Automatic speech recognition by computers can provide humans with the most convenient method to communicate with computers. Because the Chinese language is not alphabetic and input of Chinese characters into computers is very difficult, Mandarin speech recognition is very highly desired. Recently, high performance speech recognition systems have begun to emerge from research institutes. However...

A number of biometric techniques have been used for personal identification such as face recognition, fingerprint recognition, voice recognition and signature recognition. However signature verification is most widely used. Signature being the most prominent handwritten proof of identity is used for authentication of documents in the fields of financial, commercial and legal transactions which ...

Various methods could deal well with frontal view face recognition if there were sufficient number of representative training samples. However, few of them worked well if only single training image per person was available. This study proposes a face recognition method based on artificial immune networks and principal component analysis to solve the one training sample problem. The performance ...

One challenge in spoken language recognition is the availability of training data. In this paper, we propose a virtual example construction method to derive artificial training examples from the existing training data. Using the proposed method, both target virtual examples and non-target virtual examples can be derived from the available training samples. An iterative virtual example selection...

This paper is concerned with the robust endpoint detection and noisy speech recognition over wireless network. Firstly, the MLP-based and GMM-based endpoint detection incorporated with data contamination and continuous spectral subtraction techniques were investigated. Then, for noisy wireless speech recognition, a combined technique of data contamination and robust training was proposed to sep...

In this paper, we systematically study the effect of poorly registered faces on the training and inferring stages of traditional face recognition algorithms. We then propose a novel multiple-instance based subspace learning scheme for face recognition. In this approach, we iteratively update the subspace training instances according to diverse densities, using class-balanced supervised clusteri...