acoustic features. We performed the preliminary experiments on the Switchboard corpus, and demonstrated the feasibility of this acoustic model. [ABSTRACT FROM AUTHOR]

In this letter, we apply Phone Log-Likelihood Ratio (PLLR) features to the task of speaker recognition. PLLRs, which are computed on the phone posterior probabilities provided by phone decoders, convey acoustic-phonetic information in a sequence of frame-level vectors, and therefore can be easily plugged into traditional acoustic systems, just by replacing the Mel-Frequency Cepstral Coefficients (MFCC) or an alternate representation. To study the performance of the proposed features, MFCC-based and PLLR-based systems are trained under an i-vector-PLDA approach. Results on the NIST 2010 and 2012 Speaker Recognition Evaluation databases show that, despite yielding lower performance than the acoustic system, the system based on PLLR features does provide significant gains when both systems are fused, which reveals a complementarity among features, and provides a suitable and effective way of using higher level phonetic information in speaker recognition systems. [ABSTRACT FROM AUTHOR]

This study introduces a linear Gaussian model‐based framework for voice biometrics. The model works with discrete‐time linear dynamical systems. The study motivation is to use the linear Gaussian modelling method in voice biometrics, and show that the accuracy offered by the linear Gaussian modelling method is comparable with other state‐of‐the‐art methods such as Probabilistic Linear Discriminant Analysis and two‐covariance model. An expectation–maximisation algorithm is derived to train the model and a Bayesian solution is used to calculate the log‐likelihood ratio score of all trials of speakers. This approach performed well on the core‐extended conditions of the NIST 2010 Speaker Recognition Evaluation, and is competitive compared with the Gaussian probabilistic linear discriminant analysis, in terms of normalised decision cost function. [ABSTRACT FROM AUTHOR]

This work presents a new and efficient approach to discriminative speaker verification in the i–vector space. We illustrate the development of a linear discriminative classifier that is trained to discriminate between the hypothesis that a pair of feature vectors in a trial belong to the same speaker or to different speakers. This approach is alternative to the usual discriminative setup that discriminates between a speaker and all the other speakers. We use a discriminative classifier based on a Support Vector Machine (SVM) that is trained to estimate the parameters of a symmetric quadratic function approximating a log–likelihood ratio score without explicit modeling of the i–vector distributions as in the generative Probabilistic Linear Discriminant Analysis (PLDA) models. Training these models is feasible because it is not necessary to expand the i–vector pairs, which would be expensive or even impossible even for medium sized training sets. The results of experiments performed on the tel-tel extended core condition of the NIST 2010 Speaker Recognition Evaluation are competitive with the ones obtained by generative models, in terms of normalized Detection Cost Function and Equal Error Rate. Moreover, we show that it is possible to train a gender–independent discriminative model that achieves state–of–the–art accuracy, comparable to the one of a gender–dependent system, saving memory and execution time both in training and in testing. [ABSTRACT FROM PUBLISHER]

Face recognition in uncontrolled environments remains an open problem that has not been satisfactorily solved by existing recognition techniques. In this paper, we tackle this problem using a variant of the recently proposed Probabilistic Linear Discriminant Analysis (PLDA). We show that simplified versions of the PLDA model, which are regularly used in the field of speaker recognition, rely on certain assumptions that not only result in a simpler PLDA model, but also reduce the computational load of the technique and - as indicated by our experimental assessments - improve recognition performance. Moreover, we show that, contrary to the general belief that PLDA-based methods produce well calibrated verification scores, score normalization techniques can still deliver significant performance gains, but only if non-parametric score normalization techniques are employed. Last but not least, we demonstrate the competitiveness of the simplified PLDA model for face recognition by comparing our results with the state-of-the-art results from the literature obtained on the second version of the large-scale Face Recognition Grand Challenge (FRGC) database. [ABSTRACT FROM AUTHOR]

The application of probabilistic linear discriminant analysis (PLDA) to speaker adaptation for automatic speech recognition based on hidden Markov models is proposed. By expressing the set of acoustic models of each of the training speakers in a matrix and treating each column as a sample, the small sample problem that can be encountered in PLDA if only one sample is available for each training speaker is overcome. In the continuous speech recognition experiments, the performance of the PLDA based approach improves over the principal component analysis (PCA) based approach and the two‐dimensional PCA based approach for adaptation data longer than 12 s. [ABSTRACT FROM AUTHOR]