A new, likelihood-based non-uniform allocation of Gaussian kernels in scalar (feature) dimension is proposed to compress complex, Gaussian mixture-based, continuous density HMMs into computationally efficient, small footprint models. Different from the objective of the previously proposed Kullback-Leibler divergence-based (KLD-based) allocation (Li et al., 2005), which is to make a better representation of the original model, the objective of the likelihood-based approach is to make the current compressed model be a better representation of the training data. It is implemented based on the unequal likelihood contributions of different features with uniform representation resolutions. Our experiments on the resource management database show that likelihood-based allocation outperforms uniform allocation and KLD-based non-uniform allocation due to its better representation of the training data.

A new, state divergence-based algorithm is proposed in this paper to determine the number of Gaussian components of each state in continuous density HMM by maximizing the between-state divergence. The unscented transform based approximation of the Kullback-Leibler divergence is adopted to measure the between-state model divergence to direct the determination. Due to the advantage of being more discriminative, the proposed approach can lead to more compact HMM. Our experimental evaluation shows that compared with the conventional Bayesian Information Criterion based determination (which is better than the uniform determination), the presented method can reduce the total number of Gaussian components to about 63%, while it results in almost negligible degradation of the recognition performance.

We propose an algorithm for optimal clustering and nonuniform allocation of Gaussian kernels in scalar (feature) dimension to compress complex, Gaussian mixture-based, continuous density HMMs into computationally efficient, small footprint models. The symmetric Kullback-Leibler divergence (KLD) is used as the universal distortion measure and it is minimized in both kernel clustering and allocation procedures. The algorithm was tested on the resource management (RM) database. The original context-dependent HMMs can be compressed to any resolution, measured by the total number of clustered scalar kernel components. Good trade-offs between the recognition performance and model complexities have been obtained; the HMM can be compressed to 15-20% of the original model size, which needs 1-5% of multiplication/division operations, and results in almost negligible recognition performance degradation.

In this paper, the minimum classification error (MCE) method is extended to optimize both linear discriminant analysis (LDA) transformation and the classification parameters for dimensionality reduction. Firstly, under the HMM-based continuous speech recognition (CSR) framework, we use the MCE criterion to optimize the conventional dimensionality reduction method, which uses LDA to transform the standard MFCC. Then, a new dimensionality reduction method is proposed. In the new method, the combination of discrete cosine transform (DCT) and LDA, as used in the conventional method, is replaced by a single LDA transformation, which is optimized according to MCE criterion along with the classification parameters. Experimental results on TiDigits show that even when the feature dimension is reduced to 14, the performance of this new method is as good as that of the MCE-trained system using 39 dimension MFCC. It also outperforms our MCE-optimized conventional dimensionality reduction method.

The aim of this paper is to detecting inter-annual variations of vegetation growth based on ten-day 8 km NOAA/AVHRR NDVI images from 1983 to 1999 taken the temperate steppe, located at the northern China, as study area. Uniform image processing methods were employed to pre-process the multi-temporal NDVI images. The results shown, climate change presented warming and fluctuant precipitation over the past 17 years in this region. Annual maximum NDVI reflect preferably climate change, it increased and it's outset moved up in the past 17 years. An advance of onset and an extension of growth season length were detected.