Two stage iterative wiener filtering for speech enhancement

We formulate a two-stage Iterative Wiener filtering (IWF) approach to speech enhancement, bettering the performance of constrained IWF, reported in literature. The codebook constrained IWF (CCIWF) has been shown to be effective in achieving convergence of IWF in the presence of both stationary and non-stationary noise. To this, we include a second stage of unconstrained IWF and show that the speech enhancement performance can be improved in terms of average segmental SNR (SSNR), Itakura-Saito (IS) distance and Linear Prediction Coefficients (LPC) parameter coincidence. We also explore the tradeoff between the number of CCIWF iterations and the second stage IWF iterations.

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

Online Unsupervised Pattern Discovery in Speech Using Parallelization

Segmental dynamic time warping (DTW) has been demonstrated to be a useful technique for finding acoustic similarity scores between segments of two speech utterances. Due to its high computational requirements, it had to be computed in an offline manner, limiting the applications of the technique. In this paper, we present results of parallelization of this task by distributing the workload in either a static or dynamic way on an 8-processor cluster and discuss the trade-offs among different distribution schemes. We show that online unsupervised pattern discovery using segmental DTW is plausible with as low as 8 processors. This brings the task within reach of today's general purpose multi-core servers. We also show results on a 32-processor system, and discuss factors affecting scalability of our methods.

Speech Enhancement using Intra-frame Dependency in DCT Domain

In this paper, we present a new speech enhancement approach, that is based on exploiting the intra-frame dependency of discrete cosine transform (DCT) domain coefficients. It can be noted that the existing enhancement techniques treat the transformdomain coefficients independently. Instead of this traditional approach of independently processing the scalars, we split the DCT domain noisy speech vector into sub-vectors and each sub-vector is enhanced independently. Through this sub-vector based approach, the higher dimensional enhancement advantage, viz. non-linear dependency, is exploited. In the developed method, each clean speech sub-vector is modeled using a Gaussian mixture (GM) density. We show that the proposed Gaussian mixture model (GMM) based DCT domain method, using sub-vector processing approach, provides better performance than the conventional approach of enhancing the transform domain scalar components independently. Performance improvement over the recently proposed GMM based time domain approach is also shown.

GMM basedbayesian approach to speech enhancement in signal/transform domain

Considering a general linear model of signal degradation, by modeling the probability density function (PDF) of the clean signal using a Gaussian mixture model (GMM) and additive noise by a Gaussian PDF, we derive the minimum mean square error (MMSE) estimator.The derived MMSE estimator is non-linear and the linear MMSE estimator is shown to be a special case. For speech signal corrupted by independent additive noise, by modeling the joint PDF of time-domain speech samples of a speech frame using a GMM, we propose a speech enhancement method based on the derived MMSE estimator. We also show that the same estimator can be used for transform-domain speech enhancement.

High-Rate Vector Quantization for Noisy Channels With Applications to Wideband Speech Spectrum Compression

This paper considers the high-rate performance of source coding for noisy discrete symmetric channels with random index assignment (IA). Accurate analytical models are developed to characterize the expected distortion performance of vector quantization (VQ) for a large class of distortion measures. It is shown that when the point density is continuous, the distortion can be approximated as the sum of the source quantization distortion and the channel-error induced distortion. Expressions are also derived for the continuous point density that minimizes the expected distortion. Next, for the case of mean squared error distortion, a more accurate analytical model for the distortion is derived by allowing the point density to have a singular component. The extent of the singularity is also characterized. These results provide analytical models for the expected distortion performance of both conventional VQ as well as for channel-optimized VQ. As a practical example, compression of the linear predictive coding parameters in the wideband speech spectrum is considered, with the log spectral distortion as performance metric. The theory is able to correctly predict the channel error rate that is permissible for operation at a particular level of distortion.

Decision tree design and applications in speech processing

The design and operation of the minimum cost classifier, where the total cost is the sum of the measurement cost and the classification cost, is computationally complex. Noting the difficulties associated with this approach, decision tree design directly from a set of labelled samples is proposed in this paper. The feature space is first partitioned to transform the problem to one of discrete features. The resulting problem is solved by a dynamic programming algorithm over an explicitly ordered state space of all outcomes of all feature subsets. The solution procedure is very general and is applicable to any minimum cost pattern classification problem in which each feature has a finite number of outcomes. These techniques are applied to (i) voiced, unvoiced, and silence classification of speech, and (ii) spoken vowel recognition. The resulting decision trees are operationally very efficient and yield attractive classification accuracies.

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.

A stochastic dynamical system for image segmentation

Image segmentation is formulated as a stochastic process whose invariant distribution is concentrated at points of the desired region. By choosing multiple seed points, different regions can be segmented. The algorithm is based on the theory of time-homogeneous Markov chains and has been largely motivated by the technique of simulated annealing. The method proposed here has been found to perform well on real-world clean as well as noisy images while being computationally far less expensive than stochastic optimisation techniques

An approach to multi-temporal MODIS image analysis using image classification and segmentation

This paper discusses an approach for river mapping and flood evaluation based on multi-temporal time series analysis of satellite images utilizing pixel spectral information for image classification and region-based segmentation for extracting water-covered regions. Analysis of MODIS satellite images is applied in three stages: before flood, during flood and after flood. Water regions are extracted from the MODIS images using image classification (based on spectral information) and image segmentation (based on spatial information). Multi-temporal MODIS images from ``normal'' (non-flood) and flood time-periods are processed in two steps. In the first step, image classifiers such as Support Vector Machines (SVMs) and Artificial Neural Networks (ANNs) separate the image pixels into water and non-water groups based on their spectral features. The classified image is then segmented using spatial features of the water pixels to remove the misclassified water. From the results obtained, we evaluate the performance of the method and conclude that the use of image classification (SVM and ANN) and region-based image segmentation is an accurate and reliable approach for the extraction of water-covered regions. (c) 2012 COSPAR. Published by Elsevier Ltd. All rights reserved.

A UNIFIED APPROACH FOR OPTIMIZATION OF SNAKUSCULES AND OVUSCULES

Automated image segmentation techniques are useful tools in biological image analysis and are an essential step in tracking applications. Typically, snakes or active contours are used for segmentation and they evolve under the influence of certain internal and external forces. Recently, a new class of shape-specific active contours have been introduced, which are known as Snakuscules and Ovuscules. These contours are based on a pair of concentric circles and ellipses as the shape templates, and the optimization is carried out by maximizing a contrast function between the outer and inner templates. In this paper, we present a unified approach to the formulation and optimization of Snakuscules and Ovuscules by considering a specific form of affine transformations acting on a pair of concentric circles. We show how the parameters of the affine transformation may be optimized for, to generate either Snakuscules or Ovuscules. Our approach allows for a unified formulation and relies only on generic regularization terms and not shape-specific regularization functions. We show how the calculations of the partial derivatives may be made efficient thanks to the Green's theorem. Results on synthesized as well as real data are presented.

Fast Likelihood Computation in Speech Recognition using Matrices

Acoustic modeling using mixtures of multivariate Gaussians is the prevalent approach for many speech processing problems. Computing likelihoods against a large set of Gaussians is required as a part of many speech processing systems and it is the computationally dominant phase for Large Vocabulary Continuous Speech Recognition (LVCSR) systems. We express the likelihood computation as a multiplication of matrices representing augmented feature vectors and Gaussian parameters. The computational gain of this approach over traditional methods is by exploiting the structure of these matrices and efficient implementation of their multiplication. In particular, we explore direct low-rank approximation of the Gaussian parameter matrix and indirect derivation of low-rank factors of the Gaussian parameter matrix by optimum approximation of the likelihood matrix. We show that both the methods lead to similar speedups but the latter leads to far lesser impact on the recognition accuracy. Experiments on 1,138 work vocabulary RM1 task and 6,224 word vocabulary TIMIT task using Sphinx 3.7 system show that, for a typical case the matrix multiplication based approach leads to overall speedup of 46 % on RM1 task and 115 % for TIMIT task. Our low-rank approximation methods provide a way for trading off recognition accuracy for a further increase in computational performance extending overall speedups up to 61 % for RM1 and 119 % for TIMIT for an increase of word error rate (WER) from 3.2 to 3.5 % for RM1 and for no increase in WER for TIMIT. We also express pairwise Euclidean distance computation phase in Dynamic Time Warping (DTW) in terms of matrix multiplication leading to saving of approximately of computational operations. In our experiments using efficient implementation of matrix multiplication, this leads to a speedup of 5.6 in computing the pairwise Euclidean distances and overall speedup up to 3.25 for DTW.