Jeff Siu-Kei Au-Yeung

Learn More
The introduction of Aurora 4 tasks provides a standard database and methodology for comparing the effectiveness of different robust algorithms on LVCSR. One important issue on Aurora 4 tasks is the computation time involved in evaluating different test conditions. In this paper we show that by employing HTK as the recognition frontend and backend on Aurora(More)
With the advance in semiconductor memory and the availability of very large speech corpora (of hundreds to thousands of hours of speech), we would like to revisit the use of discrete hidden Markov model (DHMM) in automatic speech recognition. To estimate the discrete density in a DHMM state, the acoustic space is divided into bins and one simply count the(More)
In this letter, we propose a novel video encryption technique that is used to achieve partial encryption where an annoying video can still be reconstructed even without the security key. In contrast to the existing methods where the encryption usually takes place at the entropy-coding stage or the bit-stream level, our proposed scheme embeds the encryption(More)
It has been demonstrated in our earlier works [1, 2] that perceptual video encryption can be effectively achieved by using multiple transforms where the block size 4×4 has been considered. In this paper, we study the extension to the transforms of size 8×8. In this case, a more complex flow-graph structure is resulted, thus leading to a larger room for(More)
Perceptual video encryption, in which a user can still obtain some visible video contents (but at a very annoying quality) even without knowing the encryption key, is becoming more and more interesting in video applications such as video-on-demand (VoD) and pay-TV. Since not all visual information is corrupted, the quality assessment methods that are used(More)
Traditionally, any 2D transform (such as 2D DCT) is implemented through two separable 1D transforms along the vertical and horizontal dimensions. Such a framework is however not most suitable for a 2D directional source in which the dominant directional information is neither horizontal nor vertical. In this letter, we attempt to determine the R-D(More)
Polynomial segment models (PSMs), which are generalization of the hidden Markov models (HMMs), have opened an alternative research direction for speech recognition. However, they have been limited by their computational complexity. Traditionally, any change in PSM segment boundary requires likelihood recomputation of all the frames within the segment. This(More)