Hongbing Hu

Weighted trust evaluation-based malicious node detection for wireless sensor networks

Deployed in a hostile environment, the individual Sensor Node (SN) of a Wireless Sensor Network (WSN) could be easily compromised by an adversary due to constraints such as limited memory space and computing capability. Therefore, it is critical to detect and isolate compromised nodes in order to avoid being misled by the falsified information injected by adversaries through compromised nodes. However, it is challenging to secure the flat topology networks effectively because of the poor scalability and high communication overhead. On top of a hierarchical WSN architecture, a novel algorithm based on Weighted Trust Evaluation (WTE) to detect malicious nodes for hierarchical sensor networks is proposed in this paper. The hierarchical network can reduce the communication overhead among SNs by utilising clustered topology. The proposed algorithm models a cluster of SNs and detects malicious nodes by examining their weights that represent the reliability of SNs. Through intensive simulations, the accuracy and effectiveness of the proposed detection algorithm are verified.

Dimensionality reduction methods for HMM phonetic recognition

This paper presents two nonlinear feature dimensionality reduction methods based on neural networks for a HMM-based phone recognition system. The neural networks are trained as feature classifiers to reduce feature dimensionality as well as maximize discrimination among speech features. The outputs of different network layers are used for obtaining transformed features. Moreover, the training of the neural networks uses the category information that corresponds to a state in HMMs so that the trained networks can better accommodate the temporal variability of features and obtain more discriminative features in a low dimensional space. Experimental evaluation using the TIMIT database shows that recognition accuracies with the transformed features are slightly higher than those obtained with original features and considerably higher than obtained with linear dimensionality reduction methods. The highest phone accuracy obtained with 39 phone classes and TIMIT was 74.9% using a large number of training iterations based on the state-specific targets.

Tone recognition for continuous accented Mandarin Chinese

In this paper, the ability of human listeners to recognize tones from continuous Mandarin Chinese is evaluated and compared to the accuracy of automatic systems for tone classification and recognition. All tones used for experimentation were extracted from the RASC863 continuous Mandarin Chinese database. The human listeners are native speakers of Mandarin and the automatic methods consist of tone classification using neural networks and tone recognition using Hidden Markov Models. Features used for the automatic methods are a combination of spectral/temporal features, energy contours, and pitch contours. When very little context is used (i.e., vowel segments only) the human and machine performance is comparable. However, as the context interval is increased, the human performance is much better than the best machine performance obtained.

An experimental comparison of fundamental frequency tracking algorithms

“Yet another Algorithm for Pitch Tracking -YAAPT” was published in a 2010 JASA paper (Zahorian and Hu). Although demonstrated to provide high accuracy and noise robustness for fundamental frequency tracking for both studio quality speech and telephone speech, especially as compared to other well-known algorithms (YIN, Praat, RAPT), YAAPT has not been widely used, possibly due to the difficulty of using it and uncertainty about its effectiveness for difficult conditions. Therefore, more work has been done to improve the algorithm and especially to improve its functionality and ease of use as MATLAB functions. In the present paper, the current version of YAAPT is presented, along with clear documentation for using it, both stand alone and as a function to be called by another program. Experimentally, YAAPT is compared with YIN, Praat, RAPT, and a cepstrum method for studio bandwidth speech and telephone speech for a variety of noise conditions. Experiments are conducted with multiple databases, including Am...

Nonlinear Dimensionality Reduction Methods for Use with Automatic Speech Recognition

For nearly a century, researchers have investigated and used mathematical techniques for reducing the dimensionality of vector valued data used to characterize categorical data with the goal of preserving “information” or discriminability of the different categories in the reduced dimensionality data. The most established techniques are Principal Components Analysis (PCA) and Linear Discriminant Analysis (LDA) (Jolliffe, 1986; Wang & Paliwal, 2003). Both PCA and LDA are based on linear, i.e. matrix multiplication, transformations. For the case of PCA, the transformation is based on minimizing mean square error between original data vectors and data vectors that can be estimated from the reduced dimensionality data vectors. For the case of LDA, the transformation is based on minimizing a ratio of “between class variance” to “within class variance” with the goal of reducing data variation in the same class and increasing the separation between classes. There are newer versions of these methods such as Heteroscedastic Discriminant Analysis (HDA) (Kumar & Andreou, 1998; Saon et al., 2000). However, in all cases certain assumptions are made about the statistical properties of the original data (such as multivariate Gaussian); even more fundamentally, the transformations are restricted to be linear. In this chapter, a class of nonlinear transformations is presented both from a theoretical and experimental point of view. Theoretically, the nonlinear methods have the potential to be more “efficient” than linear methods, that is, give better representations with fewer dimensions. In addition, some examples are shown from experiments with Automatic Speech Recognition (ASR) where the nonlinear methods in fact perform better, resulting in higher ASR accuracy than obtained with either the original speech features, or linearly reduced feature sets. Two nonlinear transformation methods, along with several variations, are presented. In one of these methods, referred to as nonlinear PCA (NLPCA), the goal of the nonlinear transformation is to minimize the mean square error between features estimated from reduced dimensionality features and original features. Thus this method is patterned after PCA. In the second method, referred to as nonlinear LDA (NLDA), the goal of the nonlinear transformation is to maximize discriminability of categories of data. Thus the method is patterned after LDA. In all cases, the dimensionality reduction is accomplished with a Neural Network (NN), which internally encodes data with a reduced number of dimensions. The differences in the methods depend on error criteria used to train the network, the architecture of the network, and the extent to which the reduced dimensions are “hidden” in the neural network.

A further comparison of fundamental frequency tracking algorithms

“Yet another Algorithm for Pitch Tracking -YAAPT” was published in a 2008 JASA paper (Zahorian and Hu), with additional experimental results presented at the fall 2012 ASA meeting in Kansas City. The results presented in both the journal paper and at the fall 2012 meeting indicated that YAAPT generally has lower error rates than other widely used pitch trackers (YIN, PRAAT, and RAPT). However, even YAAPT-created pitch tracks had significant “large” errors (pitch doubling and pitch-halving) for both clean and noisy speech. Recently additional post-processing heuristics have been incorporated to reduce the incidence of these type errors—thus reducing the need for hand correcting pitch tracks for situations where extremely accurate tracks are desired. For the case of an all-voiced track, interpolation through unvoiced intervals has been improved. The updated version of YAAPT is presented along with experimental results. The experiments are conducted with multiple databases, including British English, America...

Tone recognition in continuous Mandarin Chinese

Tones are important characteristics of Mandarin Chinese for conveying lexical meaning. Thus tone recognition, either explicit or implicit, is required for automatic recognition of Mandarin. Most literature on machine recognition of tones is based on syllables spoken in isolation or even machine-synthesized voices. This is likely due to the difficulty of recognizing tones from syllables extracted from conversational speech, even for native speakers of Mandarin. In this study, human and machine recognition of tones from continuous speech is evaluated and compared for four conditions: 1, vowel portions of syllables; 2, complete syllables; 3, syllable pairs; 4, groupings of three syllables. The syllables are extracted from the RASC-863 continuous Mandarin Chinese database. The human listeners are all native speakers of Mandarin. The automatic recognition is based on either Hidden Markov Models, or neural networks, and a combination of spectral/temporal, energy, and pitch features. When very little context is ...

Time/frequency resolution of acoustic features for automatic speech recognition.

The underlying assumption for spectral/temporal features for use in automatic speech recognition is that the frequency resolution should be emphasized in relation to temporal resolution. Accordingly, Mel frequency cepstral coefficients are typically computed using an approximately 25‐ms frame length with a 10‐ms frame spacing, and using 3–5 frames to represent temporal derivative information. In phone recognition experiments based on the TIMIT database using discrete cosine transform coefficients for spectral information and discrete cosine series coefficients for their temporal evolution, substantially higher phone accuracies were obtained with much shorter frame lengths (8 ms), much shorter frame spacings (2 ms), and much longer time intervals for capturing spectral tracks (on the order of 500 ms). Experimental results with various conditions are given for phone recognition using the TIMIT database. The implications of these results are that spectral/temporal evolution features, emphasizing the temporal...