This paper presents an error shaping technique for line spectrum frequency (LSF) vector quantization. The error shaping technique based on the weighted logarithm spectral distortion (WLSD) measure can be used for shaping the spectral distortion distribution of quantization error into any different curve depending on what kind of weighting function is used. However, the high computational complexity of the WLSD measure deters this error shaping technique from practical use. To solve this problem, we approximate the WLSD measure by the quadratically weighted measure or the weighted mean squared error (WMSE) measure and propose an optimal error shaping technique of LSF vector quantization. In this proposed error shaping technique, the optimal WMSE weights (i.e., the optimal weights of LSF parameters) are determined based on the theoretical analysis of the WLSD measure. Three experiments are performed to check the performance of the proposed error shaping technique. One experiment is set up by incorporating human perception into the LSF quantization and another is set up by emphasizing the human-sensitivity frequency band in lower frequency bandwidth 0-3 kHz. In the third experiment, we apply the proposed error shaping technique to the LSF quantization of a CELP coder to test how it affects the overall speech quality in an actual speech coding algorithm.

Among various kinds of speech features, the two-dimensional (2-D) cepstrum (TDC) is a special one, which can simultaneously represent several types of information contained in the speech waveform: static and dynamic features, as well as global and fine frequency structures. Analysis results show that the coefficients located at lower indexes portion of the TDC matrix seem to be more significant than others. Hence, to represent an utterance only some TDC coefficients need to be selected to form a feature vector instead of the sequence of feature vectors. It has the advantages of simple computation and less storage space. However, our experiments show that the selection of TDC coefficients is quite sensitive to background noise. In order to solve this problem, we propose the GA-based M-TDC (modified TDC) method in this paper to improve the representativeness and robustness of the selected TDC coefficients in noisy environments. The M-TDC differs from the standard TDC by the use of filters to remove the noise components. Furthermore, in the GA-based M-TDC method, we apply the genetic algorithms (GAs) to find the robust coefficients in the M-TDC matrix. From the experiments with five noise types, we find that the GA-based M-TDC method has better recognition results than the original TDC approaching noisy environments.

Motion recognition has received increasing attention in recent years owing to heightened demand for computer vision in many domains, including the surveillance system, multimodal human computer interface, and traffic control system. Most conventional approaches classify the motion recognition task into partial feature extraction and time-domain recognition subtasks. However, the information of motion resides in the space-time domain instead of the time domain or space domain independently, implying that fusing the feature extraction and classification in the space and time domains into a single framework is preferred. Based on this notion, this work presents a novel Space-Time Delay Neural Network (STDNN) capable of handling the space-time dynamic information for motion recognition. The STDNN is unified structure, in which the low-level spatiotemporal feature extraction and high-level space-time-domain recognition are fused. The proposed network possesses the spatiotemporal shift-invariant recognition ability that is inherited from the time delay neural network (TDNN) and space displacement neural network (SDNN), where TDNN and SDNN are good at temporal and spatial shift-invariant recognition, respectively. In contrast to multilayer perceptron (MLP), TDNN, and SDNN, STDNN is constructed by vector-type nodes and matrix-type links such that the spatiotemporal information can be accurately represented in a neural network. Also evaluated herein is the performance of the proposed STDNN via two experiments. The moving Arabic numerals (MAN) experiment simulates the object's free movement in the space-time domain on image sequences. According to these results, STDNN possesses a good generalization ability with respect to the spatiotemporal shift-invariant recognition. In the lipreading experiment, STDNN recognizes the lip motions based on the inputs of real image sequences. This observation confirms that STDNN yields a better performance than the existing TDNN-based system, particularly in terms of the generalization ability. In addition to the lipreading application, the STDNN can be applied to other problems since no domain-dependent knowledge is used in the experiment.

In this paper, we propose a speech recognition algorithm which utilizes hidden Markov models (HMM) and Viterbi algorithm for segmenting the input speech sequence, such that the variable-dimensional speech signal is converted into a fixed-dimensional speech signal, called TN vector. We then use the fuzzy perceptron to generate hyperplanes which separate patterns of each class from the others. The proposed speech recognition algorithm is easy for speaker adaptation when the idea of "supporting pattern" is used. The supporting patterns are those patterns closest to the hyperplane. When a recognition error occurs, we include all the TN vectors of the input speech sequence with respect to the segmentations of all HMM models as the supporting patterns. The supporting patterns are then used by the fuzzy perceptron to tune the hyperplane that can cause correct recognition, and also tune the hyperplane that resulted in wrong recognition. Since only two hyperplane need to be tuned for a recognition error, the proposed adaptation scheme is time-economic and suitable for on-line adaptation. Although the adaptation scheme cannot ensure to correct the wrong recognition right after adaptation, the hyperplanes are tuned in the direction for correct recognition iteratively and the speed of adaptation can be adjusted by a "belief" parameter set by the user. Several examples are used to show the performance of the proposed speech recognition algorithm and the speaker adaptation scheme.