Automated Transcription System for Malayalam Language

Malayalam is one of the 22 scheduled languages in India with more than 130 million speakers. This paper presents a report on the development of a speaker independent, continuous transcription system for Malayalam. The system employs Hidden Markov Model (HMM) for acoustic modeling and Mel Frequency Cepstral Coefficient (MFCC) for feature extraction. It is trained with 21 male and female speakers in the age group ranging from 20 to 40 years. The system obtained a word recognition accuracy of 87.4% and a sentence recognition accuracy of 84%, when tested with a set of continuous speech data.

Malayalam Isolated Digit Recognition using HMM and PLP cepstral coefficient

Development of Malayalam speech recognition system is in its infancy stage; although many works have been done in other Indian languages. In this paper we present the first work on speaker independent Malayalam isolated speech recognizer based on PLP (Perceptual Linear Predictive) Cepstral Coefficient and Hidden Markov Model (HMM). The performance of the developed system has been evaluated with different number of states of HMM (Hidden Markov Model). The system is trained with 21 male and female speakers in the age group ranging from 19 to 41 years. The system obtained an accuracy of 99.5% with the unseen data

Connected digit speech recognition system for Malayalam language

A connected digit speech recognition is important in many applications such as automated banking system, catalogue-dialing, automatic data entry, automated banking system, etc. This paper presents an optimum speaker-independent connected digit recognizer forMalayalam language. The system employs Perceptual Linear Predictive (PLP) cepstral coefficient for speech parameterization and continuous density Hidden Markov Model (HMM) in the recognition process. Viterbi algorithm is used for decoding. The training data base has the utterance of 21 speakers from the age group of 20 to 40 years and the sound is recorded in the normal office environment where each speaker is asked to read 20 set of continuous digits. The system obtained an accuracy of 99.5 % with the unseen data.

Surface Reflectance Recognition and Real-World Illumination Statistics

Humans distinguish materials such as metal, plastic, and paper effortlessly at a glance. Traditional computer vision systems cannot solve this problem at all. Recognizing surface reflectance properties from a single photograph is difficult because the observed image depends heavily on the amount of light incident from every direction. A mirrored sphere, for example, produces a different image in every environment. To make matters worse, two surfaces with different reflectance properties could produce identical images. The mirrored sphere simply reflects its surroundings, so in the right artificial setting, it could mimic the appearance of a matte ping-pong ball. Yet, humans possess an intuitive sense of what materials typically "look like" in the real world. This thesis develops computational algorithms with a similar ability to recognize reflectance properties from photographs under unknown, real-world illumination conditions. Real-world illumination is complex, with light typically incident on a surface from every direction. We find, however, that real-world illumination patterns are not arbitrary. They exhibit highly predictable spatial structure, which we describe largely in the wavelet domain. Although they differ in several respects from the typical photographs, illumination patterns share much of the regularity described in the natural image statistics literature. These properties of real-world illumination lead to predictable image statistics for a surface with given reflectance properties. We construct a system that classifies a surface according to its reflectance from a single photograph under unknown illuminination. Our algorithm learns relationships between surface reflectance and certain statistics computed from the observed image. Like the human visual system, we solve the otherwise underconstrained inverse problem of reflectance estimation by taking advantage of the statistical regularity of illumination. For surfaces with homogeneous reflectance properties and known geometry, our system rivals human performance.

Computational Models of Object Recognition in Cortex: A Review

Understanding how biological visual systems perform object recognition is one of the ultimate goals in computational neuroscience. Among the biological models of recognition the main distinctions are between feedforward and feedback and between object-centered and view-centered. From a computational viewpoint the different recognition tasks - for instance categorization and identification - are very similar, representing different trade-offs between specificity and invariance. Thus the different tasks do not strictly require different classes of models. The focus of the review is on feedforward, view-based models that are supported by psychophysical and physiological data.

WAIS Seminar:Modelling the Web: Examples of modelling language, network evolution and physical-social systems

Speaker(s): Prof. Steffen Staab Organiser: Dr Tim Chown Time: 23/05/2014 10:30-11:30 Location: B53/4025 Abstract The Web is constructed based on our experiences in a multitude of modalities: text, networks, images, physical locations are some examples. Understanding the Web requires from us that we can model these modalities as they appear on the Web. In this talk I will show some examples of how we model text, hyperlink networks and physical-social systems in order to improve our understanding and our use of the Web.

Mediating between hearer's and speaker's views in the generation of adaptive explanations

In this article, we examine the case of a system that cooperates with a “direct” user to plan an activity that some “indirect” user, not interacting with the system, should perform. The specific application we consider is the prescription of drugs. In this case, the direct user is the prescriber and the indirect user is the person who is responsible for performing the therapy. Relevant characteristics of the two users are represented in two user models. Explanation strategies are represented in planning operators whose preconditions encode the cognitive state of the indirect user; this allows tailoring the message to the indirect user's characteristics. Expansion of optional subgoals and selection among candidate operators is made by applying decision criteria represented as metarules, that negotiate between direct and indirect users' views also taking into account the context where explanation is provided. After the message has been generated, the direct user may ask to add or remove some items, or change the message style. The system defends the indirect user's needs as far as possible by mentioning the rationale behind the generated message. If needed, the plan is repaired and the direct user model is revised accordingly, so that the system learns progressively to generate messages suited to the preferences of people with whom it interacts.

A direct comparison of one- and two-component dendritic self-assembled materials: elucidating molecular recognition pathways

This paper compares and contrasts, for the first time, one- and two-component gelation systems that are direct structural analogues and draws conclusions about the molecular recognition pathways that underpin fibrillar self-assembly. The new one-component systems comprise L-lysine-based dendritic headgroups covalently connected to an aliphatic diamine spacer chain via an amide bond, One-component gelators with different generations of headgroup (from first to third generation) and different length spacer chains are reported. The self-assembly of these dendrimers in toluene was elucidated using thermal measurements, circular dichroism (CD) and NMR spectroscopies, scanning electron microscopy (SEM), and small-angle X-ray scattering (SAXS). The observations are compared with previous results for the analogous two-component gelation system in which the dendritic headgroups are bound to the aliphatic spacer chain noncovalently via acid-amine interactions. The one-component system is inherently a more effective gelator, partly as a consequence of the additional covalent amide groups that provide a new hydrogen bonding molecular recognition pathway, whereas the two-component analogue relies solely on intermolecular hydrogen bond interactions between the chiral dendritic headgroups. Furthermore, because these amide groups are important in the assembly process for the one-component system, the chiral information preset in the dendritic headgroups is not always transcribed into the nanoscale assembly, whereas for the two-component system, fiber formation is always accompanied by chiral ordering because the molecular recognition pathway is completely dependent on hydrogen bond interactions between well-organized chiral dendritic headgroups.

Ditopic redox-active polyferrocenyl zinc(II) dithiocarbamate macrocyclic receptors: synthesis, coordination and electrochemical recognition properties

The synthesis of a range of ditopic polyferrocenyl zinc(II) dithiocarbamate macrocyclic receptors containing ferrocene groups on the macrocycle's periphery and/or as part of the cyclic cavity is reported. The assemblies have been characterised by a range of spectroscopic techniques, electrochemical studies and in two cases by X-ray structure determination. The ability of these host systems to bind and sense electrochemically anionic guest species, isonicotinate and benzoate, and neutral 4-picoline guest was examined by H-1 NMR and cyclic voltammetric titration studies. The strongest association was found between the isonicotinate anion and a dinuclear zinc(II) receptor whose macrocyclic cavity is of complementary size to complex this bidentate guest species in a cooperative manner. Cyclic voltammetric studies demonstrated that all receptors can electrochemically sense the binding of isonicotinate and benzoate via significant cathodic perturbations of the respective ferrocene redox couple.

Incorporating HACCP into national food control systems - Analyzing progress in the United Arab Emirates

Today governments and other parties involved in food control are under constant pressure to find more efficient and effective mechanisms to carry out their mandates for food control. This has led to international recognition of the importance of the HACCP system as a food control tool and guidance on the role of government agencies in the application of such a system has been developed. Based on this international guidance, four main elements identified as key activities have been used in this study to evaluate the progress of HACCP implementation in the UAE. The internal Strengths and Weaknesses, as well as the external Opportunities and Threats that the government is facing towards the implementation of a HACCP-based food control system have been identified. The analysis shows that the government’s dedicated role has been an essential driving force to encourage the implementation of a HACCP-based food control system. Some areas of difficulty, including the dependence on high levels of food imports, are highlighted.

Simulation of the future performance of low-energy evaporative cooling systems using UKCP09 climate projections

Recent activity in the development of future weather data for building performance simulation follows recognition of the limitations of traditional methods, which have been based on a stationary (observed) climate. In the UK, such developments have followed on from the availability of regional climate models as delivered in UKCIP02 and recently the probabilistic projections released under UKCP09. One major area of concern is the future performance and adaptability of buildings which employ exclusively passive or low-energy cooling systems. One such method which can be employed in an integral or retrofit situation is direct or indirect evaporative cooling. The effectiveness of evaporative cooling is most strongly influenced by the wet-bulb depression of the ambient air, hence is generally regarded as most suited to hot, dry climates. However, this technology has been shown to be effective in the UK, primarily in mixed-mode buildings or as a retrofit to industrial/commercial applications. Climate projections for the UK generally indicate an increase in the summer wet-bulb depression, suggesting an enhanced potential for the application of evaporative cooling. The paper illustrates this potential by an analysis of the probabilistic scenarios released under UKCP09, together with a detailed building/plant simulation of case study building located in the South-East of England. The results indicate a high probability that evaporative cooling will still be a viable low-energy technique in the 2050s.

Inferring the biggest and best: a measurement model for applying recognition to evoke consideration sets and judge between multiple alternatives

It has long been supposed that preference judgments between sets of to-be-considered possibilities are made by means of initially winnowing down the most promising-looking alternatives to form smaller “consideration sets” (Howard, 1963; Wright & Barbour, 1977). In preference choices with >2 options, it is standard to assume that a “consideration set”, based upon some simple criterion, is established to reduce the options available. Inferential judgments, in contrast, have more frequently been investigated in situations in which only two possibilities need to be considered (e.g., which of these two cities is the larger?) Proponents of the “fast and frugal” approach to decision-making suggest that such judgments are also made on the basis of limited, simple criteria. For example, if only one of two cities is recognized and the task is to judge which city has the larger population, the recognition heuristic states that the recognized city should be selected. A multinomial processing tree model is outlined which provides the basis for estimating the extent to which recognition is used as a criterion in establishing a consideration set for inferential judgments between three possible options.

Anion recognition and transport properties of sulfamide-, phosphoric triamide- and thiophosphoric triamide-based receptors

Studies of sulfamide, phosphoric triamide and thiophosphoric triamidebased organocatalysts show that the phosphorus containing systems are effective new hydrogen bonding motifs for the recognition and transport of anions.

Segmentation-level fusion for iris recognition

This paper investigates the potential of fusion at normalisation/segmentation level prior to feature extraction. While there are several biometric fusion methods at data/feature level, score level and rank/decision level combining raw biometric signals, scores, or ranks/decisions, this type of fusion is still in its infancy. However, the increasing demand to allow for more relaxed and less invasive recording conditions, especially for on-the-move iris recognition, suggests to further investigate fusion at this very low level. This paper focuses on the approach of multi-segmentation fusion for iris biometric systems investigating the benefit of combining the segmentation result of multiple normalisation algorithms, using four methods from two different public iris toolkits (USIT, OSIRIS) on the public CASIA and IITD iris datasets. Evaluations based on recognition accuracy and ground truth segmentation data indicate high sensitivity with regards to the type of errors made by segmentation algorithms.