Mesh Processing for Computerized Facial Anthropometry

Understanding of the shape and size of different features of the human body from scanned data is necessary for automated design and evaluation of product ergonomics. In this paper, a computational framework is presented for automatic detection and recognition of important facial feature regions, from scanned head and shoulder polyhedral models. A noise tolerant methodology is proposed using discrete curvature computations, band-pass filtering, and morphological operations for isolation of the primary feature regions of the face, namely, the eyes, nose, and mouth. Spatial disposition of the critical points of these isolated feature regions is analyzed for the recognition of these critical points as the standard landmarks associated with the primary facial features. A number of clinically identified landmarks lie on the facial midline. An efficient algorithm for detection and processing of the midline, using a point sampling technique, is also presented. The results obtained using data of more than 20 subjects are verified through visualization and physical measurements. A color based and triangle skewness based schemes for isolation of geometrically nonprominent features and ear region are also presented. [DOI: 10.1115/1.3330420]

Multi Pattern Dynamic Time Warping For Automatic Speech Recognition

We are addressing the problem of jointly using multiple noisy speech patterns for automatic speech recognition (ASR), given that they come from the same class. If the user utters a word K times, the ASR system should try to use the information content in all the K patterns of the word simultaneously and improve its speech recognition accuracy compared to that of the single pattern based speech recognition. T address this problem, recently we proposed a Multi Pattern Dynamic Time Warping (MPDTW) algorithm to align the K patterns by finding the least distortion path between them. A Constrained Multi Pattern Viterbi algorithm was used on this aligned path for isolated word recognition (IWR). In this paper, we explore the possibility of using only the MPDTW algorithm for IWR. We also study the properties of the MPDTW algorithm. We show that using only 2 noisy test patterns (10 percent burst noise at -5 dB SNR) reduces the noisy speech recognition error rate by 37.66 percent when compared to the single pattern recognition using the Dynamic Time Warping algorithm.

Automatic Recognition of Facial Features and Landmarking of Digital Human Head

Ergonomic design of products demands accurate human dimensions-anthropometric data. Manual measurement over live subjects, has several limitations like long time, required presence of subjects for every new measurement, physical contact etc. Hence the data currently available is limited and anthropometric data related to facial features is difficult to obtain. In this paper, we discuss a methodology to automatically detect facial features and landmarks from scanned human head models. Segmentation of face into meaningful patches corresponding to facial features is achieved by Watershed algorithms and Mathematical Morphology tools. Many Important physiognomical landmarks are identified heuristically.

A Pattern Recognition Model of Voice-Based Personal Verification Systems for Forensic Applications

Abstract-The success of automatic speaker recognition in laboratory environments suggests applications in forensic science for establishing the Identity of individuals on the basis of features extracted from speech. A theoretical model for such a verification scheme for continuous normaliy distributed featureIss developed. The three cases of using a) single feature, b)multipliendependent measurements of a single feature, and c)multpleindependent features are explored.The number iofndependent features needed for areliable personal identification is computed based on the theoretcal model and an expklatory study of some speech featues.

Joint evaluation of multiple speech patterns for speech recognition and training

We are addressing the novel problem of jointly evaluating multiple speech patterns for automatic speech recognition and training. We propose solutions based on both the non-parametric dynamic time warping (DTW) algorithm, and the parametric hidden Markov model (HMM). We show that a hybrid approach is quite effective for the application of noisy speech recognition. We extend the concept to HMM training wherein some patterns may be noisy or distorted. Utilizing the concept of ``virtual pattern'' developed for joint evaluation, we propose selective iterative training of HMMs. Evaluating these algorithms for burst/transient noisy speech and isolated word recognition, significant improvement in recognition accuracy is obtained using the new algorithms over those which do not utilize the joint evaluation strategy.

Distress call-induced gene expression in the brain of the Indian short-nosed fruit bat, Cynopterus sphinx

Individuals in distress emit audible vocalizations to either warn or inform conspecifics. The Indian short-nosed fruit bat, Cynopterus sphinx, emits distress calls soon after becoming entangled in mist nets, which appear to attract conspecifics. Phase I of these distress calls is longer and louder, and includes a secondary peak, compared to phase II. Activity-dependent expression of egr-1 was examined in free-ranging C. sphinx following the emissions and responses to a distress call. We found that the level of expression of egr-1 was higher in bats that emitted a distress call, in adults that responded, and in pups than in silent bats. Up-regulated cDNA was amplified to identify the target gene (TOE1) of the protein Egr-1. The observed expression pattern Toe1 was similar to that of egr-1. These findings suggest that the neuronal activity related to recognition of a distress call and an auditory feedback mechanism induces the expression of Egr-1. Co-expression of egr-1 with Toe1 may play a role in initial triggering of the genetic mechanism that could be involved in the consolidation or stabilization of distress call memories.

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.

Machine recognition of online handwritten Devanagari characters

In this paper, we describe a system for the automatic recognition of isolated handwritten Devanagari characters obtained by linearizing consonant conjuncts. Owing to the large number of characters and resulting demands on data acquisition, we use structural recognition techniques to reduce some characters to others. The residual characters are then classified using the subspace method. Finally the results of structural recognition and feature-based matching are mapped to give final output. The proposed system Ifs evaluated for the writer dependent scenario.

Automatic text block separation in document images

Separation of printed text blocks from the non-text areas, containing signatures, handwritten text, logos and other such symbols, is a necessary first step for an OCR involving printed text recognition. In the present work, we compare the efficacy of some feature-classifier combinations to carry out this separation task. We have selected length-nomalized horizontal projection profile (HPP) as the starting point of such a separation task. This is with the assumption that the printed text blocks contain lines of text which generate HPP's with some regularity. Such an assumption is demonstrated to be valid. Our features are the HPP and its two transformed versions, namely, eigen and Fisher profiles. Four well known classifiers, namely, Nearest neighbor, Linear discriminant function, SVM's and artificial neural networks have been considered and efficiency of the combination of these classifiers with the above features is compared. A sequential floating feature selection technique has been adopted to enhance the efficiency of this separation task. The results give an average accuracy of about 96.

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

Language identification using parallel sub-word recognition

Parallel sub-word recognition (PSWR) is a new model that has been proposed for language identification (LID) which does not need elaborate phonetic labeling of the speech data in a foreign language. The new approach performs a front-end tokenization in terms of sub-word units which are designed by automatic segmentation, segment clustering and segment HMM modeling. We develop PSWR based LID in a framework similar to the parallel phone recognition (PPR) approach in the literature. This includes a front-end tokenizer and a back-end language model, for each language to be identified. Considering various combinations of the statistical evaluation scores, it is found that PSWR can perform as well as PPR, even with broad acoustic sub-word tokenization, thus making it an efficient alternative to the PPR system.

Call intensity is a repeatable and dominant acoustic feature determining male call attractiveness in a field cricket

Acoustic signal variation and female preference for different signal components constitute the prerequisite framework to study the mechanisms of sexual selection that shape acoustic communication. Despite several studies of acoustic communication in crickets, information on both male calling song variation in the field and female preference in the same system is lacking for most species. Previous studies on acoustic signal variation either were carried out on populations maintained in the laboratory or did not investigate signal repeatability. We therefore used repeatability analysis to quantify variation in the spectral, temporal and amplitudinal characteristics of the male calling song of the field cricket Plebeiogryllus guttiventris in a wild population, at two temporal scales, within and across nights. Carrier frequency (CF) was the most repeatable character across nights, whereas chirp period (CP) had low repeatability across nights. We investigated whether female preferences were more likely to be based on features with high (CF) or low (CP) repeatability. Females showed no consistent preferences for CF but were significantly more attracted towards signals with short CPs. The attractiveness of lower CP calls disappeared, however, when traded off with sound pressure level (SPL). SPL was the only acoustic feature that was significantly positively correlated with male body size. Since relative SPL affects female phonotaxis strongly and can vary unpredictably based on male spacing, our results suggest that even strong female preferences for acoustic features may not necessarily translate into greater advantage for males possessing these features in the field. (C) 2013 The Association for the Study of Animal Behaviour. Published by Elsevier Ltd. All rights reserved.

Automatic Data Allocation and Buffer Management for Multi-GPU Machines

Multi-GPU machines are being increasingly used in high-performance computing. Each GPU in such a machine has its own memory and does not share the address space either with the host CPU or other GPUs. Hence, applications utilizing multiple GPUs have to manually allocate and manage data on each GPU. Existing works that propose to automate data allocations for GPUs have limitations and inefficiencies in terms of allocation sizes, exploiting reuse, transfer costs, and scalability. We propose a scalable and fully automatic data allocation and buffer management scheme for affine loop nests on multi-GPU machines. We call it the Bounding-Box-based Memory Manager (BBMM). BBMM can perform at runtime, during standard set operations like union, intersection, and difference, finding subset and superset relations on hyperrectangular regions of array data (bounding boxes). It uses these operations along with some compiler assistance to identify, allocate, and manage data required by applications in terms of disjoint bounding boxes. This allows it to (1) allocate exactly or nearly as much data as is required by computations running on each GPU, (2) efficiently track buffer allocations and hence maximize data reuse across tiles and minimize data transfer overhead, and (3) and as a result, maximize utilization of the combined memory on multi-GPU machines. BBMM can work with any choice of parallelizing transformations, computation placement, and scheduling schemes, whether static or dynamic. Experiments run on a four-GPU machine with various scientific programs showed that BBMM reduces data allocations on each GPU by up to 75% compared to current allocation schemes, yields performance of at least 88% of manually written code, and allows excellent weak scaling.

Automatic Tonic Identification in Indian Art Music: Approaches and Evaluation

The tonic is a fundamental concept in Indian art music. It is the base pitch, which an artist chooses in order to construct the melodies during a rg(a) rendition, and all accompanying instruments are tuned using the tonic pitch. Consequently, tonic identification is a fundamental task for most computational analyses of Indian art music, such as intonation analysis, melodic motif analysis and rg recognition. In this paper we review existing approaches for tonic identification in Indian art music and evaluate them on six diverse datasets for a thorough comparison and analysis. We study the performance of each method in different contexts such as the presence/absence of additional metadata, the quality of audio data, the duration of audio data, music tradition (Hindustani/Carnatic) and the gender of the singer (male/female). We show that the approaches that combine multi-pitch analysis with machine learning provide the best performance in most cases (90% identification accuracy on average), and are robust across the aforementioned contexts compared to the approaches based on expert knowledge. In addition, we also show that the performance of the latter can be improved when additional metadata is available to further constrain the problem. Finally, we present a detailed error analysis of each method, providing further insights into the advantages and limitations of the methods.

A mode-shape classification technique for robust speech rate estimation and syllable nuclei detection

Acoustic feature based speech (syllable) rate estimation and syllable nuclei detection are important problems in automatic speech recognition (ASR), computer assisted language learning (CALL) and fluency analysis. A typical solution for both the problems consists of two stages. The first stage involves computing a short-time feature contour such that most of the peaks of the contour correspond to the syllabic nuclei. In the second stage, the peaks corresponding to the syllable nuclei are detected. In this work, instead of the peak detection, we perform a mode-shape classification, which is formulated as a supervised binary classification problem - mode-shapes representing the syllabic nuclei as one class and remaining as the other. We use the temporal correlation and selected sub-band correlation (TCSSBC) feature contour and the mode-shapes in the TCSSBC feature contour are converted into a set of feature vectors using an interpolation technique. A support vector machine classifier is used for the classification. Experiments are performed separately using Switchboard, TIMIT and CTIMIT corpora in a five-fold cross validation setup. The average correlation coefficients for the syllable rate estimation turn out to be 0.6761, 0.6928 and 0.3604 for three corpora respectively, which outperform those obtained by the best of the existing peak detection techniques. Similarly, the average F-scores (syllable level) for the syllable nuclei detection are 0.8917, 0.8200 and 0.7637 for three corpora respectively. (C) 2016 Elsevier B.V. All rights reserved.