A blind indic script recognizer for multi-script documents

We report a hierarchical blind script identifier for 11 different Indian scripts. An initial grouping of the 11 scripts is accomplished at the first level of this hierarchy. At the subsequent level, we recognize the script in each group. The various nodes of this tree use different feature-classifier combinations. A database of 20,000 words of different font styles and sizes is collected and used for each script. Effectiveness of Gabor and Discrete Cosine Transform features has been independently, evaluated using nearest neighbor linear discriminant and support vector machine classifiers. The minimum and maximum accuracies obtained, using this hierarchical mechanism, are 92.2% and 97.6%, respectively.

Joint decoding of multiple speech patterns for robust speech recognition

We are addressing a new problem of improving automatic speech recognition performance, given multiple utterances of patterns from the same class. We have formulated the problem of jointly decoding K multiple patterns given a single Hidden Markov Model. It is shown that such a solution is possible by aligning the K patterns using the proposed Multi Pattern Dynamic Time Warping algorithm followed by the Constrained Multi Pattern Viterbi Algorithm The new formulation is tested in the context of speaker independent isolated word recognition for both clean and noisy patterns. When 10 percent of speech is affected by a burst noise at -5 dB Signal to Noise Ratio (local), it is shown that joint decoding using only two noisy patterns reduces the noisy speech recognition error rate to about 51 percent, when compared to the single pattern decoding using the Viterbi Algorithm. In contrast a simple maximization of individual pattern likelihoods, provides only about 7 percent reduction in error rate.

Service firms´ action upon negative incidents in high touch services: A narrative study

The study concerns service management, and specifically the action service firms take with regard to customer dissatisfaction, customer complaints and complaining customers in high touch services. Customer dissatisfaction, customer complaints and complaining customers are called negative incidents in the study. The study fills a research gap in service management studies by investigating negative incidents as a part of an open service system. In contrast to main stream service management studies defining service quality as how the customer as a consumer defines it, in the present study, the concept of interactive service quality is adopted. The customer is considered as a co-producer of service who thus has a role to play in service quality and productivity. Additionally, the study juxtaposes the often opposed perspectives of the manager and the customer as well as the often forgotten silent voices of service employees and supervisors. The study proposes that the service firm as an entity does not act but it is the actors at the different hierarchical layers who act. Additionally, it is acknowledged in the study that the different actors at the different hierarchical layers have different knowledge of the service system and different objectives for service encounters. Therefore, they interpret the negative incidents from different perspectives and their actions upon negative incidents are subsequently guided by their interpretations. The research question is: how do service firms act upon negative incidents in high touch services? In order to answer to the research question a narrative research approach was chosen. The actors at the different hierarchical layers acted as informants of the study and provided stories about customer dissatisfaction, customer complaining and complaint handling in high touch services. Through storytelling, access to the socially constructed reality of service firms’ action was achieved. Stemming from the literature review, analysis of empirical data and my theoretical thinking, a theory about service firms’ action upon negative incidents in high touch services was developed and the research question was answered. The study contributes to service recovery and complaint management studies as well as to studies on customer orientation and its implementation in service firms. Additionally, the study has a methodological contribution to service management studies since it reflects service firms’ action with narratives from multiple perspectives. The study is positioned in the tradition of the Nordic School of Marketing Thought and presents service firms’ action upon negative incidents in high touch services as a complex human-centered phenomenon in which the actors at the different hierarchical layers have crucial roles to play. Ritva Höykinpuro is associated with CERS, the Centre for Relationship Marketing and Service Management at Hanken School of Economics.

Multi-Pattern Viterbi Algorithm for joint decoding of multiple speech patterns

Joint decoding of multiple speech patterns so as to improve speech recognition performance is important, especially in the presence of noise. In this paper, we propose a Multi-Pattern Viterbi algorithm (MPVA) to jointly decode and recognize multiple speech patterns for automatic speech recognition (ASR). The MPVA is a generalization of the Viterbi Algorithm to jointly decode multiple patterns given a Hidden Markov Model (HMM). Unlike the previously proposed two stage Constrained Multi-Pattern Viterbi Algorithm (CMPVA),the MPVA is a single stage algorithm. MPVA has the advantage that it cart be extended to connected word recognition (CWR) and continuous speech recognition (CSR) problems. MPVA is shown to provide better speech recognition performance than the earlier techniques: using only two repetitions of noisy speech patterns (-5 dB SNR, 10% burst noise), the word error rate using MPVA decreased by 28.5%, when compared to using individual decoding. (C) 2010 Elsevier B.V. All rights reserved.

Comparison of AM-FM Based Features For Robust Speech Recognition

Effective feature extraction for robust speech recognition is a widely addressed topic and currently there is much effort to invoke non-stationary signal models instead of quasi-stationary signal models leading to standard features such as LPC or MFCC. Joint amplitude modulation and frequency modulation (AM-FM) is a classical non-parametric approach to non-stationary signal modeling and recently new feature sets for automatic speech recognition (ASR) have been derived based on a multi-band AM-FM representation of the signal. We consider several of these representations and compare their performances for robust speech recognition in noise, using the AURORA-2 database. We show that FEPSTRUM representation proposed is more effective than others. We also propose an improvement to FEPSTRUM based on the Teager energy operator (TEO) and show that it can selectively outperform even FEPSTRUM

MAST: multi-script annotation toolkit for scenic text

This paper describes a semi-automatic tool for annotation of multi-script text from natural scene images. To our knowledge, this is the maiden tool that deals with multi-script text or arbitrary orientation. The procedure involves manual seed selection followed by a region growing process to segment each word present in the image. The threshold for region growing can be varied by the user so as to ensure pixel-accurate character segmentation. The text present in the image is tagged word-by-word. A virtual keyboard interface has also been designed for entering the ground truth in ten Indic scripts, besides English. The keyboard interface can easily be generated for any script, thereby expanding the scope of the toolkit. Optionally, each segmented word can further be labeled into its constituent characters/symbols. Polygonal masks are used to split or merge the segmented words into valid characters/symbols. The ground truth is represented by a pixel-level segmented image and a '.txt' file that contains information about the number of words in the image, word bounding boxes, script and ground truth Unicode. The toolkit, developed using MATLAB, can be used to generate ground truth and annotation for any generic document image. Thus, it is useful for researchers in the document image processing community for evaluating the performance of document analysis and recognition techniques. The multi-script annotation toolokit (MAST) is available for free download.

Finding hidden females in a crowd: Mate recognition in fig wasps

Multi-species mating aggregations are crowded environments within which mate recognition must occur. Mating aggregations of fig wasps can consist of thousands of individuals of many species that attain sexual maturity simultaneously and mate in the same microenvironment, i.e, in syntopy, within the close confines of an enclosed globular inflorescence called a syconium - a system that has many signalling constraints such as darkness and crowding. All wasps develop within individual galled flowers. Since mating mostly occurs when females are still confined within their galls,, male wasps have the additional burden of detecting conspecific females that are ``hidden'' behind barriers consisting of gall walls. In Ficus racemosa, we investigated signals used by pollinating fig wasp males to differentiate conspecific females from females of other syntopic fig wasp species. Male Ceratosolen fusciceps could detect conspecific females using cues from galls containing females, empty galls, as well as cues from gall volatiles and gall surface hydrocarbons. In many figs, syconia are pollinated by single foundress wasps, leading to high levels of wasp inbreeding due to sibmating. In F. racemosa, as most syconia contain many foundresses, we expected male pollinators to prefer non-sib females to female siblings to reduce inbreeding. We used galls containing females from non-natal figs as a proxy for non-sibs and those from natal figs as a proxy for sibling females. We found that males preferred galls of female pollinators from natal figs. However, males were undecided when given a choice between galls containing non-pollinator females from natal syconia and pollinator females from non-natal syconia, suggesting olfactory imprinting by the natal syconial environment. (C) 2013 Elsevier Masson SAS. All rights reserved.

Spectral Clustering with Jensen-type kernels and their multi-point extensions

Motivated by multi-distribution divergences, which originate in information theory, we propose a notion of `multipoint' kernels, and study their applications. We study a class of kernels based on Jensen type divergences and show that these can be extended to measure similarity among multiple points. We study tensor flattening methods and develop a multi-point (kernel) spectral clustering (MSC) method. We further emphasize on a special case of the proposed kernels, which is a multi-point extension of the linear (dot-product) kernel and show the existence of cubic time tensor flattening algorithm in this case. Finally, we illustrate the usefulness of our contributions using standard data sets and image segmentation tasks.

The Molecular Basis of Lysine Acetylation: Addition, Removal, and Recognition

Acetyltransferases and deacetylases catalyze the addition and removal, respectively, of acetyl groups to the epsilon-amino group of protein lysine residues. This modification can affect the function of a protein through several means, including the recruitment of specific binding partners called acetyl-lysine readers. Acetyltransferases, deacetylases, and acetyl-lysine readers have emerged as crucial regulators of biological processes and prominent targets for the treatment of human disease. This work describes a combination of structural, biochemical, biophysical, cell-biological, and organismal studies undertaken on a set of proteins that cumulatively include all steps of the acetylation process: the acetyltransferase MEC-17, the deacetylase SIRT1, and the acetyl-lysine reader DPF2. Tubulin acetylation by MEC-17 is associated with stable, long-lived microtubule structures. We determined the crystal structure of the catalytic domain of human MEC-17 in complex with the cofactor acetyl-CoA. The structure in combination with an extensive enzymatic analysis of MEC-17 mutants identified residues for cofactor and substrate recognition and activity. A large, evolutionarily conserved hydrophobic surface patch distal to the active site was shown to be necessary for catalysis, suggesting that specificity is achieved by interactions with the alpha-tubulin substrate that extend outside of the modified surface loop. Experiments in C. elegans showed that while MEC-17 is required for touch sensitivity, MEC-17 enzymatic activity is dispensible for this behavior. SIRT1 deacetylates a wide range of substrates, including p53, NF-kappaB, FOXO transcription factors, and PGC-1-alpha, with roles in cellular processes ranging from energy metabolism to cell survival. SIRT1 activity is uniquely controlled by a C-terminal regulatory segment (CTR). Here we present crystal structures of the catalytic domain of human SIRT1 in complex with the CTR in an apo form and in complex with a cofactor and a pseudo-substrate peptide. The catalytic domain adopts the canonical sirtuin fold. The CTR forms a beta-hairpin structure that complements the beta-sheet of the NAD^+-binding domain, covering an essentially invariant, hydrophobic surface. A comparison of the apo and cofactor bound structures revealed conformational changes throughout catalysis, including a rotation of a smaller subdomain with respect to the larger NAD^+-binding subdomain. A biochemical analysis identified key residues in the active site, an inhibitory role for the CTR, and distinct structural features of the CTR that mediate binding and inhibition of the SIRT1 catalytic domain. DPF2 represses myeloid differentiation in acute myelogenous leukemia. Finally, we solved the crystal structure of the tandem PHD domain of human DPF2. We showed that DPF2 preferentially binds H3 tail peptides acetylated at Lys14, and binds H4 tail peptides with no preference for acetylation state. Through a structural and mutational analysis we identify the molecular basis of histone recognition. We propose a model for the role of DPF2 in AML and identify the DPF2 tandem PHD finger domain as a promising novel target for anti-leukemia therapeutics.

Modified Kanerva model. Results for real time word recognition

This paper describes results obtained using the modified Kanerva model to perform word recognition in continuous speech after being trained on the multi-speaker Alvey 'Hotel' speech corpus. Theoretical discoveries have recently enabled us to increase the speed of execution of part of the model by two orders of magnitude over that previously reported by Prager & Fallside. The memory required for the operation of the model has been similarly reduced. The recognition accuracy reaches 95% without syntactic constraints when tested on different data from seven trained speakers. Real time simulation of a model with 9,734 active units is now possible in both training and recognition modes using the Alvey PARSIFAL transputer array. The modified Kanerva model is a static network consisting of a fixed nonlinear mapping (location matching) followed by a single layer of conventional adaptive links. A section of preprocessed speech is transformed by the non-linear mapping to a high dimensional representation. From this intermediate representation a simple linear mapping is able to perform complex pattern discrimination to form the output, indicating the nature of the speech features present in the input window.

The modified Kanerva model for automatic speech recognition

A parallel processing network derived from Kanerva's associative memory theory Kanerva 1984 is shown to be able to train rapidly on connected speech data and recognize further speech data with a label error rate of 0·68%. This modified Kanerva model can be trained substantially faster than other networks with comparable pattern discrimination properties. Kanerva presented his theory of a self-propagating search in 1984, and showed theoretically that large-scale versions of his model would have powerful pattern matching properties. This paper describes how the design for the modified Kanerva model is derived from Kanerva's original theory. Several designs are tested to discover which form may be implemented fastest while still maintaining versatile recognition performance. A method is developed to deal with the time varying nature of the speech signal by recognizing static patterns together with a fixed quantity of contextual information. In order to recognize speech features in different contexts it is necessary for a network to be able to model disjoint pattern classes. This type of modelling cannot be performed by a single layer of links. Network research was once held back by the inability of single-layer networks to solve this sort of problem, and the lack of a training algorithm for multi-layer networks. Rumelhart, Hinton & Williams 1985 provided one solution by demonstrating the "back propagation" training algorithm for multi-layer networks. A second alternative is used in the modified Kanerva model. A non-linear fixed transformation maps the pattern space into a space of higher dimensionality in which the speech features are linearly separable. A single-layer network may then be used to perform the recognition. The advantage of this solution over the other using multi-layer networks lies in the greater power and speed of the single-layer network training algorithm. © 1989.

Biologically-inspired object recognition system with features from complex wavelets

In this paper, a novel cortex-inspired feed-forward hierarchical object recognition system based on complex wavelets is proposed and tested. Complex wavelets contain three key properties for object representation: shift invariance, which enables the extraction of stable local features; good directional selectivity, which simplifies the determination of image orientations; and limited redundancy, which allows for efficient signal analysis using the multi-resolution decomposition offered by complex wavelets. In this paper, we propose a complete cortex-inspired object recognition system based on complex wavelets. We find that the implementation of the HMAX model for object recognition in [1, 2] is rather over-complete and includes too much redundant information and processing. We have optimized the structure of the model to make it more efficient. Specifically, we have used the Caltech 5 standard dataset to compare with Serre's model in [2] (which employs Gabor filter bands). Results demonstrate that the complex wavelet model achieves a speed improvement of about 4 times over the Serre model and gives comparable recognition performance. © 2011 IEEE.