Alfred Mertins

Automatic speech recognition and speech variability: A review

Major progress is being recorded regularly on both the technology and exploitation of automatic speech recognition (ASR) and spoken language systems. However, there are still technological barriers to flexible solutions and user satisfaction under some circumstances. This is related to several factors, such as the sensitivity to the environment (background noise), or the weak representation of grammatical and semantic knowledge. Current research is also emphasizing deficiencies in dealing with variation naturally present in speech. For instance, the lack of robustness to foreign accents precludes the use by specific populations. Also, some applications, like directory assistance, particularly stress the core recognition technology due to the very high active vocabulary (application perplexity). There are actually many factors affecting the speech realization: regional, sociolinguistic, or related to the environment or the speaker herself. These create a wide range of variations that may not be modeled correctly (speaker, gender, speaking rate, vocal effort, regional accent, speaking style, non-stationarity, etc.), especially when resources for system training are scarce. This paper outlines current advances related to these topics.

Compressed sensing reconstruction for magnetic resonance parameter mapping

Compressed sensing (CS) holds considerable promise to accelerate the data acquisition in magnetic resonance imaging by exploiting signal sparsity. Prior knowledge about the signal can be exploited in some applications to choose an appropriate sparsifying transform. This work presents a CS reconstruction for magnetic resonance (MR) parameter mapping, which applies an overcomplete dictionary, learned from the data model to sparsify the signal. The approach is presented and evaluated in simulations and in in vivo T1 and T2 mapping experiments in the brain. Accurate T1 and T2 maps are obtained from highly reduced data. This model‐based reconstruction could also be applied to other MR parameter mapping applications like diffusion and perfusion imaging. Magn Reson Med, 2010.

Sketch-based image matching Using Angular partitioning

This work presents a novel method for image similarity measure, where a hand-drawn rough black and white sketch is compared with an existing data base of full color images (art works and photographs). The proposed system creates ambient intelligence in terms of the evaluation of nonprecise, easy to input sketched information. The system can then provide the user with options of either retrieving similar images in the database or ranking the quality of the sketch against a given standard, i.e., the original image model. Alternatively, the inherent pattern-matching capability of the system can be utilized to allow detection of distortion in any given real time-image sequences in vision-driven ambient intelligence applications. The proposed method can cope with images containing several complex objects in an inhomogeneous background. Two abstract images are obtained using strong edges of the model image and the morphologically thinned outline of the sketched image. The angular-spatial distribution of pixels in the abstract images is then employed to extract new compact and effective features using the Fourier transform. The extracted features are rotation and scale invariant and robust against translation. Experimental results from seven different approaches confirm the efficacy of the proposed method in both the retrieval performance and the time required for feature extraction and search.

Oversampled cosine-modulated filter banks with arbitrary system delay

Design methods for perfect reconstruction (PR) oversampled cosine-modulated filter banks with integer oversampling factors and arbitrary delay are presented. The system delay, which is an important parameter in real-time applications, can be chosen independently of the prototype lengths. Oversampling gives us additional freedom in the filter design process, which can be exploited to find FIR PR prototypes for oversampled filter banks with much higher stopband attenuations than for critically subsampled filter banks. It is shown that for a given analysis prototype, the PR synthesis prototype is not unique. The complete set of solutions is discussed in terms of the nullspace of a matrix operator. For example, oversampling allows the design of PR filter banks having unidentical prototypes (of equal and unequal lengths) for the analysis and synthesis stage. Examples demonstrate the increased design freedom due to oversampling. Finally, it is shown that PR prototypes being designed for the oversampled case can also serve as almost-PR prototypes for critically subsampled cosine-modulated pseudo QMF banks.

Local Region Descriptors for Active Contours Evolution

Edge-based and region-based active contours are frequently used in image segmentation. While edges characterize small neighborhoods of pixels, region descriptors characterize entire image regions that may have overlapping probability densities. In this paper, we propose to characterize image regions locally by defining local region descriptors (LRDs). These are essentially feature statistics from pixels located within windows centered on the evolving contour, and they may reduce the overlap between distributions. LRDs are used to define general-form energies based on level sets. In general, a particular energy is associated with an active contour by means of the logarithm of the probability density of features conditioned on the region. In order to reduce the number of local minima of such energies, we introduce two novel functions for constructing the energy functional which are both based on the assumption that local densities are approximately Gaussian. The first uses a similarity measure between features of pixels that involves confidence intervals. The second employs a local Markov Random Field (MRF) model. By minimizing the associated energies, we obtain active contours that can segment objects that have largely overlapping global probability densities. Our experiments show that the proposed method can accurately segment natural large images in very short time when using a fast level-set implementation.

Room Impulse Response Shortening/Reshaping With Infinity- and

The purpose of room impulse response (RIR) shortening and reshaping is usually to improve the intelligibility of the received signal by prefiltering the source signal before it is played with a loudspeaker in a closed room. In an alternative, but mathematically equivalent setting, one may aim to postfilter a recorded microphone signal to remove audible echoes. While least-squares methods have mainly been used for the design of shortening/reshaping filters for RIRs until now, we propose to use the infinity- or p-norm as optimization criteria. In our method, design errors will be uniformly distributed over the entire temporal range of the shortened/reshaped global impulse response. In addition, the psychoacoustic property of masking effects is considered during the filter design, which makes it possible to significantly reduce the filter length, compared to standard approaches, without affecting the perceived performance.

p

This paper proposes a general framework of space-time-frequency codes (STFCs) for multi-band orthogonal frequency division multiplexing (MB-OFDM) ultra-wide band (UWB) communications systems. A great similarity between the STFC MB-OFDM UWB systems and conventional wireless complex orthogonal space-time block code (CO STBC) multiple-input multiple-output (MIMO) systems is discovered. This allows us to quantify the pairwise error probability (PEP) of the proposed system and derive the general decoding method for the implemented STFCs. Based on the theoretical analysis results of PEP, we can further quantify the diversity order and coding gain of MB-OFDM UWB systems, and derive the design criteria for STFCs, namely diversity gain criterion and coding gain criterion. The maximum achievable diversity order is found to be the product of the number of transmit antennas, the number of receive antennas, and the FFT size. We also show that all STFCs constructed based on the conventional CO STBCs can satisfy the diversity gain criterion. Various baseband simulation results are shown for the Alamouti code and a code of order 8. Simulation results indicate the significant improvement achieved in the proposed STFC MB-OFDM UWB systems, compared to the conventional MB-OFDM UWB ones.

-Norm Optimization

Multi echo chemical shift‐based water–fat separation methods allow for uniform fat suppression in the presence of main field inhomogeneities. However, these methods require additional scan time for chemical shift encoding. This work presents a method for water–fat separation from undersampled data (CS‐WF), which combines compressed sensing and chemical shift‐based water–fat separation. Undersampling was applied in the k‐space and in the chemical shift encoding dimension to reduce the total scanning time. The method can reconstruct high quality water and fat images in 2D and 3D applications from undersampled data. As an extension, multipeak fat spectral models were incorporated into the CS‐WF reconstruction to improve the water–fat separation quality. In 3D MRI, reduction factors of above three can be achieved, thus fully compensating the additional time needed in three‐echo water–fat imaging. The method is demonstrated on knee and abdominal in vivo data. Magn Reson Med, 2010.

Space-Time-Frequency Code implementation in MB-OFDM UWB communications: Design criteria and performance

Despite the success of the automatic speech recognition framework in its own application field, its adaptation to the problem of acoustic event detection has resulted in limited success. In this paper, instead of treating the problem similar to the segmentation and classification tasks in speech recognition, we pose it as a regression task and propose an approach based on random forest regression. Furthermore, event localization in time can be efficiently handled as a joint problem. We first decompose the training audio signals into multiple interleaved superframes which are annotated with the corresponding event class labels and their displacements to the temporal onsets and offsets of the events. For a specific event category, a random-forest regression model is learned using the displacement information. Given an unseen superframe, the learned regressor will output the continuous estimates of the onset and offset locations of the events. To deal with multiple event categories, prior to the category-specific regression phase, a superframe-wise recognition phase is performed to reject the background superframes and to classify the event superframes into different event categories. While jointly posing event detection and localization as a regression problem is novel, the superior performance on two databases ITC-Irst and UPC-TALP demonstrates the efficiency and potential of the proposed approach.

Compressed sensing for chemical shift‐based water–fat separation

We propose a joint source-channel decoding approach for multidimensional correlated source signals. A Markov random field (MRF) source model is used which exemplarily considers the residual spatial correlations in an image signal after source encoding. Furthermore, the MRF parameters are selected via an analysis based on extrinsic information transfer charts. Due to the link between MRFs and the Gibbs distribution, the resulting soft-input soft-output (SISO) source decoder can be implemented with very low complexity. We prove that the inclusion of a high-rate block code after the quantization stage allows the MRF-based decoder to yield the maximum average extrinsic information. When channel codes are used for additional error protection the MRF-based SISO source decoder can be used as the outer constituent decoder in an iterative source-channel decoding scheme. Considering an example of a simple image transmission system we show that iterative decoding can be successfully employed for recovering the image data, especially when the channel is heavily corrupted