Adaptive detection in the presence of signal mismatch

The problem of adaptive detection in the situation of signal mismatch is considered; that is, the actual signal steering vector is not aligned with the nominal one. Two novel tunable detectors are proposed. They can control the degree to which the mismatched signals are rejected. Remarkably, it is found that they both cover existing famous detectors as their special cases. More importantly, they possess the constant false alarm rate（CFAR）property and achieve enhanced mismatched signal rejection or improved robustness than their natural competitors. Besides, they can provide slightly better matched signals detection performance than the existing detectors.

Mismatched feature detection with finer granularity for emotional speaker recognition

The shapes of speakers' vocal organs change under their different emotional states, which leads to the deviation of the emotional acoustic space of short-time features from the neutral acoustic space and thereby the degradation of the speaker recognition performance. Features deviating greatly from the neutral acoustic space are considered as mismatched features, and they negatively affect speaker recognition systems. Emotion variation produces different feature deformations for different phonemes, so it is reasonable to build a finer model to detect mismatched features under each phoneme. However, given the difficulty of phoneme recognition, three sorts of acoustic class recognition—phoneme classes, Gaussian mixture model(GMM) tokenizer, and probabilistic GMM tokenizer—are proposed to replace phoneme recognition. We propose feature pruning and feature regulation methods to process the mismatched features to improve speaker recognition performance. As for the feature regulation method, a strategy of maximizing the between-class distance and minimizing the within-class distance is adopted to train the transformation matrix to regulate the mismatched features. Experiments conducted on the Mandarin affective speech corpus(MASC) show that our feature pruning and feature regulation methods increase the identification rate(IR) by 3.64% and 6.77%, compared with the baseline GMM-UBM(universal background model) algorithm. Also, corresponding IR increases of 2.09% and 3.32% can be obtained with our methods when applied to the state-of-the-art algorithm i-vector.

Durbin test with enhanced detection performance to mismatched signal

This paper deals with the problem of detecting a signal whose amplitude is a scaling factor in the presence of homogeneous Gaussian noise with unknown covariance matrix.Since no uniformly most powerful test exists for the problem at hand,we devise and assess a detection strategy based on the well-known Durbin test design criteria.The closed-form expressions for the probabilities of false alarm and detection of the Durbin test are derived,which show that it bears a constant false alarm rate property against the noise covariance matrix.At the analysis stage,the performance of the new receiver is assessed,also in comparison with some classical adaptive detectors,both in matched and in mismatched signal cases.The results show that the proposed detector achieves a visible performance improvement in the presence of severe steering vector mismatch,while maintaining an acceptable detection loss for matched signal.

A combined image matching method for Chinese optical satellite imagery

Image matching is one of the key technologies for digital Earth.This paper presents a combined image matching method for Chinese satellite images.This method includes the following four steps:(1)a modified Wallis-type filter is proposed to determine parameters adaptively while avoiding over-enhancement;(2)a mismatch detection procedure based on a global-local strategy is introduced to remove outliers generated by the Scale-invariant feature transform algorithm,and geometric orientation with bundle block adjustment is employed to compensate for the systematic errors of the position and attitude observations;(3)we design a novel similarity measure(distance,angle and the Normalized Cross-Correlation similarities,DANCC)which considers geometric similarity and textural similarity;and(4)we introduce a hierarchical matching strategy to refine the matching result level by level.Four typical image pairs acquired from Mapping Satellite-1,ZY-102C,ZY-3 and GeoEye-1,respectively,are used for experimental analysis.A comparison with the two current main matching algorithms for satellite imagery confirms that the proposed method is capable of producing reliable and accurate matching results on different terrains from not only Chinese satellite images,but also foreign satellite images.