A comparative study of speaker adaptation methods

For the problem of speaker adaptation in speech recognition, the performance depends on the availability of adaptation data. In this paper, we have compared several existing speaker adaptation methods, viz. maximum likelihood linear regression (MLLR), eigenvoice (EV), eigenspace-based MLLR (EMLLR), segmental eigenvoice (SEV) and hierarchical eigenvoice (HEV) based methods. We also develop a new method by modifying the existing HEV method for achieving further performance improvement in a limited available data scenario. In the sense of availability of adaptation data, the new modified HEV (MHEV) method is shown to perform better than all the existing methods throughout the range of operation except the case of MLLR at the availability of more adaptation data.

Implementation of placement and routing algorithms for computer aided design of printed circuit boards

The Printed Circuit Board (PCB) layout design is one of the most important and time consuming phases during equipment design process in all electronic industries. This paper is concerned with the development and implementation of a computer aided PCB design package. A set of programs which operate on a description of the circuit supplied by the user in the form of a data file and subsequently design the layout of a double-sided PCB has been developed. The algorithms used for the design of the PCB optimise the board area and the length of copper tracks used for the interconnections. The output of the package is the layout drawing of the PCB, drawn on a CALCOMP hard copy plotter and a Tektronix 4012 storage graphics display terminal. The routing density (the board area required for one component) achieved by this package is typically 0.8 sq. inch per IC. The package is implemented on a DEC 1090 system in Pascal and FORTRAN and SIGN(1) graphics package is used for display generation.

Design of speaker identification schemes for large number of speakers (A)

Design of speaker identification schemes for a small number of speakers (around 10) with a high degree of accuracy in controlled environment is a practical proposition today. When the number of speakers is large (say 50–100), many of these schemes cannot be directly extended, as both recognition error and computation time increase monotonically with population size. The feature selection problem is also complex for such schemes. Though there were earlier attempts to rank order features based on statistical distance measures, it has been observed only recently that the best two independent measurements are not the same as the combination in two's for pattern classification. We propose here a systematic approach to the problem using the decision tree or hierarchical classifier with the following objectives: (1) Design of optimal policy at each node of the tree given the tree structure i.e., the tree skeleton and the features to be used at each node. (2) Determination of the optimal feature measurement and decision policy given only the tree skeleton. Applicability of optimization procedures such as dynamic programming in the design of such trees is studied. The experimental results deal with the design of a 50 speaker identification scheme based on this approach.

Machine recognition of printed Kannada text

This paper presents the design of a full fledged OCR system for printed Kannada text. The machine recognition of Kannada characters is difficult due to similarity in the shapes of different characters, script complexity and non-uniqueness in the representation of diacritics. The document image is subject to line segmentation, word segmentation and zone detection. From the zonal information, base characters, vowel modifiers and consonant conjucts are separated. Knowledge based approach is employed for recognizing the base characters. Various features are employed for recognising the characters. These include the coefficients of the Discrete Cosine Transform, Discrete Wavelet Transform and Karhunen-Louve Transform. These features are fed to different classifiers. Structural features are used in the subsequent levels to discriminate confused characters. Use of structural features, increases recognition rate from 93% to 98%. Apart from the classical pattern classification technique of nearest neighbour, Artificial Neural Network (ANN) based classifiers like Back Propogation and Radial Basis Function (RBF) Networks have also been studied. The ANN classifiers are trained in supervised mode using the transform features. Highest recognition rate of 99% is obtained with RBF using second level approximation coefficients of Haar wavelets as the features on presegmented base characters.

Font and Size Independent OCR for Printed Kannada Documents using SVM Classifiers

The following topics were dealt with: document analysis and recognition; multimedia document processing; character recognition; document image processing; cheque processing; form processing; music processing; document segmentation; electronic documents; character classification; handwritten character recognition; information retrieval; postal automation; font recognition; Indian language OCR; handwriting recognition; performance evaluation; graphics recognition; oriental character recognition; and word recognition

Titania nanotube-modified screen printed carbon electrodes enhance the sensitivity in the electrochemical detection of proteins

The use of titania nanotubes (TiO2-NT) as the working electrode provides a substantial improvement in the electrochemical detection of proteins. A biosensor designed using this strategy provided a robust method to detect protein samples at very low concentrations (C-protein ca 1 ng/mu l). Reproducible measurements on protein samples at this concentration (I-p,I-a of 80 +/- 1.2 mu A) could be achieved using a sample volume of ca 30 mu l. We demonstrate the feasibility of this strategy for the accurate detection of penicillin binding protein, PBP2a, a marker for methicillin resistant Staphylococcus aureus (MRSA). The selectivity and efficiency of this sensor were also validated using other diverse protein preparations such as a recombinant protein tyrosine phosphatase (PTP10D) and bovine serum albumin (BSA). This electrochemical method also presents a substantial improvement in the time taken (few minutes) when compared to conventional enzyme-linked immunosorbent assay (ELISA) protocols. It is envisaged that this sensor could substantially aid in the rapid diagnosis of bacterial infections in resource strapped environments. (C) 2014 Elsevier B.V. All rights reserved.

Voice source characterization using pitch synchronous discrete cosine transform for speaker identification

A characterization of the voice source (VS) signal by the pitch synchronous (PS) discrete cosine transform (DCT) is proposed. With the integrated linear prediction residual (ILPR) as the VS estimate, the PS DCT of the ILPR is evaluated as a feature vector for speaker identification (SID). On TIMIT and YOHO databases, using a Gaussian mixture model (GMM)-based classifier, it performs on par with existing VS-based features. On the NIST 2003 database, fusion with a GMM-based classifier using MFCC features improves the identification accuracy by 12% in absolute terms, proving that the proposed characterization has good promise as a feature for SID studies. (C) 2015 Acoustical Society of America

Speaker verification based on the fusion of speech acoustics and inverted articulatory signals

We propose apractical, feature-level and score-level fusion approach by combining acoustic and estimated articulatory information for both text independent and text dependent speaker verification. From a practical point of view, we study how to improve speaker verification performance by combining dynamic articulatory information with the conventional acoustic features. On text independent speaker verification, we find that concatenating articulatory features obtained from measured speech production data with conventional Mel-frequency cepstral coefficients (MFCCs) improves the performance dramatically. However, since directly measuring articulatory data is not feasible in many real world applications, we also experiment with estimated articulatory features obtained through acoustic-to-articulatory inversion. We explore both feature level and score level fusion methods and find that the overall system performance is significantly enhanced even with estimated articulatory features. Such a performance boost could be due to the inter-speaker variation information embedded in the estimated articulatory features. Since the dynamics of articulation contain important information, we included inverted articulatory trajectories in text dependent speaker verification. We demonstrate that the articulatory constraints introduced by inverted articulatory features help to reject wrong password trials and improve the performance after score level fusion. We evaluate the proposed methods on the X-ray Microbeam database and the RSR 2015 database, respectively, for the aforementioned two tasks. Experimental results show that we achieve more than 15% relative equal error rate reduction for both speaker verification tasks. (C) 2015 Elsevier Ltd. All rights reserved.

Strength reliability and in vitro degradation of three-dimensional powder printed strontium-substituted magnesium phosphate scaffolds

Strontium ions (Sr2+) are known to prevent osteoporosis and also encourage bone formation. Such twin requirements have motivated researchers to develop Sr-substituted biomaterials for orthopaedic applications. The present study demonstrates a new concept of developing Sr-substituted Mg-3(PO4)(2) - based biodegradable scaffolds. In particular, this work reports the fabrication, mechanical properties with an emphasis on strength reliability as well as in vitro degradation of highly biodegradable strontium-incorporated magnesium phosphate cements. These implantable scaffolds were fabricated using three-dimensional powder printing, followed by high temperature sintering and/or chemical conversion, a technique adaptable to develop patient-specific implants. A moderate combination of strength properties of 36.7 MPa (compression), 242 MPa (bending) and 10.7 MPa (tension) were measured. A reasonably modest Weibull modulus of up to 8.8 was recorded after uniaxial compression or diametral tensile tests on 3D printed scaffolds. A comparison among scaffolds with varying compositions or among sintered or chemically hardened scaffolds reveals that the strength reliability is not compromised in Sr-substituted scaffolds compared to baseline Mg-3(PO4)(2). The micro-computed tomography analysis reveals the presence of highly interconnected porous architecture in three-dimension with lognormal pore size distribution having median in the range of 17.74-26.29 mu m for the investigated scaffolds. The results of extensive in vitro ion release study revealed passive degradation with a reduced Mg2+ release and slow but sustained release of Sr2+ from strontium-substituted magnesium phosphate scaffolds. Taken together, the present study unequivocally illustrates that the newly designed Sr-substituted magnesium phosphate scaffolds with good strength reliability could be used for biomedical applications requiring consistent Sr2+-release, while the scaffold degrades in physiological medium. Statement of significance The study investigates the additive manufacturing of scaffolds based on different strontium-substituted magnesium phosphate bone cements by means of three-dimensional powder printing technique (3DPP). Magnesium phosphates were chosen due to their higher biodegradability compared to calcium phosphates, which is due to both a higher solubility as well as the absence of phase changes (to low soluble hydroxyapatite) in vivo. Since strontium ions are known to promote bone formation by stimulating osteoblast growth, we aimed to establish such a highly degradable magnesium phosphate ceramic with an enhanced bioactivity for new bone ingrowth. After post-processing, mechanical strengths of up to 36.7 MPa (compression), 24.2 MPa (bending) and 10.7 MPa (tension) could be achieved. Simultaneously, the failure reliability of those bioceramic implant materials, measured by Weibull modulus calculations, were in the range of 4.3-8.8. Passive dissolution studies in vitro proved an ion release of Mg2+ and PO43- as well as Sr2+, which is fundamental for in vivo degradation and a bone growth promoting effect. In our opinion, this work broadens the range of bioceramic bone replacement materials suitable for additive manufacturing processing. The high biodegradability of MPC ceramics together with the anticipated promoting effect on osseointegration opens up the way for a patient-specific treatment with the prospect of a fast and complete healing of bone fractures. (C) 2015 Acta Materialia Inc. Published by Elsevier Ltd. All rights reserved.

Studies on Carbon Mediated Paste Screen Printed Sensors for Blood Glucose Sensing Application

Ready-to-use screen printed glucose sensors are fabricated using Prussian Blue (PB) and Cobalt Phthalocyanine (CoPC) mediated carbon inks as working electrodes. The reference and counter electrodes are screen printed using silver/silver chloride and graphitic carbon paste respectively. The screen printed reference electrodes (internal reference electrode (IRE)) are found to be stable for more than 60 minutes when examined with saturated calomel electrode. Optimal operating voltage for PB and CoPC screen printed sensors are determined by hydrodynamic voltammetric technique. Glucose oxidase is immobilized on the working electrodes by cross-linking method. PB mediated glucose sensor exhibits a sensitivity of 5.60 mA cm(-2)/mM for the range, 10 to 1000 mu M. Sensitivity of CoPC mediated glucose sensor is found to be 5.224 mu A cm(-2)/mM and amperometeric response is linear for the range, 100 to 1500 mu M. Interference studies on the fabricated glucose sensors are conducted with species like uric acid and ascorbic acid. PB mediated sensors showed a completely interference-free behavior. The sensing characteristics of PB mediated glucose sensors are also studied in diluted human serum samples and the results are compared with the values obtained through standard clinical method. The co-efficient of variation is found to be less than 5%. (C) 2015 The Electrochemical Society. All rights reserved.