Volume 22, Issue 2

This article presents an overview of the single-channel dereverberation methods suitable for distant speech recognition (DSR) application. The dereverberation methods are mainly classified based on the domain of enhancement of speech signal captured by a distant microphone. Many single-channel speech enhancement methods focus on either denoising or dereverberating the distorted speech signal. There are very few methods that consider both noise and reverberation effects. Such methods are discussed under a multistage approach in this article. The article concludes with a hypothesis that the methods that do not require an a priori reverberation impulse response is desirable in varying the environmental conditions for DSR applications such as intelligent home and office environments, humanoid robots, and automobiles rather than the methods that require an a priori reverberation impulse response.

Proxy signature and group signature are two basic cryptographic primitives. Due to their valuable characteristics, many schemes have been put forward independently and they have been applied in many practical scenarios up to the present. However, with the development of electronic commerce, many special requirements come into being. In this article, we put forward the concept of group–proxy signature, which integrates the merits of proxy signature and group signature for the first time. We also demonstrate how to apply our scheme to construct an electronic cash system. The space, time, and communication complexities of the relevant parameters and processing procedures are independent of group size. Our demonstration of the concrete group–proxy signature scheme shows that the concepts brought forward by us are sure to elicit much consideration in the future.

Vowel phonemes are a part of any acoustic speech signal. Vowel sounds occur in speech more frequently and with higher energy. Therefore, vowel phoneme can be used to extract different amounts of speaker discriminative information in situations where acoustic information is noise corrupted. This article presents an approach to identify a speaker using the vowel sound segmented out from words spoken by the speaker. The work uses a combined self-organizing map (SOM)- and probabilistic neural network (PNN)-based approach to segment the vowel phoneme. The segmented vowel is later used to identify the speaker of the word by matching the patterns with a learning vector quantization (LVQ)-based code book. The LVQ code book is prepared by taking features of clean vowel phonemes uttered by the male and female speakers to be identified. The proposed work formulates a framework for the design of a speaker-recognition model of the Assamese language, which is spoken by ∼3 million people in the Northeast Indian state of Assam. The experimental results show that the segmentation success rates obtained using a SOM-based technique provides an increase of at least 7% compared with the discrete wavelet transform-based technique. This increase contributes to the improvement in overall performance of speaker identification by ∼3% compared with earlier related works.

This article presents a novel control approach, hybrid neuro-fuzzy (HNF), for the load frequency control (LFC) of a four-area interconnected power system. The advantage of this controller is that it can handle nonlinearities, and at the same time, it is faster than other existing controllers. The effectiveness of the proposed controller in increasing the damping of local and inter-area modes of oscillation is demonstrated in a four-area interconnected power system. Areas 1 and 2 consist of a thermal reheat power plant, whereas Areas 3 and 4 consist of a hydropower plant. Performance evaluation is carried out by using fuzzy, artificial neural network (ANN), adaptive neuro-fuzzy inference system, and conventional proportional and integral (PI) control approaches. Four different models with different controllers are developed and simulated, and performance evaluations are carried out with said controllers. The result shows that the intelligent HNF controller has improved dynamic response and is at the same time faster than ANN, fuzzy, and conventional PI controllers.

This article presents a novel full-reference (FR) image quality assessment (QA) algorithm by depicting the sub-band characteristics in the wavelet domain. The proposed image quality assessment method is based on energy estimation in the wavelet-transformed image. Image QA is achieved by applying a multilevel wavelet decomposition on both the original and the enhanced image. Next, the wavelet energy (WE) and vector are computed to obtain the percentage of the energy that corresponds to the approximation and the details, respectively. Further, the approximate and detailed energy levels of both the original and the enhanced images are compared to formulate an image quality assessment. Numerous experiments are conducted on a dozen of image enhancement algorithms. The results presented show that the image with poor contrast in the foreground than the background has continuous regular coefficient values. The probability density function for such an image has a relatively lower WE and skewness compared with the background. The proposed scheme not only evaluates the global information of an image but also estimates the fine, detailed changes in an enhanced image. Thus, the proposed metric serves as an objective and effective FR criterion for color image QA. The experimental results presented confirm that the proposed WE metric is an efficient and useful metric for evaluating the quality of the color image enhancement.

The presence of vegetation on railway tracks (amongst other issues) threatens track safety and longevity. However, vegetation inspections in Sweden (and elsewhere in the world) are currently being carried out manually. Manually inspecting vegetation is very slow and time consuming. Maintaining an even quality standard is also very difficult. A machine vision-based approach is therefore proposed to emulate the visual abilities of the human inspector. Work aimed at detecting vegetation on railway tracks has been split into two main phases. The first phase is aimed at detecting vegetation on the tracks using appropriate image analysis techniques. The second phase is aimed at detecting the rails in the image to determine the cover of vegetation that is present between the rails as opposed to vegetation present outside the rails. Results achieved in the current work indicate that the machine vision approach has performed reasonably well in detecting the presence/absence of vegetation on railway tracks when compared with a human operator.

Face detection plays important roles in many applications such as human–computer interaction, security and surveillance, face recognition, etc. This article presents an intelligent enhanced fused approach for face recognition based on the Voronoi diagram (VD) and wavelet moment invariants. Discrete wavelet transform and moment invariants are used for feature extraction of the facial face. Finally, VD and the dual tessellation (Delaunay triangulation, DT) are used to locate and detect original face images. Face recognition results based on this new fusion are promising in the state of the art.