Weighted LDA techniques for I-vector based speaker verification

This paper introduces the Weighted Linear Discriminant Analysis (WLDA) technique, based upon the weighted pairwise Fisher criterion, for the purposes of improving i-vector speaker verification in the presence of high intersession variability. By taking advantage of the speaker discriminative information that is available in the distances between pairs of speakers clustered in the development i-vector space, the WLDA technique is shown to provide an improvement in speaker verification performance over traditional Linear Discriminant Analysis (LDA) approaches. A similar approach is also taken to extend the recently developed Source Normalised LDA (SNLDA) into Weighted SNLDA (WSNLDA) which, similarly, shows an improvement in speaker verification performance in both matched and mismatched enrolment/verification conditions. Based upon the results presented within this paper using the NIST 2008 Speaker Recognition Evaluation dataset, we believe that both WLDA and WSNLDA are viable as replacement techniques to improve the performance of LDA and SNLDA-based i-vector speaker verification.

PLDA based speaker recognition on short utterances

This paper investigates the effects of limited speech data in the context of speaker verification using a probabilistic linear discriminant analysis (PLDA) approach. Being able to reduce the length of required speech data is important to the development of automatic speaker verification system in real world applications. When sufficient speech is available, previous research has shown that heavy-tailed PLDA (HTPLDA) modeling of speakers in the i-vector space provides state-of-the-art performance, however, the robustness of HTPLDA to the limited speech resources in development, enrolment and verification is an important issue that has not yet been investigated. In this paper, we analyze the speaker verification performance with regards to the duration of utterances used for both speaker evaluation (enrolment and verification) and score normalization and PLDA modeling during development. Two different approaches to total-variability representation are analyzed within the PLDA approach to show improved performance in short-utterance mismatched evaluation conditions and conditions for which insufficient speech resources are available for adequate system development. The results presented within this paper using the NIST 2008 Speaker Recognition Evaluation dataset suggest that the HTPLDA system can continue to achieve better performance than Gaussian PLDA (GPLDA) as evaluation utterance lengths are decreased. We also highlight the importance of matching durations for score normalization and PLDA modeling to the expected evaluation conditions. Finally, we found that a pooled total-variability approach to PLDA modeling can achieve better performance than the traditional concatenated total-variability approach for short utterances in mismatched evaluation conditions and conditions for which insufficient speech resources are available for adequate system development.

PLDA based speaker verification with weighted LDA techniques

This paper investigates the use of the dimensionality-reduction techniques weighted linear discriminant analysis (WLDA), and weighted median fisher discriminant analysis (WMFD), before probabilistic linear discriminant analysis (PLDA) modeling for the purpose of improving speaker verification performance in the presence of high inter-session variability. Recently it was shown that WLDA techniques can provide improvement over traditional linear discriminant analysis (LDA) for channel compensation in i-vector based speaker verification systems. We show in this paper that the speaker discriminative information that is available in the distance between pair of speakers clustered in the development i-vector space can also be exploited in heavy-tailed PLDA modeling by using the weighted discriminant approaches prior to PLDA modeling. Based upon the results presented within this paper using the NIST 2008 Speaker Recognition Evaluation dataset, we believe that WLDA and WMFD projections before PLDA modeling can provide an improved approach when compared to uncompensated PLDA modeling for i-vector based speaker verification systems.

Near infrared (NIR) absorption spectra correlates with subchondral bone micro-CT parameters in osteoarthritic rat models

Determining the properties and integrity of subchondral bone in the developmental stages of osteoarthritis, especially in a form that can facilitate real-time characterization for diagnostic and decision-making purposes, is still a matter for research and development. This paper presents relationships between near infrared absorption spectra and properties of subchondral bone obtained from 3 models of osteoarthritic degeneration induced in laboratory rats via: (i) menisectomy (MSX); (ii) anterior cruciate ligament transaction (ACL); and (iii) intra-articular injection of mono-ido-acetate (1 mg) (MIA), in the right knee joint, with 12 rats per model group (N = 36). After 8 weeks, the animals were sacrificed and knee joints were collected. A custom-made diffuse reflectance NIR probe of diameter 5 mm was placed on the tibial surface and spectral data were acquired from each specimen in the wavenumber range 4000–12 500 cm− 1. After spectral acquisition, micro computed tomography (micro-CT) was performed on the samples and subchondral bone parameters namely: bone volume (BV) and bone mineral density (BMD) were extracted from the micro-CT data. Statistical correlation was then conducted between these parameters and regions of the near infrared spectra using multivariate techniques including principal component analysis (PCA), discriminant analysis (DA), and partial least squares (PLS) regression. Statistically significant linear correlations were found between the near infrared absorption spectra and subchondral bone BMD (R2 = 98.84%) and BV (R2 = 97.87%). In conclusion, near infrared spectroscopic probing can be used to detect, qualify and quantify changes in the composition of the subchondral bone, and could potentially assist in distinguishing healthy from OA bone as demonstrated with our laboratory rat models.

Wetlands, climate zones and Barmah Forest virus disease in Queensland, Australia

Barmah Forest virus (BFV) disease is the second most common mosquito-borne disease in Australia, but the linkages of the wetlands and climate zones with BFV transmission remain unclear. We aimed to examine the relationship between the wetlands, climate zones and BFV risk in Queensland, Australia. Data on the wetlands, climate zones, population and BFV cases for the period 1992 to 2008 were obtained from relevant government agencies. BFV risk was grouped as low-, medium- and high-level based on BFV incidence percentiles. The buffer zones around each BFV case were made using 1, 5, 10, 15, 20, 25 and 50 km distances. We performed a discriminant analysis to determine the differences between wetland classes and BFV risk within each climate zone. The discriminant analyses show that saline 1, riverine and saline tidal influence were the most significant contributors to BFV risk in all climate and buffer zones, while lacustrine, palustrine, estuarine and saline 2 and saline 3 wetlands were less important. These models had classification accuracies of 76%, 98% and 100% for BFV risk in subtropical, tropical and temperate climate zones, respectively. This study demonstrates that BFV risk varies with wetland class and climate zone. The discriminant analysis is a useful tool to quantify the links between wetlands, climate zones and BFV risk.

I-vector based speaker recognition using advanced channel compensation techniques

This paper investigates advanced channel compensation techniques for the purpose of improving i-vector speaker verification performance in the presence of high intersession variability using the NIST 2008 and 2010 SRE corpora. The performance of four channel compensation techniques: (a) weighted maximum margin criterion (WMMC), (b) source-normalized WMMC (SN-WMMC), (c) weighted linear discriminant analysis (WLDA), and; (d) source-normalized WLDA (SN-WLDA) have been investigated. We show that, by extracting the discriminatory information between pairs of speakers as well as capturing the source variation information in the development i-vector space, the SN-WLDA based cosine similarity scoring (CSS) i-vector system is shown to provide over 20% improvement in EER for NIST 2008 interview and microphone verification and over 10% improvement in EER for NIST 2008 telephone verification, when compared to SN-LDA based CSS i-vector system. Further, score-level fusion techniques are analyzed to combine the best channel compensation approaches, to provide over 8% improvement in DCF over the best single approach, (SN-WLDA), for NIST 2008 interview/ telephone enrolment-verification condition. Finally, we demonstrate that the improvements found in the context of CSS also generalize to state-of-the-art GPLDA with up to 14% relative improvement in EER for NIST SRE 2010 interview and microphone verification and over 7% relative improvement in EER for NIST SRE 2010 telephone verification.

Which procurement system? Towards a universal procurement selection technique

Two approaches are described, which aid the selection of the most appropriate procurement arrangements for a building project. The first is a multi-attribute technique based on the National Economic Development Office procurement path decision chart. A small study is described in which the utility factors involved were weighted by averaging the scores of five 'experts' for three hypothetical building projects. A concordance analysis is used to provide some evidence of any abnormal data sources. When applied to the study data, one of the experts was seen to be atypical. The second approach is by means of discriminant analysis. This was found to provide reasonably consistent predictions through three discriminant functions. The analysis also showed the quality criteria to have no significant impact on the decision process. Both approaches provided identical and intuitively correct answers in the study described. Some concluding remarks are made on the potential of discriminant analysis for future research and development in procurement selection techniques.

Improving short utterance based I-vector speaker recognition using source and utterance-duration normalization techniques

A significant amount of speech is typically required for speaker verification system development and evaluation, especially in the presence of large intersession variability. This paper introduces a source and utterance duration normalized linear discriminant analysis (SUN-LDA) approaches to compensate session variability in short-utterance i-vector speaker verification systems. Two variations of SUN-LDA are proposed where normalization techniques are used to capture source variation from both short and full-length development i-vectors, one based upon pooling (SUN-LDA-pooled) and the other on concatenation (SUN-LDA-concat) across the duration and source-dependent session variation. Both the SUN-LDA-pooled and SUN-LDA-concat techniques are shown to provide improvement over traditional LDA on NIST 08 truncated 10sec-10sec evaluation conditions, with the highest improvement obtained with the SUN-LDA-concat technique achieving a relative improvement of 8% in EER for mis-matched conditions and over 3% for matched conditions over traditional LDA approaches.

Improving the PLDA based speaker verification in limited microphone data conditions

A significant amount of speech data is required to develop a robust speaker verification system, but it is difficult to find enough development speech to match all expected conditions. In this paper we introduce a new approach to Gaussian probabilistic linear discriminant analysis (GPLDA) to estimate reliable model parameters as a linearly weighted model taking more input from the large volume of available telephone data and smaller proportional input from limited microphone data. In comparison to a traditional pooled training approach, where the GPLDA model is trained over both telephone and microphone speech, this linear-weighted GPLDA approach is shown to provide better EER and DCF performance in microphone and mixed conditions in both the NIST 2008 and NIST 2010 evaluation corpora. Based upon these results, we believe that linear-weighted GPLDA will provide a better approach than pooled GPLDA, allowing for the further improvement of GPLDA speaker verification in conditions with limited development data.

Client and consultant perspectives of prequalification criteria

A crucial task in contractor prequalification is to establish a set of decision criteria through which the capabilities of contractors are measured and judged. However, in the UK, there are no nationwide standards or guidelines governing the selection of decision criteria for contractor prequalification. The decision criteria are usually established by individual clients on an ad hoc basis. This paper investigates the divergence of decision criteria used by different client and consultant organisations in contractor prequalification through a large empirical survey conducted in the UK. The results indicate that there are significant differences in the selection and use of decision criteria for prequalification.

Improving short utterance i-vector speaker verification using utterance variance modelling and compensation techniques

This paper proposes techniques to improve the performance of i-vector based speaker verification systems when only short utterances are available. Short-length utterance i-vectors vary with speaker, session variations, and the phonetic content of the utterance. Well established methods such as linear discriminant analysis (LDA), source-normalized LDA (SN-LDA) and within-class covariance normalisation (WCCN) exist for compensating the session variation but we have identified the variability introduced by phonetic content due to utterance variation as an additional source of degradation when short-duration utterances are used. To compensate for utterance variations in short i-vector speaker verification systems using cosine similarity scoring (CSS), we have introduced a short utterance variance normalization (SUVN) technique and a short utterance variance (SUV) modelling approach at the i-vector feature level. A combination of SUVN with LDA and SN-LDA is proposed to compensate the session and utterance variations and is shown to provide improvement in performance over the traditional approach of using LDA and/or SN-LDA followed by WCCN. An alternative approach is also introduced using probabilistic linear discriminant analysis (PLDA) approach to directly model the SUV. The combination of SUVN, LDA and SN-LDA followed by SUV PLDA modelling provides an improvement over the baseline PLDA approach. We also show that for this combination of techniques, the utterance variation information needs to be artificially added to full-length i-vectors for PLDA modelling.

Improving PLDA speaker verification with limited development data

This paper analyses the probabilistic linear discriminant analysis (PLDA) speaker verification approach with limited development data. This paper investigates the use of the median as the central tendency of a speaker’s i-vector representation, and the effectiveness of weighted discriminative techniques on the performance of state-of-the-art length-normalised Gaussian PLDA (GPLDA) speaker verification systems. The analysis within shows that the median (using a median fisher discriminator (MFD)) provides a better representation of a speaker when the number of representative i-vectors available during development is reduced, and that further, usage of the pair-wise weighting approach in weighted LDA and weighted MFD provides further improvement in limited development conditions. Best performance is obtained using a weighted MFD approach, which shows over 10% improvement in EER over the baseline GPLDA system on mismatched and interview-interview conditions.

Learning detectors quickly with stationary statistics

Computer vision is increasingly becoming interested in the rapid estimation of object detectors. The canonical strategy of using Hard Negative Mining to train a Support Vector Machine is slow, since the large negative set must be traversed at least once per detector. Recent work has demonstrated that, with an assumption of signal stationarity, Linear Discriminant Analysis is able to learn comparable detectors without ever revisiting the negative set. Even with this insight, the time to learn a detector can still be on the order of minutes. Correlation filters, on the other hand, can produce a detector in under a second. However, this involves the unnatural assumption that the statistics are periodic, and requires the negative set to be re-sampled per detector size. These two methods differ chie y in the structure which they impose on the co- variance matrix of all examples. This paper is a comparative study which develops techniques (i) to assume periodic statistics without needing to revisit the negative set and (ii) to accelerate the estimation of detectors with aperiodic statistics. It is experimentally verified that periodicity is detrimental.

Matching image sets via adaptive multi convex hull

Traditional nearest points methods use all the samples in an image set to construct a single convex or affine hull model for classification. However, strong artificial features and noisy data may be generated from combinations of training samples when significant intra-class variations and/or noise occur in the image set. Existing multi-model approaches extract local models by clustering each image set individually only once, with fixed clusters used for matching with various image sets. This may not be optimal for discrimination, as undesirable environmental conditions (eg. illumination and pose variations) may result in the two closest clusters representing different characteristics of an object (eg. frontal face being compared to non-frontal face). To address the above problem, we propose a novel approach to enhance nearest points based methods by integrating affine/convex hull classification with an adapted multi-model approach. We first extract multiple local convex hulls from a query image set via maximum margin clustering to diminish the artificial variations and constrain the noise in local convex hulls. We then propose adaptive reference clustering (ARC) to constrain the clustering of each gallery image set by forcing the clusters to have resemblance to the clusters in the query image set. By applying ARC, noisy clusters in the query set can be discarded. Experiments on Honda, MoBo and ETH-80 datasets show that the proposed method outperforms single model approaches and other recent techniques, such as Sparse Approximated Nearest Points, Mutual Subspace Method and Manifold Discriminant Analysis.

Dictionary learning and sparse coding on Grassmann manifolds : an extrinsic solution

Recent advances in computer vision and machine learning suggest that a wide range of problems can be addressed more appropriately by considering non-Euclidean geometry. In this paper we explore sparse dictionary learning over the space of linear subspaces, which form Riemannian structures known as Grassmann manifolds. To this end, we propose to embed Grassmann manifolds into the space of symmetric matrices by an isometric mapping, which enables us to devise a closed-form solution for updating a Grassmann dictionary, atom by atom. Furthermore, to handle non-linearity in data, we propose a kernelised version of the dictionary learning algorithm. Experiments on several classification tasks (face recognition, action recognition, dynamic texture classification) show that the proposed approach achieves considerable improvements in discrimination accuracy, in comparison to state-of-the-art methods such as kernelised Affine Hull Method and graph-embedding Grassmann discriminant analysis.